Multi-dimensional agricultural enterprise data intelligent matching and sorting method and system

Abstract

The present invention relates to the technical field of agricultural product supply chain optimization, and discloses a multi-dimensional agricultural enterprise data intelligent matching and sorting method and system, the method comprising the following steps: collecting matching parameters of agricultural enterprises and performing data preprocessing; calculating the matching degree of agricultural enterprises based on matching parameters; obtaining the target output of agricultural products of producers, the raw material supply of each supplier, and the purchase volume of agricultural products of each seller, and calculating the expected output of agricultural products through a neural network model; generating a supply chain and evaluating the stability of the supply chain; and recommending raw material suppliers and sellers to producers based on the stability of the supply chain. The present invention can optimize the composition and matching relationship of the supply chain, improve the efficiency and stability of the supply chain, reduce the loss and risk of agricultural products in the circulation link, reduce the cost of the supply chain, and promote the healthy development of the agricultural industry.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural product supply chain optimization, and in particular to a multi-dimensional agricultural enterprise data intelligent matching and sorting method and system. Background Art

[0002] As a bridge between agricultural product producers and consumers, the agricultural product supply chain can ensure the quality and safety of agricultural products, improve market competitiveness and promote agricultural modernization. At present, the agricultural product supply chain has initially formed a relatively complete system, including raw material procurement, production and processing, warehousing and logistics, sales and distribution, etc. Each link is closely connected and coordinated, which improves the efficiency of agricultural product circulation.

[0003] At present, the agricultural product supply chain is gradually shifting from empirical decision-making to data-driven decision-making. Some existing technologies collect and integrate data information of agricultural products and use optimization decision-making models to determine the best supply chain strategy. This method can help managers evaluate the status of the supply chain more objectively and accurately and make decisions based on data analysis. Some existing technologies can timely detect abnormal situations of agricultural products and their supply chains by establishing a real-time life cycle of the supply chain and setting associated values ​​for node monitoring. This real-time monitoring can effectively improve the response speed of the supply chain and reduce the loss of agricultural products. However, the current supply chain of agricultural products still has problems such as insufficient stability, information asymmetry, and low matching between suppliers and sellers.

[0004] For example, the patent application with the publication number CN115879645A discloses a method and device for optimizing decision-making for agricultural product supply chain, the method comprising: S1, obtaining initial data information of agricultural products; S2, integrating the initial data information to obtain integrated agricultural product data information; S3, according to the integrated agricultural product data information, using a pre-built agricultural product supply chain optimization decision model to determine the supply chain of the agricultural product. Compared with the traditional decision-making based on farmers' experience, the use of this invention can help managers make better decisions for the agricultural product supply chain.

[0005] For example, the patent application with publication number CN117495019A discloses a method and system for coordinated scheduling of agricultural products based on the agricultural product supply chain, which relates to the field of product scheduling technology. The method includes: establishing the real-time life cycle of the supply chain of agricultural products, then setting the initial node association value, performing node monitoring, generating abnormal reporting data, matching the initial node association value, performing radiation aggregation analysis of the central node according to the matching results, establishing a solution space, performing quality demand prediction and screening according to the solution space, generating screening results, performing multi-dimensional decision evaluation, and finally performing intra-chain scheduling of the supply chain. This application mainly solves the problem that scheduling and optimization cannot be performed according to the characteristics of agricultural products themselves, the response speed of the supply chain is slow, and the quality of agricultural products is reduced. By applying the prediction and screening results, the scheduling plan is determined, thereby achieving better social and economic benefits. The optimized operation of the agricultural product supply chain is realized, and the efficiency and response speed are improved.

[0006] The above patents all have the problems raised by this background technology: insufficient supply chain stability, information asymmetry, and low matching between suppliers and sellers.

[0007] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention

[0008] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide a multi-dimensional agricultural enterprise data intelligent matching and sorting method and system, which can improve the efficiency and stability of the supply chain by optimizing the composition and matching relationship of the supply chain, reduce the loss and risk of agricultural products in the circulation link, ensure the freshness and safety of agricultural products, reduce supply chain costs, and promote the healthy development of the agricultural industry.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0010] On the one hand, the present invention provides a multi-dimensional agricultural enterprise data intelligent matching and sorting method, comprising the following steps: S1: collecting matching parameters of agricultural enterprises, including matching parameters of raw material suppliers and matching parameters of sellers, and performing data preprocessing;

[0011] S2: Calculating the matching degree of agricultural enterprises based on the matching parameters, including the matching degree of each raw material supplier and the matching degree of each seller;

[0012] S3: Obtain the target output of agricultural products of the producer, the raw material supply of each supplier, the purchase volume of agricultural products of each seller, and calculate the expected output of agricultural products through the neural network model;

[0013] S4: Generate a supply chain and evaluate the stability of the supply chain based on the expected output, target output, agricultural product purchase volume, and the matching degree of agricultural enterprises;

[0014] S5: Recommend raw material suppliers and sellers to manufacturers based on the stability of the supply chain.

[0015] As a preferred solution of the multi-dimensional agricultural enterprise data intelligent matching and sorting method of the present invention, the matching parameters of the raw material supplier include supply capacity parameters, sales volume parameters, order completion rate, inventory turnover index, and price competitiveness index; wherein:

[0016] The supply capacity parameter is the ratio of the output of raw materials of any raw material supplier to the average output of raw materials, and the average output of raw materials is the average output of raw materials of all raw material suppliers;

[0017] The sales volume parameter is the ratio of the sales volume of raw materials of any raw material supplier to the average sales volume of raw materials, and the average sales volume of raw materials is the average sales volume of raw materials of all raw material suppliers;

[0018] The order completion rate is the ratio of the valid orders completed by any raw material supplier to the total number of orders;

[0019] The inventory turnover index is the average inventory turnover days of any raw material supplier;

[0020] The price competitiveness index is the ratio of the price quoted by any raw material supplier to the average price quoted by the raw materials, and the average price quoted by the raw materials is the average of the price quoted by all raw material suppliers.

[0021] As a preferred solution of the multi-dimensional agricultural enterprise data intelligent matching and sorting method of the present invention, the matching parameters of the sellers include market share parameters, sales volume parameters, payment cycle parameters, and distance cost parameters; wherein:

[0022] The market share parameter is the market share of any seller in the market for the agricultural products provided by the producer;

[0023] The sales volume parameter is the ratio of the sales volume of agricultural products provided by any seller to the average sales volume of agricultural products;

[0024] The payment cycle parameter is the ratio of the regular payment cycle of any seller to the average of the regular payment cycles of all sellers;

[0025] The distance cost parameter is expressed by the time required for the producer to transport the agricultural products to any seller;

[0026] The data preprocessing includes missing value processing, outlier detection and processing, and consistency verification.

[0027] As a preferred solution of the multi-dimensional agricultural enterprise data intelligent matching and sorting method of the present invention, the calculation formula of the matching degree of each raw material supplier is as follows:

[0028] ;

[0029] in, represents the matching degree of the i-th raw material supplier, the value range of i is 1, 2, ..., m, where m is the number of raw material suppliers;

[0030] represents the supply capacity parameter of the i-th raw material supplier; represents the sales volume parameter of the i-th raw material supplier; represents the order completion rate of the i-th raw material supplier; represents the inventory turnover index of the i-th raw material supplier; Represents the price competitiveness index of the i-th raw material supplier.

[0031] As a preferred solution of the multi-dimensional agricultural enterprise data intelligent matching and sorting method of the present invention, the calculation formula of the matching degree of each seller is as follows:

[0032] ;

[0033] in, Indicates the matching degree of the jth seller; the value range of j is 1, 2, ..., n, where n is the number of sellers;

[0034] represents the market share parameter of the j-th seller; represents the sales volume parameter of the j-th seller; represents the payment cycle parameter of the jth seller; represents the distance cost parameter of the j-th seller; The coefficient of the deterioration rate of the agricultural products produced by the manufacturer is determined by parameter fitting; the formula of the parameter fitting is as follows:

[0035] ;

[0036] in, is a function of time t, representing the quality parameters of agricultural products at time t; Represents the initial quality parameters of agricultural products.

[0037] As a preferred solution of the multi-dimensional agricultural enterprise data intelligent matching and sorting method of the present invention, the input of the neural network model is the raw material supply and climate data of any raw material supplier; the output is the expected output of agricultural products when the manufacturer selects the raw material supplier corresponding to the input;

[0038] The climate data includes temperature, precipitation, humidity, and light intensity.

[0039] As a preferred solution of the multi-dimensional agricultural enterprise data intelligent matching and sorting method of the present invention, the method for evaluating the stability of the supply chain is to calculate the stability index of the supply chain, and the formula is as follows:

[0040] ;

[0041] in, It represents the stability index of the supply chain with the i-th raw material supplier and the j-th seller selected; represents the target output; It represents the revenue of producers from selling a unit mass of agricultural products to sellers; represents the elastic cost of the supply chain with the i-th raw material supplier and the j-th seller selected; It means to find the maximum value of the function in the brackets; represents the matching degree of the qth raw material supplier, and the value range of q is 1, 2, ..., m; Represents the matching degree of the p-th seller; the value range of p is 1, 2, ..., n.

[0042] As a preferred solution of the multi-dimensional agricultural enterprise data intelligent matching and sorting method of the present invention, the calculation formula of the elastic cost is as follows:

[0043] ;

[0044] in, represents the first elastic cost parameter, which indicates the cost required for producers to produce one more unit of agricultural product quality; represents the expected output when selecting the i-th raw material supplier; represents the second elastic cost parameter, which indicates the cost required for producers to distribute an additional unit of agricultural product quality; represents the purchase volume of agricultural products of the jth seller;

[0045] a is the adjustment coefficient of the first elastic cost. If the expected output is less than the target output, a is 1; otherwise, a is 0. b is the adjustment coefficient of the second elastic cost. If the target output is greater than the purchase volume of agricultural products, b is 1; otherwise, b is 0.

[0046] As a preferred solution of the multi-dimensional agricultural enterprise data intelligent matching and sorting method described in the present invention, the method for recommending raw material suppliers and sellers is as follows: traverse all raw material suppliers and sellers, generate a supply chain of raw material supplier-producer-seller, calculate the stability index of each supply chain, and sort the supply chains in descending order according to the stability index; obtain the N supply chains with the highest stability ranking, generate N combinations of raw material suppliers and sellers based on the N supply chains, and recommend them to the manufacturer.

[0047] In a second aspect, the present invention provides a multi-dimensional agricultural enterprise data intelligent matching and sorting system, including a data acquisition module, a preprocessing module, an enterprise evaluation module, a climate data module, a yield prediction module, a supply chain evaluation module, and an enterprise recommendation module;

[0048] Among them, the data collection module is used to collect the matching parameters of the agricultural enterprises; the preprocessing module is used to preprocess the matching parameters of the agricultural enterprises;

[0049] The enterprise evaluation module is used to calculate the matching degree of agricultural enterprises;

[0050] The climate data module is used to collect and process climate data;

[0051] The yield prediction module is used to predict the expected yield of agricultural products;

[0052] The supply chain evaluation module is used to generate the supply chain and calculate the stability index of the supply chain;

[0053] The enterprise recommendation module is used to recommend raw material suppliers and sellers to manufacturers.

[0054] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0055] By collecting the matching parameters of raw material suppliers and sellers and calculating the matching degree, the information asymmetry problem in the agricultural product supply chain can be significantly improved, which helps to improve the matching degree between suppliers and sellers, allowing manufacturers to select partners more accurately, thereby optimizing the composition structure of the supply chain, reducing logistics costs, improving overall operational efficiency, enhancing market competitiveness, and creating more economic benefits for manufacturers.

[0056] By comprehensively considering factors such as agricultural product target output, raw material supply, agricultural product purchase volume and matching, a stable supply chain is generated, which helps reduce the risk of supply chain disruption and ensures the continuity and reliability of the supply chain. By optimizing the composition and matching relationship of the supply chain, reducing the loss and contamination risk of agricultural products in the circulation link, and ensuring the freshness and safety of agricultural products, it is of great significance to enhance the market competitiveness of agricultural products. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of 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 ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0058] Figure 1 A flow chart of the multi-dimensional agricultural enterprise data intelligent matching and sorting method provided by the present invention;

[0059] Figure 2 A schematic diagram of the structure of a neural network model for predicting expected yield of agricultural products provided by the present invention;

[0060] Figure 3 This is a schematic diagram of the structure of the multi-dimensional agricultural enterprise data intelligent matching and sorting system provided by the present invention. DETAILED DESCRIPTION

[0061] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0062] Example 1

[0063] This embodiment introduces a multi-dimensional agricultural enterprise data intelligent matching and sorting method. Figure 1 , the method comprises the following steps:

[0064] S1: Collect matching parameters of agricultural enterprises, including matching parameters of raw material suppliers and sellers, and perform data preprocessing;

[0065] The matching parameters of the raw material supplier include supply capacity parameters, sales volume parameters, order completion rate, inventory turnover index, and price competitiveness index; among which:

[0066] The supply capacity parameter is the ratio of the raw material output of any raw material supplier to the average raw material output, and the average raw material output is the average of the raw material outputs of all raw material suppliers; the supply capacity parameter reflects the raw material production capacity of the raw material supplier, which directly determines whether it can meet the large-scale raw material demand of the manufacturer. Large-scale production usually means that the raw material supplier has a stable source of raw materials, sufficient production equipment and efficient production processes, and can ensure continuous supply during peak demand periods.

[0067] The sales volume parameter is the ratio of the sales volume of raw materials of any raw material supplier to the average sales volume of raw materials. The average sales volume of raw materials is the average sales volume of raw materials of all raw material suppliers. The sales volume parameter reveals the market's recognition and demand intensity for the supplier's raw materials. High sales volume may mean that the supplier's product quality, performance or price is widely accepted and matches the manufacturer's target market or production needs.

[0068] The order completion rate is the ratio of the valid orders completed by any raw material supplier to the total number of orders; it is a key indicator that reflects whether the supplier can complete customer orders according to the agreed quantity, quality and time requirements. A high order completion rate means that the supplier has stable production capacity, effective internal process management and good supply chain coordination capabilities, and can meet the procurement needs of manufacturers.

[0069] The inventory turnover index is the average inventory turnover days of any raw material supplier, which is calculated by dividing the number of days in a year or a quarter by the number of inventory turnovers in a year or a quarter. It indicates the average number of days that the supplier's inventory of raw materials stays in the warehouse, which helps to evaluate whether the supplier's inventory turnover speed matches its business goals and industry standards.

[0070] The price competitiveness index is the ratio of the price quoted by any raw material supplier to the average price quoted by the raw material, and the average price quoted by the raw material is the average of the prices quoted by all raw material suppliers;

[0071] The matching parameters of the seller include market share parameters, sales volume parameters, payment cycle parameters, and distance cost parameters; wherein:

[0072] The market share parameter is the market share of any seller in the market of agricultural products provided by the producer; in a specific agricultural product category or target market, the market share of the seller can measure its market position and competitiveness. A high market share often means stronger market penetration and brand influence.

[0073] The sales volume parameter is the ratio of the sales volume of agricultural products provided by any seller to the manufacturer to the average sales volume of agricultural products; the average sales volume of agricultural products is the mean of the sales volume of agricultural products provided by all sellers to the manufacturer; the sales volume parameter can evaluate whether the seller's purchasing demand is stable and whether it matches the manufacturer's production capacity.

[0074] The payment cycle parameter is the ratio of the regular payment cycle of any seller to the average of the regular payment cycles of all sellers; a shorter payment cycle is conducive to the stability of the manufacturer's cash flow.

[0075] The distance cost parameter is expressed by the time required for a producer to transport agricultural products to any seller; it is related to transportation costs and spoilage loss costs, and especially for perishable agricultural products, transportation distance and transportation time are crucial.

[0076] The data preprocessing includes missing value processing, outlier detection and processing, and consistency check; first identify and fill in the missing values ​​in the data of agricultural enterprises. You can use mean filling, mode filling, multiple interpolation, etc., or decide whether to delete records with too many missing values ​​according to the actual situation. Then: identify and process outliers in parameters such as raw material prices, supply, and delivery time. Outliers may be caused by data entry errors, extreme events, or special trading situations. They can be identified through statistical methods (such as the quartile rule, Z-score, IQR, etc.), and then choose to delete, modify, or retain (depending on their impact on the model). Finally, a consistency check is performed to ensure the consistency of supplier data from different sources or time points, such as unit unification, time format standardization, and supplier name or code standardization.

[0077] One form of agricultural product supply chain is raw material supplier-producer-seller; among them:

[0078] Raw material suppliers are upstream companies that provide inputs required for agricultural production, such as seeds, fertilizers, pesticides, feed, etc., to ensure the smooth progress of the agricultural production process;

[0079] A producer refers to an entity that is directly engaged in the production of agricultural products and is responsible for the production process including the growth, cultivation, and harvesting of agricultural products.

[0080] Sellers refer to the sales entities in the process of agricultural products flowing from producers to consumers; they purchase agricultural products from producers, provide value-added services such as warehousing, sorting, and packaging, and then resell the products to other middlemen, retailers or consumers.

[0081] The solution provided in this application is intended to serve manufacturers and is committed to matching the best raw material suppliers and sellers for manufacturers, a key node in the supply chain.

[0082] S2: Calculating the matching degree of agricultural enterprises based on the matching parameters, including the matching degree of each raw material supplier and the matching degree of each seller;

[0083] The calculation formula for the matching degree of each raw material supplier is as follows:

[0084] ;

[0085] in, represents the matching degree of the i-th raw material supplier, the value range of i is 1, 2, ..., m, where m is the number of raw material suppliers;

[0086] represents the supply capacity parameter of the i-th raw material supplier; represents the sales volume parameter of the i-th raw material supplier; represents the order completion rate of the i-th raw material supplier; represents the inventory turnover index of the i-th raw material supplier; Represents the price competitiveness index of the i-th raw material supplier.

[0087] The calculation formula of the matching degree of each seller is as follows:

[0088] ;

[0089] in, Indicates the matching degree of the jth seller; the value range of j is 1, 2, ..., n, where n is the number of sellers;

[0090] represents the market share parameter of the j-th seller; represents the sales volume parameter of the j-th seller; represents the payment cycle parameter of the jth seller; represents the distance cost parameter of the j-th seller; The coefficient of the deterioration rate of the agricultural products produced by the manufacturer is determined by parameter fitting; the formula of the parameter fitting is as follows:

[0091] ;

[0092] in, is a function of time t, representing the quality parameters of agricultural products at time t; Represents the initial quality parameters of agricultural products; the quality parameters are parameters that reflect the quality of agricultural products, for example, It can represent the average market price of agricultural products just produced. It represents the average market price of agricultural products that are already somewhat stale at time t.

[0093] S3: Obtain the target output of agricultural products of the producer, the raw material supply of each supplier, the purchase volume of agricultural products of each seller, and calculate the expected output of agricultural products through the neural network model;

[0094] Reference Figure 2 The neural network model includes an input layer, a hidden layer, and an output layer; the input is the raw material supply and climate data of any raw material supplier; the output is the expected output of agricultural products when the producer selects the raw material supplier corresponding to the input.

[0095] The climate data includes temperature, precipitation, humidity, and light intensity.

[0096] Climate data is one of the key factors affecting crop growth and final yield, so they are included in the model as an important input parameter. Temperature affects plant growth rate and physiological processes; precipitation is related to crop water supply; humidity and light intensity also have a significant impact on crop photosynthesis and growth cycle.

[0097] First, the past and current climate data are collected through observation data from the National Agricultural Science Data Center, agricultural meteorological stations, and remote sensing technology. Then, the average climate data during the agricultural product production process is estimated through statistical analysis methods, and used together with the raw material supply as the input of the neural network model.

[0098] S4: Generate a supply chain and evaluate the stability of the supply chain based on the expected output, target output, agricultural product purchase volume, and the matching degree of agricultural enterprises; the method is to calculate the stability index of the supply chain, and the formula is as follows:

[0099] ;

[0100] in, It represents the stability index of the supply chain with the i-th raw material supplier and the j-th seller selected; represents the target output; It represents the revenue of producers from selling a unit mass of agricultural products to sellers; represents the elastic cost of the supply chain with the i-th raw material supplier and the j-th seller selected; It means to find the maximum value of the function in the brackets; represents the matching degree of the qth raw material supplier, and the value range of q is 1, 2, ..., m; Indicates the matching degree of the p-th seller; the value range of p is 1, 2, ..., n;

[0101] The calculation formula of the elasticity cost is as follows:

[0102] ;

[0103] in, represents the first elastic cost parameter, which represents the cost required for the producer to produce more units of agricultural products, and is determined by technical personnel in this field based on experience; when the expected output does not reach the target output, the producer may have to purchase raw materials from other channels and re-plan the production plan, thereby generating the first elastic cost; represents the expected output when selecting the i-th raw material supplier;

[0104] represents the second elastic cost parameter, which represents the cost required for the producer to distribute more units of agricultural products, and is determined by those skilled in the art based on experience; when the seller's purchase volume is not enough to carry the producer's production volume, the producer may need to distribute through other channels, which may generate the second elastic cost; represents the purchase volume of agricultural products of the jth seller;

[0105] a is the adjustment coefficient of the first elastic cost. If the expected output is less than the target output, a takes the value of 1; otherwise, a takes the value of 0. If the expected output is greater than the target output, the manufacturer can choose to expand the production plan, reduce the purchase of raw materials, or store some raw materials.

[0106] b is the adjustment coefficient of the second elastic cost. If the target output is greater than the purchase volume of agricultural products, b is 1; otherwise, b is 0.

[0107] S5: Recommend raw material suppliers and sellers to manufacturers based on the stability of the supply chain. The method is as follows: traverse all raw material suppliers and sellers, generate a supply chain of raw material supplier-manufacturer-seller, calculate the stability index of each supply chain, and sort the supply chains in descending order according to the stability index; obtain the N supply chains with the highest stability rankings, generate N combinations of raw material suppliers and sellers based on the N supply chains, and recommend them to manufacturers.

[0108] Example 2

[0109] This embodiment is the second embodiment of the present invention; it is based on the same inventive concept as embodiment 1, Figure 3 ,This embodiment introduces a multi-dimensional agricultural enterprise data intelligent matching and ranking system, including: a data collection module, a preprocessing module, an enterprise evaluation module, a climate data module, a yield prediction module, a supply chain evaluation module, and an enterprise recommendation module;

[0110] Among them, the data collection module is used to collect matching parameters of agricultural enterprises, including matching parameters of raw material suppliers and matching parameters of sellers;

[0111] The preprocessing module is used to preprocess the matching parameters of the agricultural enterprises;

[0112] The enterprise evaluation module is used to calculate the matching degree of agricultural enterprises; based on the pre-processed matching parameters, the matching degree of each raw material supplier and each seller is calculated respectively;

[0113] The climate data module is used to collect and process climate data. First, the past and current climate data are collected by visiting the National Agricultural Science Data Center and other channels. Then, the average climate data in the agricultural product production process is estimated by statistical analysis.

[0114] The yield prediction module is used to predict the expected yield of agricultural products. This function is achieved through a trained neural network model, which inputs climate data and the raw material supply of any supplier, and outputs the expected yield of agricultural products when this supplier is selected.

[0115] The supply chain evaluation module is used to generate a supply chain and calculate the stability index of the supply chain; the supply chain stability index calculated based on the expected output, target output, agricultural product purchase volume and the matching degree of agricultural enterprises can reflect the stability of the supply chain;

[0116] The enterprise recommendation module is used to recommend raw material suppliers and sellers to manufacturers; based on the supply chain generated by the supply chain evaluation module and the stability index calculated, raw material suppliers and sellers on the supply chain with high stability index are recommended to manufacturers.

[0117] The specific functional implementation of each of the above modules refers to the relevant content in the multi-dimensional agricultural enterprise data intelligent matching and sorting method described in Example 1 and will not be repeated here.

[0118] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose and scope of protection of the present invention, which are all within the protection of the present invention.

Claims

1. A multi-dimensional agricultural enterprise data intelligent matching and sorting method, characterized by: The following steps are involved: S1: Collect matching parameters of agricultural enterprises, including matching parameters of raw material suppliers and sellers, and perform data preprocessing; S2: Calculating the matching degree of agricultural enterprises based on the matching parameters, including the matching degree of each raw material supplier and the matching degree of each seller; The calculation formula for the matching degree of each raw material supplier is as follows: ； in, represents the matching degree of the i-th raw material supplier, the value range of i is 1, 2, ..., m, where m is the number of raw material suppliers; represents the supply capacity parameter of the i-th raw material supplier; represents the sales volume parameter of the i-th raw material supplier; represents the order completion rate of the i-th raw material supplier; represents the inventory turnover index of the i-th raw material supplier; represents the price competitiveness index of the i-th raw material supplier; The calculation formula of the matching degree of each seller is as follows: ； in, Indicates the matching degree of the jth seller; the value range of j is 1, 2, ..., n, where n is the number of sellers; represents the market share parameter of the j-th seller; represents the sales volume parameter of the j-th seller; represents the payment cycle parameter of the jth seller; represents the distance cost parameter of the j-th seller; The coefficient of the deterioration rate of the agricultural products produced by the manufacturer is determined by parameter fitting; the formula of the parameter fitting is as follows: ； in, is a function of time t, representing the quality parameters of agricultural products at time t; Indicates the initial quality parameters of agricultural products; S3: Obtain the target output of agricultural products of the producer, the raw material supply of each supplier, the purchase volume of agricultural products of each seller, and calculate the expected output of agricultural products through the neural network model; S4: Generate a supply chain and evaluate the stability of the supply chain based on the expected output, target output, agricultural product purchase volume, and the matching degree of agricultural enterprises; The method for evaluating the stability of the supply chain is to calculate the stability index of the supply chain, and the formula is as follows: ； in, It represents the stability index of the supply chain with the i-th raw material supplier and the j-th seller selected; represents the target output; It represents the revenue of producers from selling a unit mass of agricultural products to sellers; represents the elastic cost of the supply chain with the i-th raw material supplier and the j-th seller selected; It means to find the maximum value of the function in the brackets; represents the matching degree of the qth raw material supplier, and the value range of q is 1, 2, ..., m; Indicates the matching degree of the p-th seller; the value range of p is 1, 2, ..., n; S5: Recommend raw material suppliers and sellers to manufacturers based on the stability of the supply chain.

2. The multi-dimensional agricultural enterprise data intelligent matching and sorting method according to claim 1, characterized in that: The matching parameters of the raw material supplier include supply capacity parameters, sales volume parameters, order completion rate, inventory turnover index, and price competitiveness index; among which: The supply capacity parameter is the ratio of the output of raw materials of any raw material supplier to the average output of raw materials, and the average output of raw materials is the average output of raw materials of all raw material suppliers; The sales volume parameter is the ratio of the sales volume of raw materials of any raw material supplier to the average sales volume of raw materials, and the average sales volume of raw materials is the average sales volume of raw materials of all raw material suppliers; The order completion rate is the ratio of the valid orders completed by any raw material supplier to the total number of orders; The inventory turnover index is the average inventory turnover days of any raw material supplier; The price competitiveness index is the ratio of the price quoted by any raw material supplier to the average price quoted by the raw materials, and the average price quoted by the raw materials is the average of the price quoted by all raw material suppliers.

3. The multi-dimensional agricultural enterprise data intelligent matching and sorting method according to claim 2, characterized in that: The matching parameters of the seller include market share parameters, sales volume parameters, payment cycle parameters, and distance cost parameters; wherein: The market share parameter is the market share of any seller in the market for the agricultural products provided by the producer; The sales volume parameter is the ratio of the sales volume of agricultural products provided by any seller to the average sales volume of agricultural products; The payment cycle parameter is the ratio of the regular payment cycle of any seller to the average of the regular payment cycles of all sellers; The distance cost parameter is expressed by the time required for the producer to transport the agricultural products to any seller; The data preprocessing includes missing value processing, outlier detection and processing, and consistency verification.

4. The multi-dimensional agricultural enterprise data intelligent matching and sorting method according to claim 3 is characterized by: The input of the neural network model is the raw material supply and climate data of any raw material supplier; the output is the expected output of agricultural products when the producer selects the raw material supplier corresponding to the input; The climate data includes temperature, precipitation, humidity, and light intensity.

5. The multi-dimensional agricultural enterprise data intelligent matching and sorting method according to claim 4, characterized in that: The calculation formula of the elasticity cost is as follows: ； in, represents the first elastic cost parameter, which indicates the cost required for producers to produce one more unit of agricultural product quality; represents the expected output when selecting the i-th raw material supplier; represents the second elastic cost parameter, which indicates the cost required for producers to distribute an additional unit of agricultural product quality; represents the purchase volume of agricultural products of the jth seller; a is the adjustment coefficient of the first elastic cost. If the expected output is less than the target output, a is 1; otherwise, a is 0. b is the adjustment coefficient of the second elastic cost. If the target output is greater than the purchase volume of agricultural products, b is 1; otherwise, b is 0.

6. The multi-dimensional agricultural enterprise data intelligent matching and sorting method according to claim 5, characterized in that: The method for recommending raw material suppliers and sellers is as follows: traverse all raw material suppliers and sellers, generate a supply chain of raw material supplier-producer-seller, calculate the stability index of each supply chain, and sort the supply chains in descending order according to the stability index; The N supply chains with the highest stability rankings are obtained, and based on the N supply chains, N combinations of raw material suppliers and sellers are generated and recommended to the manufacturers.

7. A multi-dimensional agricultural enterprise data intelligent matching and sorting system, which is implemented based on the multi-dimensional agricultural enterprise data intelligent matching and sorting method according to any one of claims 1 to 6, characterized in that: It includes data collection module, preprocessing module, enterprise evaluation module, climate data module, production forecast module, supply chain evaluation module and enterprise recommendation module; Among them, the data collection module is used to collect the matching parameters of the agricultural enterprises; the preprocessing module is used to preprocess the matching parameters of the agricultural enterprises; The enterprise evaluation module is used to calculate the matching degree of agricultural enterprises; The climate data module is used to collect and process climate data; The yield prediction module is used to predict the expected yield of agricultural products; The supply chain evaluation module is used to generate the supply chain and calculate the stability index of the supply chain; The enterprise recommendation module is used to recommend raw material suppliers and sellers to manufacturers.

Images