Intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting

Abstract

This invention relates to the field of agricultural product trading technology, and more particularly to an intelligent matching and scheduling system for agricultural product trading based on supply and demand forecasting. The system includes: a data acquisition module for acquiring historical characteristic data of potential users within a target area, potential correlation data between potential users and several agricultural product push information, and agricultural product data from several scheduling centers within the target area; a data analysis module for determining the agricultural products to be selected for potential users based on the potential correlation data and historical characteristic data, and determining the scheduling direction relationship between agricultural products and scheduling centers based on the agricultural product data from each scheduling center; a data matching module for determining the associated scheduling centers corresponding to the agricultural products to be selected and determining the selection matching degree; and a scheduling adjustment module for determining the scheduling adjustment method based on the selection matching degree. This invention can improve the matching accuracy and scheduling efficiency of agricultural product trading, and achieve a stable supply of agricultural products.

Description

Technical Field

[0001] This invention relates to the field of agricultural product trading technology, and in particular to an intelligent matching and scheduling system for agricultural product trading based on supply and demand forecasting. Background Technology

[0002] In the agricultural product trading sector, with the advancement of digital transformation, traditional trading models are gradually upgrading to "data-driven" models. The agricultural product trading market is becoming increasingly complex, with drastic fluctuations in supply and demand. Traditional systems mainly rely on completed orders to analyze user demand, failing to capture potential, unconverted user intentions and lacking accurate predictions of user needs and market changes. This results in a significant lag in judging real and emerging market demands, leading to frequent instances of unsold agricultural products or supply shortages, and making it impossible to achieve true "on-demand scheduling" and "precise delivery."

[0003] Chinese Patent Application Publication No. CN120070053A discloses a method and apparatus for processing agricultural product transaction data based on multi-indicator linkage analysis. The method includes: acquiring multiple transaction data of a target agricultural product, wherein the transaction data includes exogenous indicator values, transaction volume, and transaction price of the target agricultural product; processing the transaction data based on a pre-constructed price expectation model to give the expected transaction price of the corresponding transaction data; matching the corresponding data processing model through analysis of the expected transaction price; and completing the processing of the transaction data by combining the expected transaction price and based on the data processing model.

[0004] Existing technologies have the following problems: they only consider the exogenous index values, trading volume and trading price of the target agricultural product to analyze the trading data and determine the expected trading price. They lack accurate prediction of user demand and market changes, making it difficult to achieve accurate matching of agricultural product transactions and impossible to achieve accurate and efficient scheduling of agricultural products. Summary of the Invention

[0005] To address this, the present invention provides an intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting, which overcomes the problems in the prior art of lacking accurate forecasting of user demand and market changes, making it difficult to achieve accurate matching of agricultural product transactions and accurate and efficient scheduling of agricultural products.

[0006] To achieve the above objectives, the present invention provides an intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting, comprising:

[0007] The data acquisition module is used to acquire historical characteristic data of potential users in the target area, potential correlation data between potential users and several agricultural product push information, and agricultural product data of several dispatch centers in the target area. The potential correlation data includes the number of clicks and browsing time, and the agricultural product data includes the dispatchable quantity and product characteristics.

[0008] The data analysis module, which is connected to the data acquisition module, is used to determine the agricultural products to be selected for the potential users based on the potential correlation data and the historical feature data, and to determine the product characteristics to be selected for the agricultural products. Based on the agricultural product data of each scheduling center, the module determines the scheduling direction relationship between the agricultural products and the scheduling centers, and the scheduling product characteristics corresponding to each agricultural product in each scheduling center.

[0009] The data matching module is connected to the data acquisition module and the data analysis module respectively. It is used to determine the associated dispatch center corresponding to the agricultural product to be selected based on the historical feature data and the agricultural product data of each dispatch center, and to determine the selection matching degree based on the comparison result of the dispatch product characteristics of the agricultural product to be selected in the associated dispatch center and the product characteristics of the agricultural product to be selected.

[0010] The scheduling adjustment module, which is connected to both the data analysis module and the data matching module, is used to determine the scheduling adjustment method based on the selected matching degree, including a first adjustment method and a second adjustment method.

[0011] Under the first adjustment method, several candidate scheduling centers are determined based on the scheduling direction relationship, and the key scheduling center corresponding to the selected agricultural product is determined based on the comparison results of the scheduling product characteristics and the selected product characteristics of the selected agricultural product in each candidate scheduling center, so as to schedule the corresponding selected agricultural product to the associated scheduling center.

[0012] In the second adjustment method, the push priority of each agricultural product is determined based on the scheduling direction relationship and the historical feature data, so as to adjust the push information of each agricultural product.

[0013] Furthermore, the data analysis module includes:

[0014] The push analysis submodule is connected to the data acquisition module. It is used to determine a number of potential agricultural products and their corresponding selectability probabilities based on the potential correlation data between the potential users and the push information of each agricultural product, to determine the expected representation value of each potential agricultural product based on the historical feature data, and to determine the agricultural product to be selected by the potential user based on the selectability probability and expected representation value of each potential agricultural product.

[0015] The product feature analysis submodule is connected to the data acquisition module and the push analysis submodule respectively, and is used to determine the product features corresponding to the agricultural products to be selected based on the push information of the agricultural products to be selected.

[0016] The scheduling analysis submodule, which is connected to the data acquisition module, is used to determine the scheduling direction relationship between agricultural products and scheduling centers based on the agricultural product data of each scheduling center, as well as the scheduling product characteristics corresponding to each agricultural product in each scheduling center.

[0017] Furthermore, the data matching module includes:

[0018] The scheduling center matching submodule is connected to the data acquisition module and the data analysis module respectively. It is used to determine the predicted scheduling quantity and several predicted scheduling centers corresponding to the agricultural products to be selected based on the historical feature data, and to determine the associated scheduling center corresponding to the agricultural products to be selected based on the comparison result between the schedulable quantity of each predicted scheduling center and the predicted scheduling quantity.

[0019] The selection matching submodule, which is connected to the scheduling center matching submodule, is used to determine the selection matching degree based on the comparison results of the scheduling product characteristics of the agricultural products to be selected and the product characteristics to be selected within the associated scheduling center.

[0020] Furthermore, the scheduling adjustment module determines the scheduling adjustment method based on the comparison results of the selected matching degree with the first preset matching degree and the second preset matching degree;

[0021] If the selected match degree is greater than the first preset match degree, no adjustment will be made;

[0022] The first preset matching degree is greater than the second preset matching degree.

[0023] Furthermore, the scheduling adjustment module determines several alternative scheduling centers based on the agricultural products to be selected, the associated scheduling centers, and the scheduling direction relationship.

[0024] Furthermore, the scheduling adjustment module determines the candidate matching degree based on the comparison results between the scheduling product characteristics of the agricultural products to be selected and the product characteristics to be selected in each of the candidate scheduling centers, and determines the key scheduling center corresponding to the agricultural products to be selected based on the candidate matching degree.

[0025] Furthermore, the scheduling adjustment module determines the feature adjustment coefficient of each agricultural product based on the historical feature data, determines the scheduling adjustment coefficient of each agricultural product based on the scheduling pointing relationship, and determines the push priority of each agricultural product based on the feature adjustment coefficient and the scheduling adjustment coefficient.

[0026] Furthermore, the scheduling adjustment module determines the scheduling adjustment method as the first adjustment method based on the first determination condition;

[0027] The first determination condition is that the selected matching degree is greater than the second preset matching degree and less than or equal to the first preset matching degree.

[0028] Furthermore, the scheduling adjustment module determines the scheduling adjustment method as the second adjustment method based on the second determination condition;

[0029] The second determination condition is that the selected matching degree is less than or equal to the second preset matching degree.

[0030] Furthermore, the push analysis submodule determines the optional association representation value corresponding to each agricultural product based on the potential association data between the potential users and the push information of each agricultural product, and determines a number of potential agricultural products based on the comparison results between the optional association representation value corresponding to each agricultural product and the preset association representation value.

[0031] Compared with existing technologies, the beneficial effects of this invention are as follows: By setting up a data acquisition module, it acquires potential correlation data between potential users and agricultural product push information, providing a data foundation for accurately predicting user demand. It also acquires agricultural product data from the dispatch center, providing a data foundation for accurate and efficient dispatch analysis, ensuring the timeliness of agricultural product transaction matching and dispatch. By setting up a data analysis module, it analyzes user behavior data, accurately identifies potential user needs, and analyzes the dispatch relationships of agricultural products between various dispatch centers, clarifying the dispatch basis and priority, thereby improving the accuracy and efficiency of subsequent agricultural product transaction matching. By setting up a data matching module, it combines historical user characteristic data with agricultural product data from the dispatch center to quickly filter out related dispatch centers, improving the accuracy of related dispatch center selection. Furthermore, by comparing the characteristics of dispatched products with the characteristics of candidate products to calculate the matching degree, it achieves refined comparison of product characteristics, improving matching accuracy. By setting up a scheduling adjustment module, the adjustment method can be flexibly switched based on the selection matching degree, realizing flexible adaptation of the scheduling strategy. In the first adjustment method, candidate scheduling centers are selected based on the scheduling direction relationship, and key scheduling centers are determined by feature comparison, which can improve the utilization efficiency of scheduling resources, realize accurate and efficient scheduling of agricultural product transactions, and ensure the effectiveness of agricultural product transactions. In the second adjustment method, the push priority is determined by combining the scheduling direction relationship and historical feature data, which further improves the matching accuracy and scheduling efficiency of agricultural product transactions and realizes a stable supply of agricultural products.

[0032] Furthermore, the data analysis module of this invention, by setting up a push analysis submodule, can accurately determine the agricultural products that potential users are interested in and their availability by analyzing the potential correlation data between potential users and agricultural product push information, thus improving the targeting and effectiveness of push information. Combining the historical characteristic data of potential users, the expected characteristic value of each potential agricultural product is determined. Based on the availability probability and expected characteristic value, the most suitable agricultural product for each potential user is selected, ensuring that the push content always matches the user's current needs and market conditions, accurately locating the supply and demand of potential users, and improving the system's adaptability and flexibility. By setting up a product feature analysis submodule, specific product characteristics are extracted based on the push information of the agricultural products to be selected, providing accurate agricultural product information for subsequent matching and scheduling, ensuring the accuracy of transactions and scheduling. By setting up a scheduling analysis submodule, the scheduling direction relationship between agricultural products and scheduling centers is determined based on agricultural product data from each scheduling center, which helps to clarify the flow and allocation of agricultural products, optimize the allocation of scheduling resources, and improve scheduling efficiency.

[0033] Furthermore, the data matching module of this invention, by setting up a scheduling center matching submodule, predicts the forecast scheduling volume of agricultural products to be selected based on the historical characteristic data of potential users, thereby accurately predicting user demand and improving the accuracy of scheduling center matching. By identifying several forecast scheduling centers and comparing the available scheduling volume with the forecast scheduling volume of each forecast scheduling center, the most suitable associated scheduling center is selected, optimizing scheduling resources, improving scheduling efficiency, and ensuring the timely supply of agricultural products. By setting up a selection matching submodule, the matching degree is determined by comparing the scheduling product characteristics of the agricultural products to be selected within the associated scheduling centers with the characteristics of the selected products, thereby improving the matching accuracy of subsequent agricultural product transactions and achieving efficient and accurate scheduling. Attached Figure Description

[0034] Figure 1 This is a structural block diagram of an intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting, according to an embodiment of the present invention.

[0035] Figure 2 This is a structural block diagram of the data analysis module in an embodiment of the present invention;

[0036] Figure 3 This is a structural block diagram of the data matching module in an embodiment of the present invention;

[0037] Figure 4 The logical decision diagram for determining the scheduling adjustment method in an embodiment of the present invention is shown. Detailed Implementation

[0038] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0039] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0040] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0041] Please see Figure 1 The diagram shown is a structural block diagram of an intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting, according to an embodiment of the present invention. The present invention provides an intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting, comprising:

[0042] The data acquisition module is used to acquire historical characteristic data of potential users in the target area, potential correlation data between potential users and several agricultural product push information, and agricultural product data of several dispatch centers in the target area. The potential correlation data includes the number of clicks and browsing time. The agricultural product data includes dispatchable quantity (inbound quantity, planned outbound quantity) and product characteristics. The historical characteristic data includes the association establishment time, product characteristics, dispatch center, and association evaluation index of the associated agricultural products in each historical association. The association establishment is the user's execution of a transaction action (the product characteristics are standardized and converted to between 0 and 1 to eliminate the units of measurement and facilitate subsequent data analysis).

[0043] The number of times each historically associated agricultural product was associated, the time of association establishment, the product characteristics of each association, the dispatch center of each association, and the association evaluation index of each association.

[0044] Specifically, in practical application scenarios, agricultural product push information can be any agricultural product information displayed on the interface of any agricultural product trading APP or webpage, including agricultural product images, product characteristics, dispatch centers, etc. The dispatchable quantity can be calculated based on the difference between the inbound quantity and the planned outbound quantity. Product characteristics include, but are not limited to, shape, size, color, surface roughness, weight, harvest time, shelf life, hardness, etc. Historically associated agricultural products are agricultural products that potential users have traded. The number of associations is the number of times a potential user has traded any agricultural product. The most recent association time is the most recent transaction time between a potential user and any agricultural product. The product characteristics of each association are the product characteristics of the agricultural products traded by the potential user in each transaction. The dispatch center of each association is the dispatch center of the potential user in each transaction. The association evaluation index of each association is the comprehensive evaluation value of the potential user for each transaction, which can be obtained based on the potential user's rating of each transaction (for example, the comprehensive evaluation value can be set to a range of 0 to 10, where a comprehensive evaluation value of 0 indicates that the potential user has the lowest evaluation of the traded agricultural product, and a comprehensive evaluation value of 10 indicates that the potential user has the highest evaluation of the traded agricultural product).

[0045] The data analysis module, which is connected to the data acquisition module, is used to determine the agricultural products to be selected for the potential users based on the potential correlation data and the historical feature data, and to determine the product characteristics to be selected for the agricultural products. Based on the agricultural product data of each scheduling center, the module determines the scheduling direction relationship between the agricultural products and the scheduling centers, and the scheduling product characteristics corresponding to each agricultural product in each scheduling center.

[0046] Please see Figure 2 The diagram shown is a structural block diagram of the data analysis module according to an embodiment of the present invention; specifically, the data analysis module includes:

[0047] The push analysis submodule is connected to the data acquisition module. It is used to determine a number of potential agricultural products and their corresponding selectability probabilities based on the potential correlation data between the potential users and the push information of each agricultural product, to determine the expected representation value of each potential agricultural product based on the historical feature data, and to determine the agricultural product to be selected by the potential user based on the selectability probability and expected representation value of each potential agricultural product.

[0048] Specifically, the push analysis submodule determines the optional association representation value corresponding to each agricultural product based on the potential association data between the potential users and the push information of each agricultural product, and determines a number of potential agricultural products based on the comparison results between the optional association representation value corresponding to each agricultural product and the preset association representation value.

[0049] In implementation, for any agricultural product push notification, the ratio of potential user clicks to a preset click count is determined as the click representation value, the ratio of browsing time to a preset browsing time is determined as the browsing representation value, and the product of the click representation value and the browsing representation value is determined as the optional association representation value of the agricultural product corresponding to the push notification. Agricultural products with optional association representation values ​​greater than the preset association representation value are identified as potential agricultural products. Implementers can set the preset click count and preset browsing time based on actual conditions. Preferably, the preset click count ranges from 3 to 5, the preset browsing time ranges from 2 seconds to 5 seconds, and the preset association representation value ranges from 1.2 to 1.5. For any potential agricultural product, the difference between the optional association representation value and the preset association representation value is determined as the association difference, and the ratio of the association difference to the preset association representation value is determined as the optional probability corresponding to that potential agricultural product.

[0050] It is understood that a list of historical feature vectors is constructed based on the historical feature data (historical feature vectors are constructed using the association establishment time, product features, scheduling center, and association evaluation index for a single association establishment, and each list of historical feature vectors includes several historical feature vectors). The list of historical feature vectors corresponding to potential users is input into the target recommendation model to obtain the expected representation value corresponding to each potential agricultural product output by the target recommendation model (the target recommendation model outputs the recommendation probability of agricultural products traded by potential users; if a potential agricultural product exists, i.e., the potential user has traded the corresponding potential agricultural product, then the corresponding recommendation probability is determined as the expected representation value corresponding to that potential agricultural product; if no potential agricultural product exists, i.e., the potential user has not traded the corresponding potential agricultural product, then the expected representation value corresponding to that potential agricultural product is 0). It should be noted that those skilled in the art know that any recommendation model in the prior art that can determine the recommendation probability, such as the deepfm model, the multi-armed slot machine model, the deep learning model, etc., falls within the protection scope of this invention, and will not be elaborated here.

[0051] Understandably, for any potential agricultural product, the average of the selectability probability and the expected representation value corresponding to that potential agricultural product is used to determine the comprehensive evaluation value. The comprehensive evaluation values ​​of each potential agricultural product are then ranked, and the potential agricultural product with the largest comprehensive evaluation value is determined as the agricultural product to be selected by the potential user.

[0052] The product feature analysis submodule is connected to the data acquisition module and the push analysis submodule respectively, and is used to determine the product features corresponding to the agricultural products to be selected based on the push information of the agricultural products to be selected.

[0053] In practice, any agricultural product push information includes information such as the agricultural product image, product characteristics, and dispatch center. The product characteristics corresponding to the push information of the agricultural product to be selected are determined as the product characteristics to be selected for that agricultural product.

[0054] The scheduling analysis submodule, which is connected to the data acquisition module, is used to determine the scheduling direction relationship between agricultural products and scheduling centers based on the agricultural product data of each scheduling center, as well as the scheduling product characteristics corresponding to each agricultural product in each scheduling center.

[0055] In implementation, for any agricultural product, the scheduling relationship includes the priority of each scheduling center in scheduling that agricultural product. For example, scheduling center A can schedule agricultural products a, b, c, d, and e; scheduling center B can schedule agricultural products a, b, e, f, and g; scheduling center C can schedule agricultural products a, b, and c; and scheduling center D can schedule agricultural products b, c, and g. For agricultural product a, scheduling centers A, B, and C can schedule each other. If scheduling center A has insufficient supply of agricultural product a and needs to schedule it, scheduling center B has a scheduling capacity of 10 units of agricultural product a, and scheduling center C has a scheduling capacity of 5 units. Therefore, the scheduling relationship between scheduling center A and agricultural product a is: A > B > C. Similarly, for agricultural product c, scheduling centers A, C, and D can schedule each other. If scheduling center A has insufficient supply of agricultural product c and needs to schedule it, scheduling center C has a scheduling capacity of 3 units of agricultural product c, and scheduling center D has a scheduling capacity of 5 units. Therefore, the scheduling relationship between scheduling center A and agricultural product c is: A > D > C, and so on.

[0056] Specifically, the data analysis module of this invention, by setting up a push analysis submodule, analyzes the potential correlation data between potential users and agricultural product push information. This allows for the accurate identification of agricultural products of interest to potential users and their availability probabilities, improving the targeting and effectiveness of push information. Combining historical characteristic data of potential users, the expected characteristic value of each potential agricultural product is determined. Based on the availability probability and expected characteristic value, the most suitable agricultural product for each potential user is selected, ensuring that the push content always matches the user's current needs and market conditions. This accurately identifies the supply and demand of potential users, improving the system's adaptability and flexibility. By setting up a product feature analysis submodule, specific product characteristics are extracted based on the push information of the agricultural products to be selected, providing accurate agricultural product information for subsequent matching and scheduling, ensuring the accuracy of transactions and scheduling. By setting up a scheduling analysis submodule, the scheduling direction relationship between agricultural products and scheduling centers is determined based on agricultural product data from each scheduling center. This helps to clarify the flow and allocation of agricultural products, optimize the allocation of scheduling resources, and improve scheduling efficiency.

[0057] The data matching module is connected to the data acquisition module and the data analysis module respectively. It is used to determine the associated dispatch center corresponding to the agricultural product to be selected based on the historical feature data and the agricultural product data of each dispatch center, and to determine the selection matching degree based on the comparison result of the dispatch product characteristics of the agricultural product to be selected in the associated dispatch center and the product characteristics of the agricultural product to be selected.

[0058] Please see Figure 3 The diagram shown is a structural block diagram of the data matching module according to an embodiment of the present invention; specifically, the data matching module includes:

[0059] The scheduling center matching submodule is connected to the data acquisition module and the data analysis module respectively. It is used to determine the predicted scheduling quantity and several predicted scheduling centers corresponding to the agricultural products to be selected based on the historical feature data, and to determine the associated scheduling center corresponding to the agricultural products to be selected based on the comparison result between the schedulable quantity of each predicted scheduling center and the predicted scheduling quantity.

[0060] In implementation, a list of historical feature vectors corresponding to potential users is input into the target prediction model to obtain the predicted scheduling quantity for each agricultural product output by the target prediction model. It should be noted that those skilled in the art will understand that any existing prediction model capable of determining the predicted scheduling quantity for each agricultural product, such as neural network models or support vector machines, falls within the protection scope of this invention, and will not be elaborated upon here.

[0061] It is understandable that the dispatch center with the agricultural products to be selected in the target area is identified as the predicted dispatch center. If the dispatchable quantity of the agricultural products to be selected in any predicted dispatch center is greater than the predicted dispatchable quantity, then the dispatch center is identified as the associated dispatch center corresponding to the agricultural products to be selected. (If there is not a unique number of predicted dispatch centers with the dispatchable quantity of the agricultural products to be selected greater than the predicted dispatchable quantity, then the predicted dispatch center with the largest dispatchable quantity is identified as the associated dispatch center. If there is no predicted dispatch center with the dispatchable quantity of the agricultural products to be selected greater than the predicted dispatchable quantity, then the predicted dispatch center with the largest dispatchable quantity is identified as the associated dispatch center.)

[0062] The selection matching submodule, which is connected to the scheduling center matching submodule, is used to determine the selection matching degree based on the comparison results of the scheduling product characteristics of the agricultural products to be selected and the product characteristics to be selected within the associated scheduling center.

[0063] In implementation, the scheduling product characteristics of the agricultural products to be selected are the product characteristics of the agricultural products to be selected that have been stored in the associated scheduling center. For any scheduling product characteristic Y1, Y2, ..., Y... of the agricultural products to be selected... j , ..., Y m With the product features to be selected E1, E2, ..., E j, ..., E m Determine the matching degree PY; where j = 1, 2, ..., m, PY = (∑ m j=1 Y j ×E j ) / (sqrt(∑ m j=1 (Y j ) 2 )×sqrt(∑ m j=1 (E j ) 2 )), sqrt() is a preset square root determination function, and m is the number of product features.

[0064] Specifically, the data matching module of this invention, by setting up a scheduling center matching submodule, predicts the forecast scheduling volume of agricultural products to be selected based on the historical characteristic data of potential users, thereby accurately predicting user demand and improving the accuracy of scheduling center matching. By identifying several forecast scheduling centers and comparing the available scheduling volume with the forecast scheduling volume of each forecast scheduling center, the most suitable associated scheduling center is selected, optimizing scheduling resources, improving scheduling efficiency, and ensuring the timely supply of agricultural products. By setting up a selection matching submodule, the matching degree is determined by comparing the scheduling product characteristics of the agricultural products to be selected within the associated scheduling centers with the characteristics of the selected products, thereby improving the matching accuracy of subsequent agricultural product transactions and achieving efficient and accurate scheduling.

[0065] The scheduling adjustment module, which is connected to both the data analysis module and the data matching module, is used to determine the scheduling adjustment method based on the selected matching degree, including a first adjustment method and a second adjustment method.

[0066] Under the first adjustment method, several candidate scheduling centers are determined based on the scheduling direction relationship, and the key scheduling center corresponding to the selected agricultural product is determined based on the comparison results of the scheduling product characteristics and the selected product characteristics of the selected agricultural product in each candidate scheduling center, so as to schedule the corresponding selected agricultural product to the associated scheduling center.

[0067] In the second adjustment method, the push priority of each agricultural product is determined based on the scheduling direction relationship and the historical feature data, so as to adjust the push information of each agricultural product.

[0068] Please see Figure 4 As shown, it is a logic decision diagram for determining the scheduling adjustment method in an embodiment of the present invention; specifically, the scheduling adjustment module determines the scheduling adjustment method based on the comparison result of the selection matching degree with the first preset matching degree and the second preset matching degree;

[0069] If the selected match degree is greater than the first preset match degree, no adjustment will be made;

[0070] The first preset matching degree is greater than the second preset matching degree.

[0071] In practice, implementers can set a first preset matching degree and a second preset matching degree based on the actual situation. Preferably, the first preset matching degree is set to a value range of 0.8 to 0.9, and the second preset matching degree is set to a value range of 0.6 to 0.7.

[0072] Specifically, the scheduling adjustment module determines the scheduling adjustment method as the first adjustment method based on the first determination condition;

[0073] The first determination condition is that the selected matching degree is greater than the second preset matching degree and less than or equal to the first preset matching degree.

[0074] Specifically, the scheduling adjustment module determines several candidate scheduling centers based on the agricultural products to be selected, the associated scheduling centers, and the scheduling direction relationship.

[0075] In implementation, several alternative scheduling centers are determined based on the scheduling direction relationship between the associated scheduling center and the agricultural products to be selected. For example, if the scheduling direction relationship between the associated scheduling center X and the agricultural products to be selected is X > M > N > S, then the alternative scheduling centers are M, N, and S.

[0076] Specifically, the scheduling adjustment module determines the candidate matching degree based on the comparison results between the scheduling product characteristics of the agricultural products to be selected in each of the candidate scheduling centers and the product characteristics to be selected, and determines the key scheduling center corresponding to the agricultural products to be selected based on the candidate matching degree.

[0077] In implementation, for any candidate dispatch center, the dispatch product characteristics K1, K2, ..., K are... j , ..., K m With the product features to be selected E1, E2, ..., E j , ..., E m Determine the candidate matching degree PK; where j=1,2,…,m, PK=(∑ m j=1 K j ×E j ) / (sqrt(∑ m j=1 (K j ) 2 )×sqrt(∑ m j=1 (E j ) 2)), sqrt() is a preset square root determination function, which sorts the candidate matching degree of each candidate scheduling center and determines the candidate scheduling center with the highest candidate matching degree as the key scheduling center corresponding to the agricultural product to be selected.

[0078] Specifically, the scheduling adjustment module determines the scheduling adjustment method as the second adjustment method based on the second determination condition;

[0079] The second determination condition is that the selected matching degree is less than or equal to the second preset matching degree.

[0080] Specifically, the scheduling adjustment module determines the feature adjustment coefficient of each agricultural product based on the historical feature data, determines the scheduling adjustment coefficient of each agricultural product based on the scheduling pointing relationship, and determines the push priority of each agricultural product based on the feature adjustment coefficient and the scheduling adjustment coefficient.

[0081] In implementation, for any agricultural product, a basic feature vector is constructed based on the product's association establishment time, product characteristics, dispatch center, and association evaluation index. (Each feature is standardized and converted to a value between 0 and 1 to eliminate dimensions; for dispatch centers, each dispatch center is assigned a value, for example, 3 dispatch centers are assigned values ​​1, 2, and 3 respectively). Based on the basic feature vector R1, R2, ..., R..., the basic feature vectors corresponding to the agricultural product are... j , ..., R m The standard feature vectors T1, T2, ..., T corresponding to this agricultural product j ,…,T m Determine the characteristic adjustment coefficient PT for this agricultural product, PT = sqrt(∑ m j=1 (R j -T j ) 2 Those implementing the program can set the standard feature vector for the agricultural product based on the actual situation or historical data, including the establishment time, product characteristics, dispatch center, and average of the associated evaluation index of agricultural products that have passed the qualification inspection.

[0082] It is understandable that, for any agricultural product, in its corresponding scheduling direction relationship, the difference between the schedulable quantity and the minimum schedulable quantity of each scheduling center is calculated to determine the scheduling difference of each scheduling center, the ratio of the scheduling difference of each scheduling center to the minimum schedulable quantity is determined as the scheduling characteristic value of each scheduling center, and the mean of the scheduling characteristic values ​​of each scheduling center is determined as the scheduling adjustment coefficient of the agricultural product.

[0083] It is understandable that, for any agricultural product, the product of the characteristic adjustment coefficient and the scheduling adjustment coefficient of the agricultural product is determined as the push adjustment coefficient of the agricultural product. The push adjustment coefficients of each agricultural product are sorted to determine the push priority of each agricultural product. The agricultural product with the largest push adjustment coefficient is adjusted to the highest push priority, and the agricultural product with the smallest push adjustment coefficient is adjusted to the lowest push priority.

[0084] Specifically, this invention employs a data acquisition module to obtain potential correlation data between potential users and agricultural product push information, providing a data foundation for accurately predicting user demand. It also acquires agricultural product data from the dispatch center, providing a data foundation for accurate and efficient dispatch analysis and ensuring the timeliness of agricultural product transaction matching and dispatch. By setting up a data analysis module, it analyzes user behavior data to accurately pinpoint potential user needs and analyzes the dispatch relationships of agricultural products between various dispatch centers, clarifying the dispatch basis and priority, thereby improving the accuracy and efficiency of subsequent agricultural product transaction matching. Finally, by setting up a data matching module, it combines historical user characteristic data with agricultural product data from the dispatch centers to quickly filter out related dispatch centers, improving the accuracy of related dispatch center selection. Furthermore, by comparing the characteristics of dispatched products with those of candidate products to calculate the matching degree, it achieves refined comparison of product characteristics, improving matching accuracy. By setting up a scheduling adjustment module, the adjustment method can be flexibly switched based on the selection matching degree, realizing flexible adaptation of the scheduling strategy. In the first adjustment method, candidate scheduling centers are selected based on the scheduling direction relationship, and key scheduling centers are determined by feature comparison, which can improve the utilization efficiency of scheduling resources, realize accurate and efficient scheduling of agricultural product transactions, and ensure the effectiveness of agricultural product transactions. In the second adjustment method, the push priority is determined by combining the scheduling direction relationship and historical feature data, which further improves the matching accuracy and scheduling efficiency of agricultural product transactions and realizes a stable supply of agricultural products.

[0085] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A smart matching and scheduling system for agricultural product transactions based on supply and demand forecasting, characterized in that, include: The data acquisition module is used to acquire historical characteristic data of potential users in the target area, potential correlation data between potential users and several agricultural product push information, and agricultural product data of several dispatch centers in the target area. The potential correlation data includes the number of clicks and browsing time, and the agricultural product data includes the dispatchable quantity and product characteristics. The data analysis module, which is connected to the data acquisition module, is used to determine the agricultural products to be selected for the potential users based on the potential correlation data and the historical feature data, and to determine the product characteristics to be selected for the agricultural products. Based on the agricultural product data of each scheduling center, the module determines the scheduling direction relationship between the agricultural products and the scheduling centers, and the scheduling product characteristics corresponding to each agricultural product in each scheduling center. The data matching module is connected to the data acquisition module and the data analysis module respectively. It is used to determine the associated dispatch center corresponding to the agricultural product to be selected based on the historical feature data and the agricultural product data of each dispatch center, and to determine the selection matching degree based on the comparison result of the dispatch product characteristics of the agricultural product to be selected in the associated dispatch center and the product characteristics of the agricultural product to be selected. The scheduling adjustment module, which is connected to both the data analysis module and the data matching module, is used to determine the scheduling adjustment method based on the selected matching degree, including a first adjustment method and a second adjustment method. Under the first adjustment method, several candidate scheduling centers are determined based on the scheduling direction relationship, and the key scheduling center corresponding to the selected agricultural product is determined based on the comparison results of the scheduling product characteristics and the selected product characteristics of the selected agricultural product in each candidate scheduling center, so as to schedule the corresponding selected agricultural product to the associated scheduling center. In the second adjustment method, the push priority of each agricultural product is determined based on the scheduling direction relationship and the historical feature data, so as to adjust the push information of each agricultural product. The scheduling adjustment module determines the scheduling adjustment method as the first adjustment method based on a first determination condition, wherein the first determination condition is that the selection matching degree is greater than the second preset matching degree and less than or equal to the first preset matching degree. The scheduling adjustment module determines the scheduling adjustment method as the second adjustment method based on the second determination condition, wherein the selection matching degree is less than or equal to the second preset matching degree.

2. The intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting as described in claim 1, characterized in that, The data analysis module includes: The push analysis submodule is connected to the data acquisition module. It is used to determine a number of potential agricultural products and their corresponding selectability probabilities based on the potential correlation data between the potential users and the push information of each agricultural product, to determine the expected representation value of each potential agricultural product based on the historical feature data, and to determine the agricultural product to be selected by the potential user based on the selectability probability and expected representation value of each potential agricultural product. The product feature analysis submodule is connected to the data acquisition module and the push analysis submodule respectively, and is used to determine the product features corresponding to the agricultural products to be selected based on the push information of the agricultural products to be selected. The scheduling analysis submodule, which is connected to the data acquisition module, is used to determine the scheduling direction relationship between agricultural products and scheduling centers based on the agricultural product data of each scheduling center, as well as the scheduling product characteristics corresponding to each agricultural product in each scheduling center.

3. The intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting according to claim 2, characterized in that, The data matching module includes: The scheduling center matching submodule is connected to the data acquisition module and the data analysis module respectively. It is used to determine the predicted scheduling quantity and several predicted scheduling centers corresponding to the agricultural products to be selected based on the historical feature data, and to determine the associated scheduling center corresponding to the agricultural products to be selected based on the comparison result between the schedulable quantity of each predicted scheduling center and the predicted scheduling quantity. The selection matching submodule, which is connected to the scheduling center matching submodule, is used to determine the selection matching degree based on the comparison results of the scheduling product characteristics of the agricultural products to be selected and the product characteristics to be selected within the associated scheduling center.

4. The intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting according to claim 3, characterized in that, The scheduling adjustment module determines the scheduling adjustment method based on the comparison results of the selected matching degree with the first preset matching degree and the second preset matching degree; If the selected match degree is greater than the first preset match degree, no adjustment will be made; The first preset matching degree is greater than the second preset matching degree.

5. The intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting according to claim 4, characterized in that, The scheduling adjustment module determines several candidate scheduling centers based on the agricultural products to be selected, the associated scheduling centers, and the scheduling direction relationship.

6. The intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting according to claim 5, characterized in that, The scheduling adjustment module determines the matching degree of the candidate agricultural products based on the comparison results between the scheduling product characteristics and the product characteristics of the candidate agricultural products in each candidate scheduling center, and determines the key scheduling center corresponding to the candidate agricultural products based on the matching degree of the candidate.

7. The intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting according to claim 6, characterized in that, The scheduling adjustment module determines the feature adjustment coefficient of each agricultural product based on the historical feature data, determines the scheduling adjustment coefficient of each agricultural product based on the scheduling direction relationship, and determines the push priority of each agricultural product based on the feature adjustment coefficient and the scheduling adjustment coefficient.

8. The intelligent matching and scheduling system for agricultural product transactions based on supply and demand forecasting according to claim 2 or 7, characterized in that, The push analysis submodule determines the optional association representation value corresponding to each agricultural product based on the potential association data between the potential users and the push information of each agricultural product, and determines a number of potential agricultural products based on the comparison results between the optional association representation value corresponding to each agricultural product and the preset association representation value.

Images