A transport scheduling intelligent management system and method based on cross-border logistics

Abstract

The present invention discloses a transport scheduling intelligent management system and method based on cross-border logistics, and relates to the technical field of big data analysis. The present invention can quickly identify high-value orders, optimize resource allocation, and effectively improve the operational efficiency of warehouses by acquiring transport information and order data in real time. Combined with dynamic and static saturation predictions, the system can accurately analyze the trend of order changes, accurately predict warehouse saturation, and reduce inventory backlogs. By predicting the quality improvement trend of some commodities, the system can further optimize the warehouse consumption reduction value and concentrate resources to increase commodity sales. At the same time, a complete early warning module is set up, combined with real-time warehouse monitoring data, to timely judge the saturation and potential overload risks of the warehouse. This early warning mechanism not only helps enterprises adjust procurement and replenishment strategies to avoid inventory crises, but also ensures the safety and stability of warehouse operations, provides data support for management, and reduces operating costs and risks.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and specifically to a transportation scheduling intelligent management system and method based on cross-border logistics. Background Art

[0002] Cross-border logistics and transportation plays a vital role in the global economy, promoting international trade and regional economic cooperation, driving economic growth and investment, and creating jobs. It improves supply chain efficiency, optimizes resource allocation, reduces inventory costs, and supports the rapid development of e-commerce. Cross-border logistics also promotes technological innovation, improves transportation transparency, and helps companies respond quickly to changes in market demand. In addition, it promotes cultural exchanges, enhances understanding and cooperation among people of all countries, helps to meet the challenges of globalization and promote sustainable development. Therefore, cross-border logistics is of indispensable importance in the modern economy.

[0003] In the process of cross-border logistics and transportation, due to uncontrollable factors such as order returns and equipment failures, the warehouse consumption reduction prediction accuracy is low, which in turn affects the accuracy of warehouse consumption reduction management and leads to inventory backlog problems. This not only takes up storage space, but also increases operating costs and management complexity. Inventory backlogs will lead to resource retention, reduce the company's operating efficiency and the effective utilization of storage space, and may also cause risks such as product expiration, damage or failure. Summary of the invention

[0004] The purpose of the present invention is to provide a transport scheduling intelligent management system and method based on cross-border logistics to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: a transportation scheduling intelligent management method based on cross-border logistics, the transportation scheduling intelligent management method comprising the following steps:

[0006] Step S1: Obtain the transportation cycle and warehouse data of cross-border logistics transportation, and obtain the order data within the transportation cycle in real time from the start of transportation to generate a warehouse order set;

[0007] Step S1-1, obtain historical data of cross-border logistics transportation, extract the shipping location, destination and transportation method, and determine the transportation cycle T of the current cross-border logistics transportation based on the shipping location, destination and transportation method that match the historical data;

[0008] Step S1-2, obtaining warehouse data, wherein the warehouse data includes product category SKU, inventory quantity corresponding to the product category SKU, maximum warehouse capacity of the warehouse and saturation of the current warehouse;

[0009] Step S1-3: From the start of transportation, real-time monitoring is performed to obtain order data within the transportation cycle T to generate a warehouse order set, where the warehouse order set includes product category SKU and corresponding order quantity.

[0010] By acquiring and monitoring order data in the transportation cycle in real time, it is ensured that the reduction value of warehouse saturation by warehouse orders is updated in time. This method not only improves the efficiency of order processing, but also enhances the monitoring ability of warehouse saturation and inventory status, which helps to optimize resource allocation and reduce the risk of inventory backlog. Product category SKU represents a product category or model, which is different from other products.

[0011] Step S2: Set a high-quality order threshold, extract order information with order quantity greater than the high-quality order threshold from the warehouse order set to generate an object order set, and remove the object order set from the warehouse order set to generate a basic order set;

[0012] Step S2-1: Setting the high-quality order threshold G max , traverse the warehouse order set and filter out orders with a quantity greater than the high-quality order threshold G max The order information is aggregated and filtered to generate an object order set;

[0013] Step S2-2: Using the order information in the object order set as an index, delete records with the same order information from the warehouse order set, and retain different order information to generate a basic order set.

[0014] Accurately screen out high-value orders, form a target order set, and ensure that resources are concentrated on the orders with the greatest potential. Effectively eliminate low-quality orders, generate a basic order set, improve the flexibility and pertinence of the overall operation, and promote the personalization and efficiency of warehouse management.

[0015] Step S3: construct an object order change trend graph according to the object order set, and predict the warehouse saturation at the end of the transportation cycle through the object order change trend graph and the basic order set, which is recorded as static warehouse saturation;

[0016] Step S3-1, set a time series, and build a target order change trend chart by combining the product category SKU and the corresponding order quantity in the target order set;

[0017] Step S3-2: predict the trend at the end of the transportation cycle T according to the object order change trend chart, obtain the order quantity of the product category SKU corresponding to the trend, and combine the product category SKU and the corresponding order quantity of the basic order set to predict the warehouse saturation at the end of the transportation cycle T, which is recorded as the static saturation D Q , the process of warehouse saturation is as follows:

[0018] The reduction value of warehouse saturation of the object order set at the end of the transportation cycle T uses the following formula:

[0019] ;

[0020] In the formula, B object It is expressed as the predicted reduction value of the warehouse saturation caused by the object order set at the end of the transportation cycle T; V 0M It is represented by the sales speed of products of category M at the time of transportation start; T is the transportation cycle; R M It is represented as the average growth rate of products in the M category; n is represented as the number of SKUs of the product category in the object order set;

[0021] The basic order set uses the following formula to reduce the warehouse saturation at the end of the transportation cycle T:

[0022] ;

[0023] In the formula, B seat It is expressed as the predicted reduction value of warehouse saturation by the basic order set at the end of the transportation cycle T; B avg，i It is represented as the average value of the i-th product; m is the sum of the product quantities in the basic order set;

[0024] At the end of the transportation cycle T, the warehouse saturation is predicted. The predicted saturation is calculated using the following formula:

[0025] ;

[0026] Where D Q It is expressed as the warehouse saturation predicted at the end of the transportation cycle T, recorded as static saturation; B 0 It is expressed as the capacity of the warehouse at the time when transportation starts; B max Expressed as the maximum warehouse capacity of the warehouse.

[0027] By predicting warehouse saturation, potential inventory pressure can be identified in a timely manner, thereby optimizing warehouse management and operational decisions, enabling companies to respond to market changes more flexibly, improve resource allocation efficiency, and reduce operating costs.

[0028] Step S4: construct a category change trend graph based on the warehouse order set, predict the order information whose order quantity is greater than the high-quality order threshold in the remaining transportation cycle through the category change trend graph, construct a prediction object set in combination with the object order set, and predict the warehouse saturation at the end of the transportation cycle again based on the prediction object set, which is recorded as dynamic warehouse saturation;

[0029] Step S4-1: extract the product category SKU and the corresponding order quantity in the warehouse order set, build a category change trend chart based on the changes of the product category SKU and the corresponding order quantity at different times, and predict based on the category change trend chart that at the end of the transportation cycle T, the order quantity is greater than the high-quality order threshold G max The order information is predicted based on the category change trend chart. The formula used is as follows:

[0030] ;

[0031] In the formula, B pre It is represented by the number of orders that are greater than the high-quality order threshold within the remaining time of the transportation cycle, and t<T; k is the intercept of the linear regression model; l is the slope, which is the increase or decrease in the sales quantity at each time series; t is the remaining time of the transportation cycle;

[0032] Step S4-2, extracting order information that satisfies the order quantity greater than the high-quality order threshold within the remaining transportation cycle t, building a prediction object set in combination with the object order set, and removing the prediction object set from the warehouse order set to generate a prediction basic order set;

[0033] Step S4-3, recursively call the prediction calculation method of step S3, and predict the warehouse saturation at the end of the transportation cycle again. The prediction object set uses the prediction calculation method of the object order set in step S3, and the prediction basic order set uses the prediction calculation method of the basic order set in step S3. The warehouse saturation predicted again is recorded as the dynamic warehouse saturation D W ;

[0034] Recursive prediction of warehouse saturation can provide a more accurate understanding of inventory status.

[0035] Step S5: Obtain order data for historical periods, extract the number of returned orders in each historical period, and calculate the average and standard deviation of the returned orders. Based on the calculated average and standard deviation, predict the total number of returned orders at the end of the transportation period;

[0036] Obtain order data for historical periods, extract the number of returned orders in each historical period, and calculate the average and standard deviation of returned orders. Based on the calculated average and standard deviation, predict the total number of returned orders at the end of the transportation period. The prediction calculation formula for the total number of returned orders is:

[0037] ;

[0038] In the formula, H T It is represented by the total number of returned orders predicted in the current transportation cycle T; z is represented by the number of historical cycles; H iIt is represented by the number of returned orders in the i-th historical period, and c is the fluctuation range constant of the number of returned orders.

[0039] Taking order returns into account can improve the prediction accuracy of warehouse saturation, thereby achieving more effective inventory management, adjusting procurement and replenishment strategies in a timely manner, and avoiding inventory backlogs caused by order returns.

[0040] Step S6, set the inventory backlog threshold, obtain the transportation information of cross-border logistics transportation, calculate the saturation increment of the warehouse based on the transportation information, and combine the predicted static warehouse saturation, dynamic warehouse saturation and total number of returned orders to calculate the warehouse inventory backlog rate, and use the set inventory backlog threshold to make an early warning judgment on the warehouse saturation.

[0041] Step S6-1: Set the inventory backlog threshold J max , obtain the transportation information of cross-border logistics transportation, which includes product category SKU and corresponding order quantity, and calculate the saturation increment of the warehouse according to the transportation information, that is, add the new order quantity of all product category SKUs to obtain the total order quantity;

[0042] Step S6-2: According to the total order quantity and the maximum warehouse capacity B of the transportation information max Perform a percentage calculation to find out the saturation increment D of the warehouse caused by the transportation information calculation new ;

[0043] Step S6-3: According to the static warehouse saturation D Q , Dynamic warehouse saturation D W 、Total number of returned orders H T and degree increment D new Conditional judgment is performed on the warehouse backlog rate. The judgment conditions are as follows:

[0044] When J is satisfied max >D Q +H T / B max +D new and J max >D W +H T / B max +D new When the new logistics arrive at the warehouse at the end of the transportation cycle T, it is judged that there is sufficient available space in the warehouse;

[0045] When J is satisfied max ≤D Q +H T / B max +D new and J max ≤D W +H T / B max +D new When the warehouse is judged to have insufficient available space after new logistics arrive at the warehouse at the end of the transportation cycle T, the warehouse will face the risk of overloading, and an overloading risk warning signal will be issued;

[0046] The accurate early warning mechanism can timely identify the risk of warehouse overload, so that measures can be taken in advance to avoid overload. By predicting warehouse saturation and issuing early warning signals, the safety and stability of warehouse operations can be effectively guaranteed.

[0047] A transport scheduling intelligent management system based on cross-border logistics, the transport scheduling intelligent management system includes a data collection module, an order collection module, an order trend module, a saturation prediction module and an early warning module;

[0048] The data collection module is used to collect cross-border logistics transportation information, order information and warehouse information; the order collection module is used to construct a collection based on the collected information; the order trend module is used to generate a trend chart based on the constructed collection; the saturation prediction module is used to predict the trend based on each trend chart; the early warning module is used to compare and judge based on the predicted data, and perform early warning processing for situations that meet specific conditions;

[0049] The output end of the data acquisition module is electrically connected to the input end of the order collection module; the output end of the order collection module is electrically connected to the input end of the order trend module; the output end of the order trend module is electrically connected to the input end of the saturation prediction module; the output end of the saturation prediction module is electrically connected to the input end of the early warning module;

[0050] The data collection module includes a logistics collection unit, an order collection unit and a warehouse collection unit; the logistics collection unit is used to collect transportation information of cross-border logistics transportation; the order collection unit is used to collect order data information of goods; the warehouse collection unit is used to collect the maximum inventory capacity, inventory depletion value and current inventory saturation of the warehouse;

[0051] The order collection module includes an object collection unit and a basic collection unit; the object collection unit is used to aggregate order information that meets the conditions to generate an object order collection; the basic collection unit is used to extract order data of the object collection unit from the total order data to generate a basic order collection;

[0052] The order trend module includes an actual trend unit and a predicted trend unit; the actual trend unit is used to generate a trend chart according to actual order information; the predicted trend unit predicts the subsequent order trend according to the order information and generates a trend chart;

[0053] The saturation prediction module includes a static prediction unit and a dynamic prediction unit; the static prediction unit is used to predict the saturation of the warehouse at a specific moment according to the order information; the dynamic prediction unit is used to re-predict the saturation of the warehouse at a specific moment according to the predicted order information;

[0054] The early warning module includes a condition judgment unit and an early warning sending unit; the condition judgment unit is used to judge the saturation of the warehouse; the early warning sending unit is used to send an early warning signal when a specific condition is met.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] 1. The present invention can quickly identify and process high-value orders and optimize resource allocation by acquiring transportation information and order data in real time. By accurately analyzing the trend of order changes, the system can better predict warehouse saturation, thereby reducing inventory backlogs and improving warehouse operating efficiency.

[0057] 2. The present invention uses dynamic and static saturation predictions to enable enterprises to adjust procurement and replenishment strategies in a timely manner to cope with market changes. Predicting whether some goods will become high-quality goods can more accurately predict the warehouse consumption reduction value, thereby concentrating resources to increase sales. The system's accurate prediction and analysis within the transportation cycle provides reliable data support for management, thereby reducing operating costs and risks.

[0058] 3. The present invention sets up a perfect early warning module, combines the warehouse monitoring data in real time, predicts the warehouse saturation, and makes condition judgments, so as to identify overload risks in time. This early warning mechanism can not only prevent potential inventory crises, but also ensure the safety and stability of warehouse operations and guarantee the continuous operation capability of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of a flow chart of a transport scheduling intelligent management method based on cross-border logistics according to the present invention;

[0060] Figure 2 This is a structural schematic diagram of a transportation scheduling intelligent management system based on cross-border logistics in the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Embodiment 1: Figure 1 As shown, the present invention provides a transportation scheduling intelligent management method based on cross-border logistics, and the transportation scheduling intelligent management method includes the following steps:

[0063] Step S1: Obtain the transportation cycle and warehouse data of cross-border logistics transportation, and obtain the order data within the transportation cycle in real time from the start of transportation to generate a warehouse order set;

[0064] Step S1-1, obtain historical data of cross-border logistics transportation, extract the shipping location, destination and transportation method, and determine the transportation cycle T of the current cross-border logistics transportation based on the shipping location, destination and transportation method that match the historical data;

[0065] Step S1-2, obtaining warehouse data, wherein the warehouse data includes product category SKU, inventory quantity corresponding to the product category SKU, maximum warehouse capacity of the warehouse and saturation of the current warehouse;

[0066] Step S1-3: From the start of transportation, real-time monitoring is performed to obtain order data within the transportation cycle T to generate a warehouse order set, where the warehouse order set includes product category SKU and corresponding order quantity.

[0067] Step S2: Set a high-quality order threshold, extract order information with order quantity greater than the high-quality order threshold from the warehouse order set to generate an object order set, and remove the object order set from the warehouse order set to generate a basic order set;

[0068] Step S2-1: Setting the high-quality order threshold G max , traverse the warehouse order set and filter out orders with a quantity greater than the high-quality order threshold G max The order information is aggregated and filtered to generate an object order set;

[0069] Step S2-2: Using the order information in the object order set as an index, delete records with the same order information from the warehouse order set, and retain different order information to generate a basic order set.

[0070] Step S3: construct an object order change trend graph according to the object order set, and predict the warehouse saturation at the end of the transportation cycle through the object order change trend graph and the basic order set, which is recorded as static warehouse saturation;

[0071] Step S3-1, set a time series, and build a target order change trend chart by combining the product category SKU and the corresponding order quantity in the target order set;

[0072] Step S3-2: predict the trend at the end of the transportation cycle T according to the object order change trend chart, obtain the order quantity of the product category SKU corresponding to the trend, and combine the product category SKU and the corresponding order quantity of the basic order set to predict the warehouse saturation at the end of the transportation cycle T, which is recorded as the static saturation D Q , the process of warehouse saturation is as follows:

[0073] The reduction value of warehouse saturation of the object order set at the end of the transportation cycle T uses the following formula:

[0074] ;

[0075] In the formula, B object It is expressed as the predicted reduction value of the warehouse saturation caused by the object order set at the end of the transportation cycle T; V 0M It is represented by the sales speed of products of category M at the time of transportation start; T is the transportation cycle; R M It is represented as the average growth rate of products in the M category; n is represented as the number of SKUs of the product category in the object order set;

[0076] The basic order set uses the following formula to reduce the warehouse saturation at the end of the transportation cycle T:

[0077] ;

[0078] In the formula, B seat It is expressed as the predicted reduction value of warehouse saturation by the basic order set at the end of the transportation cycle T; B avg，i It is represented as the average value of the i-th product; m is the sum of the product quantities in the basic order set;

[0079] At the end of the transportation cycle T, the warehouse saturation is predicted. The predicted saturation is calculated using the following formula:

[0080] ;

[0081] Where D Q It is expressed as the warehouse saturation predicted at the end of the transportation cycle T, recorded as static saturation; B 0 It is expressed as the capacity of the warehouse at the time when transportation starts; B max Expressed as the maximum warehouse capacity of the warehouse.

[0082] Step S4: construct a category change trend graph based on the warehouse order set, predict the order information whose order quantity is greater than the high-quality order threshold in the remaining transportation cycle through the category change trend graph, construct a prediction object set in combination with the object order set, and predict the warehouse saturation at the end of the transportation cycle again based on the prediction object set, which is recorded as dynamic warehouse saturation;

[0083] Step S3-1, set a time series, and build a target order change trend chart by combining the product category SKU and the corresponding order quantity in the target order set;

[0084] Step S3-2: predict the trend at the end of the transportation cycle T according to the object order change trend chart, obtain the order quantity of the product category SKU corresponding to the trend, and combine the product category SKU and the corresponding order quantity of the basic order set to predict the warehouse saturation at the end of the transportation cycle T, which is recorded as the static saturation D Q , the process of warehouse saturation is as follows:

[0085] The reduction value of warehouse saturation of the object order set at the end of the transportation cycle T uses the following formula:

[0086] ;

[0087] In the formula, B object It is expressed as the predicted reduction value of the warehouse saturation caused by the object order set at the end of the transportation cycle T; V 0M It is represented by the sales speed of products of category M at the time of transportation start; T is the transportation cycle; R M It is represented as the average growth rate of products in the M category; n is represented as the number of SKUs of the product category in the object order set;

[0088] The basic order set uses the following formula to reduce the warehouse saturation at the end of the transportation cycle T:

[0089] ;

[0090] In the formula, B seat It is expressed as the predicted reduction value of warehouse saturation by the basic order set at the end of the transportation cycle T; B avg，i Expressed as the average value of the i-th product;

[0091] At the end of the transportation cycle T, the warehouse saturation is predicted. The predicted saturation is calculated using the following formula:

[0092] ;

[0093] Where D Q It is expressed as the warehouse saturation predicted at the end of the transportation cycle T, recorded as static saturation; B 0 It is expressed as the capacity of the warehouse at the time when transportation starts; B max Expressed as the maximum warehouse capacity of the warehouse.

[0094] Step S5: Obtain order data for historical periods, extract the number of returned orders in each historical period, and calculate the average and standard deviation of the returned orders. Based on the calculated average and standard deviation, predict the total number of returned orders at the end of the transportation period;

[0095] Obtain order data for historical periods, extract the number of returned orders in each historical period, and calculate the average and standard deviation of returned orders. Based on the calculated average and standard deviation, predict the total number of returned orders at the end of the transportation period. The prediction calculation formula for the total number of returned orders is:

[0096] ;

[0097] In the formula, H T It is represented by the total number of returned orders predicted in the current transportation cycle T; z is represented by the number of historical cycles; H i It is represented as the number of returned orders in the i-th historical period, and c is represented as the fluctuation range constant of the number of returned orders.

[0098] Step S6, set the inventory backlog threshold, obtain the transportation information of cross-border logistics transportation, calculate the saturation increment of the warehouse based on the transportation information, and combine the predicted static warehouse saturation, dynamic warehouse saturation and total number of returned orders to calculate the warehouse inventory backlog rate, and use the set inventory backlog threshold to make an early warning judgment on the warehouse saturation.

[0099] Step S6-1: Set the inventory backlog threshold J max , obtain the transportation information of cross-border logistics transportation, which includes product category SKU and corresponding order quantity, and calculate the saturation increment of the warehouse according to the transportation information, that is, add the new order quantity of all product category SKUs to obtain the total order quantity;

[0100] Step S6-2: According to the total order quantity and the maximum warehouse capacity B of the transportation information max Perform a percentage calculation to find out the saturation increment D of the warehouse caused by the transportation information calculation new ;

[0101] Step S6-3: According to the static warehouse saturation D Q , Dynamic warehouse saturation D W 、Total number of returned orders H T and degree increment D new Conditional judgment is performed on the warehouse backlog rate. The judgment conditions are as follows:

[0102] When J is satisfied max >D Q +H T / B max +D new and J max >DW +H T / B max +D new When the new logistics arrive at the warehouse at the end of the transportation cycle T, it is judged that there is sufficient available space in the warehouse;

[0103] When J is satisfied max ≤D Q +H T / B max +D new and J max ≤D W +H T / B max +D new When the new logistics arrive at the warehouse at the end of the transportation cycle T, it is judged that the available space in the warehouse is insufficient and the warehouse will face the risk of overloading, and an overloading risk warning signal will be issued.

[0104] For example, the cross-border logistics transportation cycle T = 10 days, the maximum inventory capacity B max = 10,000 orders, initial inventory B 0 = 10,000 orders, the number of SKUs in the object order set is n=3, the number of orders for cross-border logistics transportation is 3,000 orders, the saturation increment of the warehouse is 30%, and the inventory backlog threshold J is set max =90%, set the quality order threshold G max =50 orders / day, the initial sales speed V corresponding to the SKU 0M :

[0105] SKU1: V 0M =100 orders / day;

[0106] SKU2: V 0M =80 orders / day;

[0107] SKU3: V 0M =50 orders / day;

[0108] The average growth rate of each SKU M :

[0109] SKU1: R M =10%;

[0110] SKU1: R M =15%;

[0111] SKU1: R M =20%;

[0112] Calculate the total number of sales of each SKU in the object order set at the end of the shipping period T:

[0113] SKU1=100*10*(1+0.1)=1100 orders;

[0114] SKU2=80*10*(1+0.15)=920 orders;

[0115] SKU3=50*10*(1+0.2)=600 orders;

[0116] SKU (total) = 1100 + 920 + 600 = 2620 orders;

[0117] The basic order set contains three products (A, B, C), and their average sales quantities are as follows:

[0118] B avg，A =40 orders;

[0119] B avg，B =30 orders;

[0120] B avg，C =45 single;

[0121] Calculate the total number of products sold in the base order set at the end of the shipping period T:

[0122] B seat =10*(40+30+45)=1150 orders;

[0123] Calculate the warehouse saturation at the end of the transportation cycle T, recorded as static warehouse saturation:

[0124] D Q = (10000-1150-2620) / 10000*100%=62.3%;

[0125] Assume that product A will exceed the set premium order threshold G at T / 2 max , SKU: V 0A =150 orders / day, SKU: R A =60%;

[0126] Recursively call the prediction calculation to calculate the sales quantity of product A;

[0127] Product A: SKU = 150 * (10 / 2) * (1 + 0.6) = 1200 orders

[0128] By inserting the data, we can see that product A sells 1,000 more orders in the remaining T / 2. The value of the dynamic warehouse saturation is calculated as:

[0129] D W =62.3%-1000 / 1000*100%=52.3%;

[0130] There are 4 historical cycles, and the corresponding return order quantities are as follows:

[0131] Historical cycle number 1 is: 30 returned orders;

[0132] Historical cycle number 2 is: 25 returned orders;

[0133] Historical cycle number 3 is: return order 35;

[0134] Historical cycle number 4 is: 40 returned orders;

[0135] By using the data to calculate, the total number of returned orders in the current period is:

[0136] H T =32.5+4*5.57=54.78;

[0137] After rounding, the total number of returned orders predicted in the current transportation cycle is approximately 55.

[0138] J max <D Q +H T / B max +D new =62.3%+55 / 10000+30%=92.3055%;

[0139] J max <>D W +H T / B max +D new =52.3%+55 / 10000+30%=82.3055%;

[0140] Cannot satisfy J at the same time max >D Q +H T / B max +D new or J max >D W +H T / B max +D new , it is judged that at the end of the transportation cycle T, after the new logistics arrives at the warehouse, the available space in the warehouse is insufficient, the warehouse will face the risk of overloading, and an overloading risk warning signal will be issued.

[0141] Embodiment 2, as Figure 2 As shown, the present invention provides a transport scheduling intelligent management system based on cross-border logistics, and the transport scheduling intelligent management system includes a data acquisition module, an order collection module, an order trend module, a saturation prediction module and an early warning module;

[0142] The data collection module is used to collect cross-border logistics transportation information, order information and warehouse information; the order collection module is used to construct a collection based on the collected information; the order trend module is used to generate a trend chart based on the constructed collection; the saturation prediction module is used to predict the trend based on each trend chart; the early warning module is used to compare and judge based on the predicted data, and perform early warning processing for situations that meet specific conditions;

[0143] The output end of the data acquisition module is electrically connected to the input end of the order collection module; the output end of the order collection module is electrically connected to the input end of the order trend module; the output end of the order trend module is electrically connected to the input end of the saturation prediction module; the output end of the saturation prediction module is electrically connected to the input end of the early warning module.

[0144] The data collection module includes a logistics collection unit, an order collection unit and a warehouse collection unit; the logistics collection unit is used to collect transportation information of cross-border logistics transportation; the order collection unit is used to collect order data information of goods; the warehouse collection unit is used to collect the maximum inventory capacity, inventory depletion value and current inventory saturation of the warehouse;

[0145] The order collection module includes an object collection unit and a basic collection unit; the object collection unit is used to aggregate order information that meets the conditions to generate an object order collection; the basic collection unit is used to extract order data of the object collection unit from the total order data to generate a basic order collection;

[0146] The order trend module includes an actual trend unit and a predicted trend unit; the actual trend unit is used to generate a trend chart according to actual order information; the predicted trend unit predicts the subsequent order trend according to the order information and generates a trend chart;

[0147] The saturation prediction module includes a static prediction unit and a dynamic prediction unit; the static prediction unit is used to predict the saturation of the warehouse at a specific moment according to the order information; the dynamic prediction unit is used to re-predict the saturation of the warehouse at a specific moment according to the predicted order information;

[0148] The early warning module includes a condition judgment unit and an early warning sending unit; the condition judgment unit is used to judge the saturation of the warehouse; the early warning sending unit is used to send an early warning signal when a specific condition is met.

[0149] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A transportation scheduling intelligent management method based on cross-border logistics, characterized by: The transportation scheduling intelligent management method comprises the following steps: Step S1: Obtain the transportation cycle and warehouse data of cross-border logistics transportation, and obtain the order data within the transportation cycle in real time from the start of transportation to generate a warehouse order set; Step S2: Set a high-quality order threshold, extract order information with order quantity greater than the high-quality order threshold from the warehouse order set to generate an object order set, and remove the object order set from the warehouse order set to generate a basic order set; Step S3: construct an object order change trend graph according to the object order set, and predict the warehouse saturation at the end of the transportation cycle through the object order change trend graph and the basic order set, which is recorded as static warehouse saturation; Step S4: construct a category change trend graph based on the warehouse order set, predict the order information whose order quantity is greater than the high-quality order threshold in the remaining transportation cycle through the category change trend graph, construct a prediction object set in combination with the object order set, and predict the warehouse saturation at the end of the transportation cycle again based on the prediction object set, which is recorded as dynamic warehouse saturation; Step S4-1: extract the product category SKU and the corresponding order quantity in the warehouse order set, build a category change trend chart based on the changes of the product category SKU and the corresponding order quantity at different times, and predict based on the category change trend chart that at the end of the transportation cycle T, the order quantity is greater than the high-quality order threshold G max The order information is predicted based on the category change trend chart. The formula used is as follows: ； In the formula, B pre It is represented by the number of orders that are greater than the high-quality order threshold within the remaining time of the transportation cycle, and t<T; k is the intercept of the linear regression model; l is the slope, which is the increase or decrease in the sales quantity at each time series; t is the remaining time of the transportation cycle; Step S4-2, extracting order information that satisfies the order quantity greater than the high-quality order threshold within the remaining transportation cycle t, building a prediction object set in combination with the object order set, and removing the prediction object set from the warehouse order set to generate a prediction basic order set; Step S4-3, recursively call the prediction calculation method of step S3, and predict the warehouse saturation at the end of the transportation cycle again. The prediction object set uses the prediction calculation method of the object order set in step S3, and the prediction basic order set uses the prediction calculation method of the basic order set in step S3. The warehouse saturation predicted again is recorded as the dynamic warehouse saturation D W； Step S5: Obtain order data for historical periods, extract the number of returned orders in each historical period, and calculate the average and standard deviation of the returned orders. Based on the calculated average and standard deviation, predict the total number of returned orders at the end of the transportation period; Step S6, set the inventory backlog threshold, obtain the transportation information of cross-border logistics transportation, calculate the saturation increment of the warehouse based on the transportation information, and combine the predicted static warehouse saturation, dynamic warehouse saturation and total number of returned orders to calculate the warehouse inventory backlog rate, and use the set inventory backlog threshold to make an early warning judgment on the warehouse saturation.

2. According to the intelligent management method of transportation scheduling based on cross-border logistics according to claim 1, it is characterized by: The specific steps of step S1 are as follows: Step S1-1, obtain historical data of cross-border logistics transportation, extract the shipping location, destination and transportation method, and determine the transportation cycle T of the current cross-border logistics transportation based on the shipping location, destination and transportation method that match the historical data; Step S1-2, obtaining warehouse data, wherein the warehouse data includes product category SKU, inventory quantity corresponding to the product category SKU, maximum warehouse capacity of the warehouse and saturation of the current warehouse; Step S1-3: From the start of transportation, real-time monitoring is performed to obtain order data within the transportation cycle T to generate a warehouse order set, where the warehouse order set includes product category SKU and corresponding order quantity.

3. The method for intelligent management of transportation scheduling based on cross-border logistics according to claim 2 is characterized by: The specific steps of step S2 are as follows: Step S2-1: Setting the high-quality order threshold G max , traverse the warehouse order set and filter out orders with a quantity greater than the high-quality order threshold G max The order information is aggregated and filtered to generate an object order set; Step S2-2: Using the order information in the object order set as an index, delete records with the same order information from the warehouse order set, and retain different order information to generate a basic order set.

4. The method for intelligent management of transportation scheduling based on cross-border logistics according to claim 3 is characterized by: The specific steps of step S3 are as follows: Step S3-1, set a time series, and build a target order change trend chart by combining the product category SKU and the corresponding order quantity in the target order set; Step S3-2: predict the trend at the end of the transportation cycle T according to the object order change trend chart, obtain the order quantity of the product category SKU corresponding to the trend, and combine the product category SKU and the corresponding order quantity of the basic order set to predict the warehouse saturation at the end of the transportation cycle T, which is recorded as the static saturation D Q , the process of warehouse saturation is as follows: The reduction value of warehouse saturation of the object order set at the end of the transportation cycle T uses the following formula: ； In the formula, B object It is expressed as the predicted reduction value of the warehouse saturation caused by the object order set at the end of the transportation cycle T; V 0M It is represented by the sales speed of products of category M at the time of transportation start; T is the transportation cycle; R M It is represented as the average growth rate of products in the M category; n is represented as the number of SKUs of the product category in the object order set; The basic order set uses the following formula to reduce the warehouse saturation at the end of the transportation cycle T: ； In the formula, B seat It is expressed as the predicted reduction value of warehouse saturation by the basic order set at the end of the transportation cycle T; B avg，i It is represented as the average value of the i-th product; m is the sum of the product quantities in the basic order set; At the end of the transportation cycle T, the warehouse saturation is predicted. The predicted saturation is calculated using the following formula: ； Where D Q It is represented by the predicted warehouse saturation at the end of the transportation cycle T, recorded as static saturation; B0 represents the capacity of the warehouse at the beginning of transportation; B max Expressed as the maximum warehouse capacity of the warehouse.

5. The method for intelligent management of transportation scheduling based on cross-border logistics according to claim 4 is characterized by: In step S5, the order data of the historical period is obtained, the number of returned orders in each historical period is extracted, and the average value and standard deviation of the returned orders are calculated. Based on the calculated average value and standard deviation, the total number of returned orders at the end of the transportation period is predicted. The prediction calculation formula for the total number of returned orders is: ； In the formula, H T It is represented by the total number of returned orders predicted in the current transportation cycle T; z is represented by the number of historical cycles; H i It is represented as the number of returned orders in the i-th historical period, and c is represented as the fluctuation range constant of the number of returned orders.

6. The method for intelligent management of transportation scheduling based on cross-border logistics according to claim 5 is characterized by: The specific steps of step S6 are as follows: Step S6-1: Set the inventory backlog threshold J max , obtain the transportation information of cross-border logistics transportation, which includes product category SKU and corresponding order quantity, and calculate the saturation increment of the warehouse according to the transportation information, that is, add the new order quantity of all product category SKUs to obtain the total order quantity; Step S6-2: According to the total order quantity and the maximum warehouse capacity B of the transportation information max Perform a percentage calculation to find out the saturation increment D of the warehouse caused by the transportation information calculation new ; Step S6-3: According to the static warehouse saturation D Q , Dynamic warehouse saturation D W 、Total number of returned orders H T and degree increment D new Conditional judgment is performed on the warehouse backlog rate. The judgment conditions are as follows: When J is satisfied max >D Q +H T / B max +D new and J max >D W +H T / B max +D new When the new logistics arrive at the warehouse at the end of the transportation cycle T, it is judged that there is sufficient available space in the warehouse; When J is satisfied max ≤D Q +H T / B max +D new and J max ≤D W +H T / B max +D new When the new logistics arrive at the warehouse at the end of the transportation cycle T, it is judged that the available space in the warehouse is insufficient and the warehouse will face the risk of overloading, and an overloading risk warning signal will be issued.

7. A transport scheduling intelligent management system based on cross-border logistics, which is applied to a transport scheduling intelligent management method based on cross-border logistics as described in any one of claims 1 to 6, characterized in that: The transportation scheduling intelligent management system includes a data acquisition module, an order collection module, an order trend module, a saturation prediction module and an early warning module; The data collection module is used to collect cross-border logistics transportation information, order information and warehouse information; the order collection module is used to construct a collection based on the collected information; the order trend module is used to generate a trend chart based on the constructed collection; the saturation prediction module is used to predict the trend based on each trend chart; the early warning module is used to compare and judge based on the predicted data, and perform early warning processing for situations that meet specific conditions; The output end of the data acquisition module is electrically connected to the input end of the order collection module; the output end of the order collection module is electrically connected to the input end of the order trend module; the output end of the order trend module is electrically connected to the input end of the saturation prediction module; the output end of the saturation prediction module is electrically connected to the input end of the early warning module.

8. According to claim 7, a transportation scheduling intelligent management system based on cross-border logistics is characterized in that: The data collection module includes a logistics collection unit, an order collection unit and a warehouse collection unit; the logistics collection unit is used to collect transportation information of cross-border logistics transportation; The order collection unit is used to collect order data information of commodities; The warehouse collection unit is used to collect the maximum inventory capacity, inventory depletion value and current inventory saturation of the warehouse; The order collection module includes an object collection unit and a basic collection unit; The object collection unit is used to aggregate the order information that meets the conditions to generate an object order collection; The basic set unit is used to extract the order data of the object set unit from the total order data to generate a basic order set; The order trend module includes an actual trend unit and a predicted trend unit; The actual trend unit is used to generate a trend graph according to actual order information; The forecasting trend unit forecasts the future order trend based on the order information and generates a trend graph.

9. According to claim 7, a transportation scheduling intelligent management system based on cross-border logistics is characterized in that: The saturation prediction module includes a static prediction unit and a dynamic prediction unit; the static prediction unit is used to predict the saturation of the warehouse at a specific moment according to the order information; the dynamic prediction unit is used to re-predict the saturation of the warehouse at a specific moment according to the predicted order information; The early warning module includes a condition judgment unit and an early warning sending unit; the condition judgment unit is used to judge the saturation of the warehouse; the early warning sending unit is used to send an early warning signal when a specific condition is met.

Images