Method and device for obtaining distribution cabinet of goods agent

Abstract

The invention discloses a method and a device for acquiring a distribution cabinet by a freight agent, and the method comprises the steps: obtaining order-receiving cargo data: obtaining the order-receiving cargo data through inputting cargo data or exporting the cargo data by the freight agent; cargo data processing: processing the order receiving cargo data so as to obtain cargo data of different dimensions; cargo data distribution: distributing the processed data to a distribution cabinet pool for distribution; determining a cabinet distribution order, wherein the cabinet distribution order is determined according to the cargo data distributed by the cabinet distribution pool; cabinet distribution requirements are read, and the cabinet distribution requirements of different goods data are read; obtaining a cabinet matching result, and determining a cabinet matching model according to the cabinet matching demand so as to obtain the cabinet matching result; according to the method for obtaining the distribution cabinet of the goods substitute, the operation efficiency can be improved, the manual error and the time cost are reduced, the distribution is reasonable, and the utilization rate of the container is maximized.

Description

Technical Field

[0001] The present invention relates to a freight forwarding container matching technology, and in particular to a method and device for a freight forwarding container matching. Background Art

[0002] Freight forwarding cargo consolidation refers to the service in international trade where the cargo consigned by the consignor is not enough to fill a full container, so it needs to be packed together with the cargo of other consignors for transportation. This service is adopted when the consignor's consignment quantity is insufficient, which can improve the utilization rate of containers and reduce transportation costs. Through reasonable loading, the utilization rate of containers can be maximized, empty runs and empty container returns can be reduced, and the cargo loading capacity of each container can be increased.

[0003] Basic cargo data interaction is carried out through system entry, table analysis, and API system docking. The system performs preliminary cargo distribution by classifying the data, training data labels, and AI intelligent container search. The profit is calculated through high-dimensional kernel functions. Multiple containers need to use chaotic dynamics dynamic programming to dynamically adjust the container-cargo relationship to maximize the profit of container distribution. Summary of the invention

[0004] The present invention aims at the technical problem of low efficiency of freight forwarding in obtaining cabinets in the prior art and provides a method and device for freight forwarding in obtaining cabinets.

[0005] In order to solve the above technical problems, the present invention is solved by the following technical solutions:

[0006] The present invention has significant technical effects due to the adoption of the above technical solution:

[0007] A method for a freight forwarder to obtain cabinet matching, comprising an order receiving end, a cabinet matching end and a configuration end; the method comprises:

[0008] Receiving side:

[0009] Acquisition of order cargo data: by inputting cargo data or exporting cargo data from the freight forwarder;

[0010] Cargo data processing: processing the order cargo data to obtain cargo data of different dimensions;

[0011] Distribution of cargo data: distribute the processed data to the distribution pool for distribution;

[0012] Cabinet side:

[0013] Determination of container distribution orders: Determine container distribution orders based on the cargo data allocated by the container distribution pool;

[0014] Reading of container distribution requirements, reading of container distribution requirements for different cargo data;

[0015] Obtaining cabinet matching results: determining the cabinet matching model based on cabinet matching requirements to obtain cabinet matching results;

[0016] Configuration side:

[0017] The cabinet distribution results need to be obtained based on the cabinet configuration.

[0018] Preferably, obtaining the cabinet matching result, determining the cabinet matching model according to the cabinet matching requirement to obtain the cabinet matching result includes:

[0019] Classification of cargo data: Cargo data in the distribution pool is classified by linear regression;

[0020] Searching for matching containers: For the classified cargo data, use artificial intelligence deep learning matching rules to find matching containers.

[0021] Preferably, the search for the distribution cabinet also includes adjusting the distribution cabinet by means of chaotic dynamics dynamic programming, so as to obtain the optimal solution of the total profit P of the distribution cabinet.

[0022] Preferably, parallel computing is used to accelerate the process of cargo data processing and model training for the search for distribution boxes.

[0023] As a preferred option, the optimal solution for the distribution cabinet box includes:

[0024] Resource configuration, including configuration of cargo attributes, box attributes, maintenance costs, and parallel computing resources;

[0025] A solution to generate multiple distribution cabinets through chaotic mapping function;

[0026] Perform parallel dynamic programming optimization on the solutions of multiple distribution cabinets generated;

[0027] Obtaining the optimal solution for the total profit P of the distribution cabinet,

[0028]

[0029] Where N is the total number of goods, n is the number of goods, n = 1, 2...N; W n is the weight of the nth cargo, V n is the statistics of the nth cargo, C n is the classification mark of the nth cargo, s is the box number, s = 1, 2…S; W s is the maximum load-bearing capacity of box s, V s is the maximum volume of box s, C s is the cost of box s, M s is the maintenance cost of box s, X ns If item n is assigned to box s, then X ns =1, otherwise 0; Ys is the total weight of box s, Z s is the total volume of box s, K s is the number of boxes s, and P is the total profit.

[0030] Preferably, the cargo data includes entrustment information, agent information, port area information, cargo weight data, and cargo volume data.

[0031] In order to solve the above technical problem, the present invention also provides a device for a freight forwarder to obtain a container, which is a device for implementing the method for a freight forwarder to obtain a container.

[0032] The present invention has significant technical effects due to the adoption of the above technical solution:

[0033] The method for a freight forwarder to obtain container matching designed by the present invention can improve operation efficiency, reduce manual errors and time costs, reasonably match loads, and maximize the utilization rate of containers.

[0034] The present invention can greatly improve computing efficiency through parallel computing, especially when processing large-scale data. The present invention uses chaotic dynamics to generate diverse initial solutions, and dynamic programming is used to find the optimal or approximately optimal solution based on each solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 Flow chart of the method of the present invention; DETAILED DESCRIPTION

[0036] The present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0037] Example 1

[0038] A method for a freight forwarder to obtain cabinet matching, comprising an order receiving end, a cabinet matching end and a configuration end; the method comprises:

[0039] Receiving side:

[0040] Acquisition of order cargo data: by inputting cargo data or exporting cargo data from the freight forwarder;

[0041] Cargo data processing: processing the order cargo data to obtain cargo data of different dimensions;

[0042] Distribution of cargo data: distribute the processed data to the distribution pool for distribution;

[0043] Cabinet side:

[0044] Determination of container distribution orders: Determine container distribution orders based on the cargo data allocated by the container distribution pool;

[0045] Reading of container distribution requirements, reading of container distribution requirements for different cargo data;

[0046] Obtaining cabinet matching results: determining the cabinet matching model based on cabinet matching requirements to obtain cabinet matching results;

[0047] Configuration side:

[0048] The cabinet distribution results need to be obtained based on the cabinet configuration.

[0049] The cabinet matching results are obtained by determining the cabinet matching model based on the cabinet matching requirements to obtain the cabinet matching results, including:

[0050] Classification of cargo data: Cargo data in the distribution pool is classified by linear regression;

[0051] Searching for matching containers: For the classified cargo data, use artificial intelligence deep learning matching rules to find matching containers.

[0052] Example 2

[0053] On the basis of Example 1, the search for the distribution cabinet in this embodiment further includes adjusting the distribution cabinet by means of chaotic dynamics dynamic programming, so as to obtain the optimal solution of the total profit P of the distribution cabinet.

[0054] The search for distribution boxes is combined with parallel computing to accelerate the process of cargo data processing and model training.

[0055] The optimal solutions for distribution cabinets include:

[0056] Resource configuration, including configuration of cargo attributes, box attributes, maintenance costs, and parallel computing resources;

[0057] A solution to generate multiple distribution cabinets through chaotic mapping function;

[0058] Perform parallel dynamic programming optimization on the solutions of multiple distribution cabinets generated;

[0059] Obtaining the optimal solution for the total profit P of the distribution cabinet,

[0060]

[0061] Where N is the total number of goods, n is the number of goods, n = 1, 2...N; W n is the weight of the nth cargo, V n is the statistics of the nth cargo, C n is the classification mark of the nth cargo, s is the box number, s = 1, 2…S; W s is the maximum load-bearing capacity of box s, V s is the maximum volume of box s, C s is the cost of box s, Ms is the maintenance cost of box s, X ns If item n is assigned to box s, then X ns =1, otherwise 0; Y s is the total weight of box s, Z s is the total volume of box s, K s is the number of boxes s, and P is the total profit.

[0062] Cargo data includes entrustment information, agent information, port area information, cargo weight data, and cargo volume data.

[0063] Example 3

[0064] Based on the above embodiment, this embodiment is a device for a freight forwarder to obtain a container, which is a device for implementing the method for a freight forwarder to obtain a container.

[0065] Example 4

[0066] Based on the above embodiment, this embodiment inputs cargo data into the system or exports order cargo data from the freight forwarding system, and submits the data to the cabinet matching tool to be matched pool. After the data is prepared, click the cabinet matching system to verify the cargo data and issue an alarm for orders that do not meet the conditions. For example, the limited agent and the designated agent are different, and the weight or volume of some goods exceeds the single box limit.

[0067] Train labeled data in advance so that you can predict and train the neural network. The training data labeling is done through data labeling, annotation, review, classification, transcription, and processing. You need to preset some cost prices in different dimensions.

[0068] When starting to allocate containers, the four attributes of the cargo, namely the consignor, port area, designated agent, and customs seal, are used as four dimensions to classify the cargo using linear regression.

[0069] Pre-trained neural networks use artificial intelligence to deeply learn the box matching rules. AI helps orders find boxes at high speed. During the high-speed box search process, it repeatedly learns and obtains optimized box search results based on the computer's advanced computing capabilities.

[0070] For the existing profit calculation formulas of different designated agents, the kernel function is used to calculate the high-dimensional function from a low-dimensional perspective and obtain the maximum benefit function for selecting different agents according to the number of votes.

[0071] For multiple containers, the chaotic dynamics dynamic programming method is used. Under the condition that the volume and weight of each container are met, the number of tickets for each container is adjusted again to maximize the final total profit. The intelligent optimization algorithm is used to obtain the maximum profit and the lowest cost, and the final container allocation solution is obtained.

[0072] According to the rules of gross profit calculation, the gross profit value is continuously calculated during the cabinet matching process until the optimized cabinet search result is achieved and the gross profit is maximized.

[0073] The cabinet matching is completed, and the cabinet matching details are viewed. The cabinet matching tasks include the number of orders, total weight, volume, number of boxes, gross profit, etc. The display of a single box includes specific order details and the number of single box orders, total volume, gross profit, etc. The tool supports dynamic addition and deletion of goods for real-time cabinet matching calculations.

[0074] The final cabinet matching result confirmation or system back-pushing tool will add the confirmed cabinet matching result to the system big data model for learning, which is convenient for the recommendation of cabinet matching with preference.

Claims

1. A method for a freight forwarder to obtain a cabinet, comprising an order receiving end, a cabinet distribution end and a configuration end; the method comprises: Receiving side: Acquisition of order cargo data: by inputting cargo data or exporting cargo data from the freight forwarder; Cargo data processing: processing the order cargo data to obtain cargo data of different dimensions; Distribution of cargo data: distribute the processed data to the distribution pool for distribution; Cabinet side: Determination of container distribution orders: Determine container distribution orders based on the cargo data allocated by the container distribution pool; Reading of container distribution requirements, reading of container distribution requirements for different cargo data; Obtaining cabinet matching results: determining the cabinet matching model based on cabinet matching requirements to obtain cabinet matching results; Configuration side: The cabinet distribution results need to be obtained based on the cabinet configuration.

2. A method for a freight forwarder to obtain a container distribution according to claim 1, characterized in that: The cabinet matching results are obtained by determining the cabinet matching model based on the cabinet matching requirements to obtain the cabinet matching results, including: Classification of cargo data: Cargo data in the distribution pool is classified by linear regression; Searching for matching containers: For the classified cargo data, use artificial intelligence deep learning matching rules to find matching containers.

3. A method for a freight forwarder to obtain a container according to claim 2, characterized in that: The search for distribution cabinets also includes adjusting the distribution cabinets through chaotic dynamics dynamic programming to obtain the optimal solution for the total profit P of the distribution cabinets.

4. A method for a freight forwarder to obtain a container distribution according to claim 3, characterized in that: The search for distribution boxes is combined with parallel computing to accelerate the process of cargo data processing and model training.

5. A method for a freight forwarder to obtain a container distribution as claimed in claim 3, characterized in that: The optimal solutions for distribution cabinets include: Resource configuration, including configuration of cargo attributes, box attributes, maintenance costs, and parallel computing resources; A solution to generate multiple distribution cabinets through chaotic mapping function; Perform parallel dynamic programming optimization on the solutions of multiple distribution cabinets generated; Obtaining the optimal solution for the total profit P of the distribution cabinet, Where N is the total number of goods, n is the number of goods, n = 1, 2...N; W n is the weight of the nth cargo, V n is the statistics of the nth cargo, C n is the classification mark of the nth cargo, s is the box number, s = 1, 2…S; W s is the maximum load-bearing capacity of box s, V s is the maximum volume of box s, C s is the cost of box s, M s is the maintenance cost of box s, X ns If item n is assigned to box s, then X ns =1, otherwise 0; Y s is the total weight of box s, Z s is the total volume of box s, K s is the number of boxes s, and P is the total profit.

6. A method for a freight forwarder to obtain a container distribution according to claim 1, characterized in that: Cargo data includes entrustment information, agent information, port area information, cargo weight data, and cargo volume data.

7. A device for a freight forwarder to obtain a container, characterized in that: A device for implementing the method for a freight forwarder to obtain a container as described in any one of claims 1-6.

Images