Scheduling method and system for automobile logistics supply chain

Abstract

The invention discloses a scheduling method and system for an automobile logistics supply chain. The method comprises the following steps: setting high-definition shooting equipment to shoot logistics labels on cargo boxes during logistics warehousing; according to the method, text area detection and image text-to-computer text conversion are carried out through a deep learning technology, the end point information and the size information of the goods are extracted, the optimal automobile planning scheme can be determined according to the number information and the size information of the goods boxes, the optimal automobile planning scheme is the minimum automobile use scheme, and the optimal automobile planning efficiency is improved. If the vehicles which are not going out cannot meet the minimum vehicle use scheme, the vehicles need to be called from other garage stations for transportation, due to the fact that the scheduling capabilities of different garage stations are different, and the vehicles which can be scheduled in each time period are different, historical data of different garage stations are analyzed, the optimal scheduling time period is determined, and the optimal scheduling time period is obtained. And finally, scheduling the required automobiles in the optimal scheduling time period to realize cargo transportation.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics supply chain, and in particular to a scheduling method and system for an automobile logistics supply chain. Background Art

[0002] At present, the field of intelligent logistics is increasingly attracting widespread attention and research. One of its core issues is how to efficiently dispatch logistics transportation vehicles to achieve improved transportation efficiency and reduced costs.

[0003] However, existing logistics transportation vehicle scheduling methods rely on manual scheduling and simple rule-making. These methods are limited in dealing with complex and changeable transportation scenarios, making it difficult for scheduling solutions to adapt to the volatility of actual transportation conditions, resulting in low vehicle utilization, low transportation efficiency, and unnecessary increase in transportation costs. Summary of the Invention

[0004] In order to solve the above technical problems, a scheduling method and system for an automobile logistics supply chain are provided. This technical solution solves the problem that the existing logistics transportation automobile scheduling method proposed in the above background technology relies on manual scheduling and simple rule-making. These methods are limited in dealing with complex and changeable transportation scenarios, making it difficult for scheduling solutions to adapt to the volatility of actual transportation conditions, resulting in low vehicle utilization, low transportation efficiency, and unnecessary increase in transportation costs.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: In a first aspect of the present invention, a scheduling method for an automobile logistics supply chain is proposed, comprising: When the goods are put into storage, high-definition camera equipment is used to take pictures of the logistics labels on the cargo boxes to obtain pictures of the logistics information labels; Preprocessing the logistics information label image, wherein the preprocessing is denoising; Analyze and extract text from the denoised logistics information label image to obtain logistics text information data, including the destination information and size information of the goods; Select all cargoes with the same destination information and determine the most optimized truck transportation plan; Determine vehicle dispatch information based on the comparison of the optimized vehicle transportation plan with vehicles that have not yet traveled; Obtain the vehicle dispatch capabilities of several other depots in the region and determine the optimal vehicle dispatch time period; Dispatch vehicles to the depot within the optimized vehicle dispatching time period to deliver and transport cargo logistics.

[0006] Preferably, the pre-processing of the logistics information label image specifically includes the following steps: Convert the logistics information label image into a grayscale image, calculate the RGB three-channel difference value, and generate the first noise image through threshold filtering under the grayscale image and three-channel difference value calculation; The logistics information label image is converted into HSV space and processed by Gaussian blur to obtain the second noise image; Merging the first noise image and the second noise image to obtain a merged noise image; Retrieve a pre-set standard h-channel from the database, compare the standard h-channel with the h-channel of the logistics information label image, obtain a comparison result, and linearly fuse the comparison result with the merged noise map to obtain the h-channel correction; Perform s-channel correction on logistics information label images; The rectified h channel and s channel are fused to obtain the denoised image.

[0007] Preferably, the analyzing of the text in the logistics information label image after denoising specifically includes the following steps: Mark the area of the logistics information label image in rows; The labeled images are combined into a training set and trained through the object detection model until convergence; The segmented image blocks are put into the trained object detection model for object detection of text areas, and the coordinates of the text area in each image block are obtained and output.

[0008] Preferably, the extraction of text from the denoised logistics information label image specifically includes the following steps: Based on the coordinates of the complete text area, obtain each complete text area in the logistics information label image; Based on the text content in the logistics information label images, the regional coordinates of the logistics information label images are marked and formed into a training set; Train a hybrid model consisting of CNN and LSTM based on deep learning attention mechanism until convergence; The text area of the segmented image block is put into the trained hybrid model for text recognition to obtain the specific text in the text.

[0009] Preferably, the steps of selecting all cargoes with the same destination information and determining the optimal automobile transportation plan specifically include the following steps: According to the destination information of each cargo, the cargo boxes with the same destination are selected; Determine the total volume of the transported goods based on the number and size of cargo boxes at the same destination; Get the transport volume of different cars; Calculations are performed based on the transport volumes of different vehicles and the total volume of transported goods to determine a minimum vehicle utilization plan, which is the most optimized vehicle transportation plan.

[0010] Preferably, the step of obtaining the vehicle dispatching capabilities of several other depots in the region and determining the optimal vehicle dispatching time period specifically includes the following steps: Extract data from several other warehouse databases to obtain historical dispatch demand data for different logistics stations, and perform fitting calculations on each dispatch demand-time period change curve for other warehouses. Obtain the maximum vehicle dispatching capacity of several other depots; Calculate the scheduling surplus value-time period change curve based on the maximum vehicle scheduling capacity of several other depots and each scheduling demand-time period change curve of the logistics station; Filter out the time periods where all excess values of several other depots are positive and determine them as the optimal scheduling time periods.

[0011] Preferably, the expression of the variation curve of the scheduling excess value-time period is:

[0012] Where, is the expression of the change curve of the scheduling excess value-time period, The maximum vehicle supply capacity of the depot. is the total number of dispatchable cars at the depot, is the expression of the scheduling demand-time period change curve of the i-th dispatchable car in the depot.

[0013] Preferably, dispatching vehicles to the depot within the optimized vehicle dispatching time period and delivering and transporting the cargo logistics specifically includes the following steps: Several other depots determine the departure time, driving route, and arrival time of the car within the optimized car dispatch time period; Determine the start time of cargo loading based on the arrival time of vehicles dispatched from several other depots; All transport vehicles are loaded and shipped in sequence.

[0014] In a second aspect of the present invention, a scheduling system for an automobile logistics supply chain is proposed, comprising: A shooting module is used to set a high-definition shooting device to shoot the logistics label on the cargo box when the logistics enters the warehouse, and obtain the logistics information label image; A preprocessing module, which is used to preprocess the logistics information label image, and the preprocessing is a denoising process; A recognition module is used to analyze and extract text from the de-noised logistics information label image to obtain logistics text information data, including the destination information and size information of the goods; A transportation plan determination module is used to select all goods with the same destination information and determine the optimal automobile transportation plan; A vehicle dispatch information determination module, configured to determine vehicle dispatch information based on a comparison between the optimized vehicle transportation plan and vehicles that have not traveled; A vehicle dispatch time period determination module, which is used to obtain the vehicle dispatch capabilities of several other depots in the area and determine the optimal vehicle dispatch time period; The shipping module is used to dispatch cars to the warehouse within the optimized car scheduling time period and to ship and transport the goods.

[0015] In a third aspect of the present invention, an electronic device is provided. The electronic device comprises at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of the first aspect of the present invention.

[0016] Compared with the existing technology, the present invention provides a scheduling method and system for automobile logistics supply chain, which has the following beneficial effects: The present invention sets high-definition shooting equipment to capture images of logistics labels when logistics enters the warehouse, removes noise in the logistics information label images to improve the accuracy of subsequent text recognition, and uses deep learning technology to detect text areas and convert image text into computer text to extract the destination information and size information of the goods. According to the quantity information and size information of the cargo boxes, the optimal car planning scheme can be determined. The optimal car planning scheme is the scheme with the least cars. If the cars that have not traveled cannot meet the scheme with the least cars, it is necessary to transfer cars from other warehouses for transportation. Since the scheduling capabilities of different warehouses are different, and the cars that can be dispatched in each time period are also different, the historical data of different warehouses are analyzed to determine the optimal scheduling time period. Finally, the required cars are dispatched within the optimal scheduling time period to realize cargo transportation, which is convenient and fast and meets the needs of the staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Schematic diagram of the scheduling method for the automobile logistics supply chain in the present invention; Figure 2Schematic diagram of the method for preprocessing logistics information label images in the present invention; Figure 3 Schematic diagram of a method for analyzing text in a logistics information label image after denoising in the present invention; Figure 4 Schematic diagram of a method for extracting text from a denoised logistics information label image in the present invention; Figure 5 A schematic diagram of a method for selecting all cargoes with the same destination information and determining an optimized automobile transportation plan in the present invention; Figure 6 This is a schematic diagram of the method for fitting and calculating each scheduling demand-time period change curve of other depots in the present invention. DETAILED DESCRIPTION

[0018] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0019] Example 1 Please refer to Figures 1-6 As shown, a scheduling method for an automobile logistics supply chain includes: When the goods are put into storage, high-definition camera equipment is used to take pictures of the logistics labels on the cargo boxes to obtain pictures of the logistics information labels; Preprocess the logistics information label images, the preprocessing is denoising; Analyze and extract the text in the denoised logistics information label image to obtain logistics text information data, which includes the destination information and size information of the goods; Select all cargoes with the same destination information and determine the most optimized truck transportation plan; Determine vehicle dispatch information based on the comparison of the optimized vehicle transportation plan with vehicles that have not yet traveled; Obtain the vehicle dispatch capabilities of several other depots in the region and determine the optimal vehicle dispatch time period; Dispatch vehicles to the depot within the optimized vehicle dispatching time period to deliver and transport cargo logistics.

[0020] It can be understood by people in this technical field that the present invention sets high-definition shooting equipment to capture images of logistics labels when logistics enter the warehouse, removes noise in the logistics information label images to improve the accuracy of subsequent text recognition, and uses deep learning technology to detect text areas and convert image text into computer text to extract the destination information and size information of the goods. The optimal car planning scheme can be determined based on the number information and size information of the cargo boxes. The optimal car planning scheme is the scheme with the least cars. If the cars that have not traveled cannot meet the scheme with the least cars, it is necessary to retrieve cars from other warehouses for transportation. Since the scheduling capabilities of different warehouses are different, and the cars that can be dispatched in each time period are also different, the historical data of different warehouses are analyzed to determine the optimal scheduling time period. Finally, the required cars are dispatched within the optimal scheduling time period to realize cargo transportation, which is convenient and fast and meets the needs of the staff.

[0021] The preprocessing of logistics information label images specifically includes the following steps: Convert the logistics information label image into a grayscale image, calculate the RGB three-channel difference value, and generate the first noise image through threshold filtering under the grayscale image and three-channel difference value calculation; The logistics information label image is converted into HSV space and processed by Gaussian blur to obtain the second noise image; Merging the first noise image and the second noise image to obtain a merged noise image; Retrieve a pre-set standard h-channel from the database, compare the standard h-channel with the h-channel of the logistics information label image, obtain a comparison result, and linearly fuse the comparison result with the merged noise map to obtain the h-channel correction; Perform s-channel correction on logistics information label images; The rectified h channel and s channel are fused to obtain the denoised image.

[0022] The analysis of the text in the denoised logistics information label image specifically includes the following steps: Mark the area of the logistics information label image in rows; The labeled images are combined into a training set and trained through the object detection model until convergence; The segmented image blocks are put into the trained object detection model for object detection of text areas, and the coordinates of the text area in each image block are obtained and output.

[0023] Extracting text from the denoised logistics information label image specifically includes the following steps: Based on the coordinates of the complete text area, obtain each complete text area in the logistics information label image; Based on the text content in the logistics information label images, the regional coordinates of the logistics information label images are marked and formed into a training set; Train a hybrid model consisting of CNN and LSTM based on deep learning attention mechanism until convergence; The text area of the segmented image block is put into the trained hybrid model for text recognition to obtain the specific text in the text.

[0024] Select all cargoes with the same destination information and determine the optimal truck transportation plan, which specifically includes the following steps: According to the destination information of each cargo, the cargo boxes with the same destination are selected; Determine the total volume of the transported goods based on the number and size of cargo boxes at the same destination; Get the transport volume of different cars; Calculations are performed based on the transport volume of different vehicles and the total volume of transported goods to determine the minimum vehicle utilization plan, which is the most optimized vehicle transportation plan.

[0025] Obtaining the vehicle dispatch capabilities of several other depots in the region and determining the optimal vehicle dispatch time period involves the following steps: Extract data from several other warehouse databases to obtain historical dispatch demand data for different logistics stations, and perform fitting calculations on each dispatch demand-time period change curve for other warehouses. Obtain the maximum vehicle dispatching capacity of several other depots; Calculate the scheduling surplus value-time period change curve based on the maximum vehicle scheduling capacity of several other depots and each scheduling demand-time period change curve of the logistics station; Filter out the time periods where all excess values of several other depots are positive and determine them as the optimal scheduling time periods.

[0026] The expression of the change curve of scheduling excess value-time period is:

[0027] Where, is the expression of the change curve of the scheduling excess value-time period, The maximum vehicle supply capacity of the depot. is the total number of dispatchable cars at the depot, is the expression of the scheduling demand-time period change curve of the i-th dispatchable car in the depot.

[0028] Dispatching vehicles to the depot within the optimized vehicle dispatching time period and shipping the cargo logistics specifically includes the following steps: Several other depots determine the departure time, driving route, and arrival time of the car within the optimized car dispatch time period; Determine the start time of cargo loading based on the arrival time of vehicles dispatched from several other depots; All transport vehicles are loaded and shipped in sequence.

[0029] In a second aspect of the present invention, a scheduling system for an automobile logistics supply chain is proposed, comprising: The shooting module is used to set a high-definition shooting device to shoot the logistics label on the cargo box when the logistics enters the warehouse, and obtain the logistics information label image; Preprocessing module, which is used to preprocess the logistics information label images, and the preprocessing is denoising; The recognition module is used to analyze and extract the text in the logistics information label image after denoising to obtain logistics text information data. The logistics text information data includes the destination information and size information of the goods; The transportation plan determination module is used to select all goods with the same destination information and determine the optimal automobile transportation plan; A vehicle dispatch information determination module, configured to determine vehicle dispatch information based on a comparison between the optimized vehicle transportation plan and vehicles that have not traveled; A vehicle dispatch time period determination module, which is used to obtain the vehicle dispatch capabilities of several other depots in the area and determine the optimal vehicle dispatch time period; The shipping module is used to dispatch cars to the warehouse within the optimized car scheduling time period and to ship and transport the goods.

[0030] In a third aspect of the present invention, an electronic device is provided. The electronic device comprises at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of the first aspect of the present invention.

[0031] In summary, the present invention sets a high-definition camera to capture images of logistics labels when logistics are put into storage, removes noise in the logistics information label images to improve the accuracy of subsequent text recognition, and uses deep learning technology to detect text areas and convert image text into computer text to extract the destination information and size information of the goods. The optimal car planning scheme can be determined according to the quantity information and size information of the cargo boxes. The optimal car planning scheme is the scheme with the least cars. If the cars that have not traveled cannot meet the scheme with the least cars, it is necessary to retrieve cars from other warehouses for transportation. Since the scheduling capabilities of different warehouses are different, and the cars that can be dispatched in each time period are also different, the historical data of different warehouses are analyzed to determine the optimal scheduling time period. Finally, the required cars are dispatched within the optimal scheduling time period to realize cargo transportation, which is convenient and fast and meets the needs of the staff.

[0032] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A scheduling method for an automobile logistics supply chain, characterized in that: include: When the goods are put into storage, high-definition camera equipment is used to take pictures of the logistics labels on the cargo boxes to obtain pictures of the logistics information labels; Preprocessing the logistics information label image, wherein the preprocessing is denoising; Analyze and extract text from the denoised logistics information label image to obtain logistics text information data, including the destination information and size information of the goods; Select all cargoes with the same destination information and determine the most optimized truck transportation plan; Determine vehicle dispatch information based on the comparison of the optimized vehicle transportation plan with vehicles that have not yet traveled; Obtain the vehicle dispatch capabilities of several other depots in the region and determine the optimal vehicle dispatch time period; Dispatch vehicles to the depot within the optimized vehicle dispatching time period to deliver and transport cargo logistics.

2. The scheduling method for automobile logistics supply chain according to claim 1, characterized in that: The pre-processing of the logistics information label image specifically includes the following steps: Convert the logistics information label image into a grayscale image, calculate the RGB three-channel difference value, and generate the first noise image through threshold filtering under the grayscale image and three-channel difference value calculation; The logistics information label image is converted into HSV space and processed by Gaussian blur to obtain the second noise image; Merging the first noise image and the second noise image to obtain a merged noise image; Retrieve a pre-set standard h-channel from the database, compare the standard h-channel with the h-channel of the logistics information label image, obtain a comparison result, and linearly fuse the comparison result with the merged noise map to obtain the h-channel correction; Perform s-channel correction on logistics information label images; The rectified h channel and s channel are fused to obtain the denoised image.

3. The scheduling method for automobile logistics supply chain according to claim 2, characterized in that: The analysis of the text in the logistics information label image after denoising specifically includes the following steps: Mark the area of the logistics information label image in rows; The labeled images are combined into a training set and trained through the object detection model until convergence; The segmented image blocks are put into the trained object detection model for object detection of text areas, and the coordinates of the text area in each image block are obtained and output.

4. The scheduling method for automobile logistics supply chain according to claim 3, characterized in that: The extraction of text from the denoised logistics information label image specifically includes the following steps: Based on the coordinates of the complete text area, obtain each complete text area in the logistics information label image; Based on the text content in the logistics information label images, the regional coordinates of the logistics information label images are marked and formed into a training set; Train a hybrid model consisting of CNN and LSTM based on deep learning attention mechanism until convergence; The text area of the segmented image block is put into the trained hybrid model for text recognition to obtain the specific text in the text.

5. The scheduling method for automobile logistics supply chain according to claim 4, characterized in that: The process of selecting all cargoes with the same destination information and determining the optimal truck transportation plan specifically includes the following steps: According to the destination information of each cargo, the cargo boxes with the same destination are selected; Determine the total volume of the transported goods based on the number and size of cargo boxes at the same destination; Get the transport volume of different cars; Calculations are performed based on the transport volumes of different vehicles and the total volume of transported goods to determine a minimum vehicle utilization plan, which is the most optimized vehicle transportation plan.

6. The scheduling method for automobile logistics supply chain according to claim 5, characterized in that: The steps of obtaining the vehicle dispatching capabilities of several other depots in the region and determining the optimal vehicle dispatching time period specifically include the following steps: Extract data from several other warehouse databases to obtain historical dispatch demand data for different logistics stations, and perform fitting calculations on each dispatch demand-time period change curve for other warehouses. Obtain the maximum vehicle dispatching capacity of several other depots; Calculate the scheduling surplus value-time period change curve based on the maximum vehicle scheduling capacity of several other depots and each scheduling demand-time period change curve of the logistics station; Filter out the time periods where all excess values of several other depots are positive and determine them as the optimal scheduling time periods.

7. The scheduling method for automobile logistics supply chain according to claim 6, characterized in that: The expression of the variation curve of the scheduling excess value-time period is: ； Where, is the expression of the change curve of the scheduling excess value-time period, The maximum vehicle supply capacity of the depot. is the total number of dispatchable cars at the depot, is the expression of the scheduling demand-time period change curve of the i-th dispatchable car in the depot.

8. The method for scheduling an automobile logistics supply chain according to claim 7, characterized in that: The method of dispatching vehicles to the depot within the optimized vehicle dispatching time period and delivering the cargo logistics specifically includes the following steps: Several other depots determine the departure time, driving route, and arrival time of the car within the optimized car dispatch time period; Determine the start time of cargo loading based on the arrival time of vehicles dispatched from several other depots; All transport vehicles are loaded and shipped in sequence.

9. A scheduling system for an automobile logistics supply chain, used to implement a scheduling method for an automobile logistics supply chain according to any one of claims 1 to 8, characterized in that: include: A shooting module is used to set a high-definition shooting device to shoot the logistics label on the cargo box when the logistics enters the warehouse, and obtain the logistics information label image; A preprocessing module, which is used to preprocess the logistics information label image, and the preprocessing is a denoising process; A recognition module is used to analyze and extract text from the de-noised logistics information label image to obtain logistics text information data, including the destination information and size information of the goods; A transportation plan determination module is used to select all goods with the same destination information and determine the optimal automobile transportation plan; A vehicle dispatch information determination module, configured to determine vehicle dispatch information based on a comparison between the optimized vehicle transportation plan and vehicles that have not traveled; A vehicle dispatch time period determination module, which is used to obtain the vehicle dispatch capabilities of several other depots in the area and determine the optimal vehicle dispatch time period; The shipping module is used to dispatch cars to the warehouse within the optimized car scheduling time period and to ship and transport the goods.

10. An electronic device comprising at least one processor; and a memory communicatively connected to the at least one processor; characterized in that: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

Images