Arrangement optimization method, device and equipment for container in port storage yard and storage medium
By acquiring container attribute parameters and a target weight calculation model, the optimal location is selected, solving the problem of unreasonable stacking caused by local information in existing technologies, and realizing efficient and optimized arrangement of containers in port yards.
Patent Information
- Application Number
- CN202511210751.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-27
- Publication Date
- 2025-11-28
AI Technical Summary
In existing technologies, the recommendation of container locations in port yards is based on local information, which is difficult to meet the overall expectations of the terminal and leads to unreasonable stacking.
By obtaining the attribute parameters of the containers, candidate locations are determined, and feature weights are calculated using the target weight calculation model to select the optimal location and optimize the container layout.
It achieves the optimization of the most suitable target location based on the global state while meeting the terminal's expectations, thus improving the efficiency and accuracy of container layout.
Smart Images
Figure CN121031893A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of machine learning, in particular to a container arrangement optimization method and device for a port yard, an equipment and a storage medium. BACKGROUND
[0002] With the continuous development of the water transport industry, port transportation has become one of the most mainstream transportation methods, and port transportation mainly involves entering the port from the entrance, berthing at the port, and leaving the port from the exit. In the above process, containers need to be temporarily stacked in the port yard, which is called "yard planning", and determining the best yard for the container is called "allocation". At present, the "yard planning" of the port is usually operated manually, that is, when the container enters the yard from the ship or the vehicle, the operator of the port will allocate a specified yard position for the container, and then the vehicle will transport the container to the specified position for subsequent stacking operation. However, the above method is based on the experience and preset planning of the operator, and it is easy to make mistakes when a large number of containers need to be stacked, and the preset planning only considers the local information of the yard state, so that the yard position recommended for placing the container does not meet the expectations of the port.
[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY
[0004] The main purpose of the present application is to provide a container arrangement optimization method and device for a port yard, an equipment and a storage medium, which aims to solve the technical problem that the yard position recommended by the prior art based on local information does not meet the expectations of the port.
[0005] To achieve the above purpose, the present application provides a container arrangement optimization method for a port yard, which comprises the following steps:
[0006] When receiving the container yard request information, the attribute parameters of the container to be placed are obtained;
[0007] A plurality of candidate yard positions are determined according to the attribute parameters;
[0008] According to the plurality of candidate yard positions and the container to be placed, each vectorization feature is obtained;
[0009] According to the arrangement optimization object, each vectorization feature is calculated by a target weight calculation model to obtain each feature weight;
[0010] According to the feature weight, the target yard position for placing the container to be placed is selected from the plurality of candidate yard positions, so as to realize the optimization of the container arrangement.
[0011] Optionally, the determining a plurality of candidate sites according to the attribute parameter comprises:
[0012] obtaining a type parameter and a height parameter of the container to be placed according to the attribute parameter;
[0013] obtaining a candidate container area of the target wharf;
[0014] filtering the candidate container area according to the type parameter and the height parameter to obtain a target candidate container area;
[0015] obtaining a state of each site according to the target candidate container area;
[0016] determining a plurality of candidate sites according to the state of each site.
[0017] Optionally, the obtaining each vectorized feature according to the plurality of candidate sites and the container to be placed comprises:
[0018] obtaining adjacent sites of the plurality of candidate sites;
[0019] obtaining attribute parameters of adjacent containers already placed according to the adjacent sites;
[0020] obtaining characteristic parameters, transportation parameters and site parameters of the adjacent containers according to the attribute parameters of the adjacent containers;
[0021] performing feature matching between the attribute parameters of the plurality of candidate sites and the characteristic parameters, the transportation parameters and the site parameters of the adjacent containers;
[0022] performing vectorization processing on the features in the matching result to obtain each vectorized feature.
[0023] Optionally, the arrangement optimization object comprises a container turnover rate.
[0024] The calculating each feature weight according to the arrangement optimization object through the target weight calculation model on the plurality of vectorized features comprises:
[0025] obtaining placement records, yard states and wharf operation records of historical containers;
[0026] determining a minimum turnover number of the historical containers according to the placement records, the yard states and the wharf operation records;
[0027] calculating a corresponding container turnover rate according to the minimum turnover number and a total number of movements of the historical containers;
[0028] calculating each feature weight according to the container turnover rate through the target weight calculation model on the plurality of vectorized features.
[0029] Optionally, the arrangement optimization object includes ship waiting time;
[0030] After the placement record of the historical container, the yard state and the terminal operation record are obtained, the following further includes:
[0031] According to the placement record, the yard state and the terminal operation record, the shortest waiting time of the ship transporting the historical container is calculated;
[0032] According to the shortest waiting time, the target weight calculation model is used to calculate the vectorized features, and each feature weight is obtained.
[0033] Optionally, the arrangement optimization object includes terminal scheduling cost;
[0034] After the placement record of the historical container, the yard state and the terminal operation record are obtained, the following further includes:
[0035] According to the placement record, the yard state and the terminal operation record, the lowest personnel operation cost, the lowest vehicle transportation cost and the lowest quay crane working cost of the historical container from entering the terminal to leaving the terminal are calculated;
[0036] The lowest personnel operation cost, the lowest vehicle transportation cost and the lowest quay crane working cost are added to obtain the terminal scheduling cost;
[0037] According to the terminal scheduling cost, the target weight calculation model is used to calculate the vectorized features, and each feature weight is obtained.
[0038] Optionally, the determination of the target site for placing the to-be-placed container from the plurality of candidate sites according to the feature weight to optimize the container arrangement includes:
[0039] The feature weights are sorted according to a target order;
[0040] The top N feature weights are selected from the sorting result;
[0041] According to the top N feature weights, the corresponding top N sites are obtained;
[0042] The top N sites are verified through a target anomaly checking item;
[0043] After the verification is successful, the target site for placing the to-be-placed container is selected from the top N sites to optimize the container arrangement.
[0044] In addition, to achieve the above object, the application further provides a container arrangement optimization device for a port yard, which comprises:
[0045] An acquisition module is configured to acquire attribute parameters of a to-be-placed container when receiving container yard request information;
[0046] A determination module is configured to determine a plurality of candidate sites according to the attribute parameters;
[0047] A matching module is configured to obtain respective vectorized features according to the plurality of candidate sites and the to-be-placed container;
[0048] A calculation module is configured to calculate the respective vectorized features according to a target weight calculation model to obtain respective feature weights;
[0049] An optimization module is configured to determine a target site for placing the to-be-placed container from the plurality of candidate sites according to the respective feature weights, so as to realize arrangement optimization of the container.
[0050] In addition, to achieve the above object, the application further provides a container arrangement optimization device for a port yard, which comprises:
[0051] In addition, to achieve the above object, the application further provides a storage medium, wherein the storage medium stores a container arrangement optimization program for a port yard, and the container arrangement optimization program for a port yard realizes the container arrangement optimization method for a port yard as described above when executed by a processor.
[0052] The port yard container arrangement optimization method provided by the application obtains attribute parameters of a to-be-placed container when receiving a container yard request information, determines a plurality of candidate sites according to the attribute parameters, obtains each vectorized feature according to the plurality of candidate sites and the to-be-placed container, calculates each vectorized feature according to an arrangement optimization object through a target weight calculation model to obtain each feature weight, and determines a target site for placing the to-be-placed container from the plurality of candidate sites according to the each feature weight, so as to realize optimization of container arrangement. In the foregoing manner, each vectorized feature is calculated according to an arrangement optimization object through a target weight calculation model, and then a target site for placing a to-be-placed container is screened out, so as to realize optimization of container arrangement, thereby being capable of optimizing the most suitable target site based on a global state under the premise of meeting the expectation of a wharf. BRIEF DESCRIPTION OF DRAWINGS
[0053] Figure 1 is a structural schematic diagram of a port yard container arrangement optimization device of a hardware running environment related to an embodiment scheme of the application.
[0054] Figure 2 is a flowchart of a first embodiment of a port yard container arrangement optimization method of the application.
[0055] Figure 3 is a flowchart of a second embodiment of a port yard container arrangement optimization method of the application.
[0056] Figure 4 is a flowchart of a third embodiment of a port yard container arrangement optimization method of the application.
[0057] Figure 5 is a functional module schematic diagram of a first embodiment of a port yard container arrangement optimization device of the application.
[0058] The implementation, functional features and advantages of the application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION
[0059] It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.
[0060] Reference Figure 1 , Figure 1 is a structural schematic diagram of a port yard container arrangement optimization device of a hardware running environment related to an embodiment scheme of the application.
[0061] As Figure 1As shown in the figure, the container arrangement optimization device of the port yard can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between the components. The user interface 1003 can include a display screen, an input unit such as a keyboard, and can also include a standard wired interface and a wireless interface. The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 can be a high-speed random access memory (RAM) memory or a stable non-volatile memory (NVM) such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001.
[0062] Those skilled in the art can understand that Figure 1 The structure shown in the figure does not constitute a limitation on the container arrangement optimization device of the port yard, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.
[0063] As Figure 1 As shown, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and a container arrangement optimization program of the port yard.
[0064] In Figure 1 The network interface 1004 of the container arrangement optimization device of the port yard is mainly used for data communication with the network integrated platform workstation; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the container arrangement optimization device of the port yard can be arranged in the container arrangement optimization device of the port yard, and the container arrangement optimization device of the port yard calls the container arrangement optimization program stored in the memory 1005 through the processor 1001, and executes the container arrangement optimization method provided by the embodiment of the application.
[0065] Based on the above hardware structure, the container arrangement optimization method of the port yard is proposed.
[0066] Referring to Figure 2 , Figure 2 is a flowchart of the first embodiment of the container arrangement optimization method of the port yard.
[0067] In the first embodiment, the method for optimizing the arrangement of containers in the port yard comprises the following steps:
[0068] In step S10, when receiving the container yard request information, the attribute parameters of the to-be-placed container are obtained.
[0069] It should be noted that the execution subject of the present embodiment is a container yard arrangement optimization device, and can also be other devices that can achieve the same or similar functions, such as a container arrangement controller, etc. The present embodiment does not limit this, and in the present embodiment, the container arrangement controller is taken as an example for description.
[0070] It should be understood that the container yard request information refers to the information that the port receives a request for yard from the container arrangement controller for a new container transported to the port by a ship or a vehicle. The to-be-placed container refers to the container that needs to be placed in the yard, which is the new container transported by the ship or the vehicle.
[0071] It can be understood that the attribute parameters include the self attribute parameters of the to-be-placed container and the attribute parameters of the pre-processed to-be-placed container, which include the transport destination port, height, weight, etc. When receiving the container yard request information sent by the port, the container arrangement controller can obtain the attribute parameters of the to-be-placed container in real time.
[0072] In step S20, a plurality of candidate yard positions are determined according to the attribute parameters.
[0073] It can be understood that the candidate yard position refers to the yard position that can be used in the process of placing the to-be-placed container. There are multiple candidate yard positions, which are obtained by gradually screening the yard positions of the port according to the attribute parameter information. After the screening is completed, a plurality of candidate yard positions are obtained.
[0074] Further, in step S20, the type parameters and height parameters of the to-be-placed container are obtained according to the attribute parameters; the candidate container area of the target port is obtained; the target candidate container area is obtained by filtering the candidate container area according to the type parameters and height parameters; the state of each yard position is obtained according to the target candidate container area; and the plurality of candidate yard positions are determined according to the state of each yard position.
[0075] It should be understood that the type parameter refers to the type of the goods to be stored in the container, which can be perishable, flammable and explosive, radioactive, and toxic, and the height parameter refers to the distance from the bottom to the top of the container to be placed. The candidate box area refers to an area where the container can be stored, i.e., there is a free space in the candidate box area. The target candidate box area refers to a box area that can store the container to be placed of the type and height.
[0076] It can be understood that after obtaining the type parameter and the height parameter of the container to be placed, the candidate box area is filtered by the type parameter and the height parameter, so that the filtered target candidate box area meets the condition of storing the container to be placed. The state of each site includes an idle state and a non-idle state. The idle state means that the site is not placed with a container, and the non-idle state means that the site has placed a container, so that no other container can be placed. The sites in the target candidate box area are screened by the state of each site. After the screening is completed, a plurality of candidate sites in the idle state are obtained.
[0077] Step S30, obtaining each vectorized feature according to the plurality of candidate sites and the container to be placed.
[0078] It should be understood that each vectorized feature refers to the same feature of the container placed in each site. After obtaining the plurality of candidate sites, the plurality of candidate sites are matched with the container to be placed in terms of features, so that the site for placing the container to be placed has the same or similar attribute parameters as the container placed in the plurality of candidate sites. At this time, the same or similar attribute parameters are each vectorized feature.
[0079] Step S40, calculating each feature weight according to the arrangement optimization object by a target weight calculation model.
[0080] It can be understood that the target weight calculation model refers to a model for calculating the weight corresponding to the vectorized feature. The target weight calculation model is closely related to the arrangement optimization object. When the arrangement optimization object is the terminal scheduling cost, the target weight calculation model is trained by machine learning according to the terminal scheduling cost. Or when the arrangement optimization object is the ship waiting time, the target weight calculation model is trained by machine learning according to the ship waiting time. Or when the arrangement optimization object is the turnover rate, the target weight calculation model is trained by machine learning according to the turnover rate. The target weight calculation model will be updated iteratively according to the weight matrix.
[0081] It should be understood that each feature weight refers to the weight corresponding to each vectorized feature, the range of each feature weight is between 0 and 1, and the weight corresponding to each vectorized feature is calculated by a target weight calculation model, and the similarity between the weight and the attribute parameter between the plurality of candidate sites and the to-be-placed container is positively correlated, that is, the higher the similarity, the higher the matching degree between the plurality of candidate sites and the to-be-placed container, and the greater the calculated weight.
[0082] Step S50, determining a target site for placing the to-be-placed container from the plurality of candidate sites according to the each feature weight, so as to realize optimization of the container arrangement.
[0083] It should be understood that the target site refers to the site corresponding to the maximum feature weight, and after obtaining the target site, the to-be-placed container is placed in the target site, and after the placement is completed, the arrangement of the container is optimal. When the arrangement optimization object is the terminal scheduling cost, the arrangement optimization is reflected in the lowest terminal scheduling cost, when the arrangement optimization object is the ship waiting time, the arrangement optimization is reflected in the shortest waiting time of the ship from entering the terminal to loading the container and leaving the terminal, and when the arrangement optimization object is the turnover rate, the arrangement optimization is reflected in the lowest turnover rate of the container in the yard.
[0084] Further, step S50 includes: sorting the each feature weight according to a target order; selecting the top N feature weights from the sorting result; obtaining the top N sites corresponding to the top N feature weights according to the top N feature weights; verifying the top N sites by a target anomaly checking item; and after the verification is successful, selecting a target site for placing the to-be-placed container from the top N sites, so as to realize optimization of the container arrangement.
[0085] It can be understood that the target order refers to the order of sorting each feature weight, which can be from large to small or from small to large. According to the target order, each feature weight is sorted in turn, and then the top N feature weights with the largest values are selected, and the N can be set to 5 or other values, which is not limited by the embodiment.
[0086] It should be understood that the target anomaly checking item refers to an item that needs to be checked to avoid real-time anomalies. The target anomaly checking item can be an item that needs to be checked by an operator according to actual operation experience, for example, whether the site is damaged, so that the placed container is abnormal, etc. After the verification is successful, the site with the largest feature weight is selected as the target site from the top N sites, and then the to-be-placed container is placed in the target site.
[0087] The embodiment obtains attribute parameters of a to-be-placed container when receiving a container yard request information, determines a plurality of candidate sites according to the attribute parameters, obtains each vectorized feature according to the plurality of candidate sites and the to-be-placed container, calculates each vectorized feature according to a target weight calculation model of an arrangement optimization object to obtain each feature weight, and determines a target site for placing the to-be-placed container from the plurality of candidate sites according to the each feature weight, so as to realize optimization of container arrangement. In the foregoing manner, each vectorized feature is calculated according to a target weight calculation model of an arrangement optimization object, and then a target site for placing a to-be-placed container is screened out, so as to realize optimization of container arrangement, thereby being capable of optimizing the most suitable target site based on a global state under the premise of meeting the expectation of a terminal.
[0088] In an embodiment, as Figure 3 The second embodiment of the container arrangement optimization method of a port yard of the present application is proposed based on the first embodiment, and the step S30 comprises:
[0089] In the step S301, adjacent sites of the plurality of candidate sites are obtained.
[0090] It should be understood that the adjacent sites refer to sites adjacent to the plurality of candidate sites respectively. The positions of the plurality of candidate sites are different, so that the adjacent sites are also different. For example, when the plurality of candidate sites are located in the middle, the adjacent sites are the sites in four directions of the plurality of candidate sites, i.e. up, down, left and right. When the plurality of candidate sites are located in the middle of the lowermost end, the adjacent sites are the sites in three directions of the plurality of candidate sites, i.e. up, left and right. When the plurality of candidate sites are located in the middle of the uppermost end, the adjacent sites are the sites in three directions of the plurality of candidate sites, i.e. down, left and right.
[0091] In the step S302, attribute parameters of adjacent containers already placed in the adjacent sites are obtained according to the adjacent sites.
[0092] It can be understood that the attribute parameters refer to attribute parameters of adjacent containers already placed in the adjacent sites. The attribute parameters of the adjacent containers include weight, destination terminal to be transported to, ship to be transported, etc.
[0093] In the step S303, characteristic parameters, transportation parameters and site parameters of the adjacent containers are obtained according to the attribute parameters of the adjacent containers.
[0094] It should be understood that the characteristic parameter refers to a parameter of a characteristic of the adjacent container placed in the adjacent position of the adjacent position, the characteristic parameter is calibrated when the adjacent container is factory, including type, height, weight and other parameters, the transportation parameter refers to a parameter when the adjacent container is transported by the ship, including ship time, unloading port and other parameters, for example, the unloading port refers to the port of the destination where the adjacent container is transported, that is, the port terminal of the embodiment is only used for the transition placement of the container, for example, the adjacent container needs to be transported from the port terminal to the port A for unloading, at this time, the unloading port is the port A, and the position parameter refers to a parameter of the position where the adjacent container is stored, including the adjacent position layer difference and the number of continuous stacking in the same ship.
[0095] In step S304, the attribute parameters of the plurality of candidate positions are respectively matched with the characteristic parameters, the transportation parameters and the position parameters of the adjacent container.
[0096] It can be understood that after obtaining the characteristic parameters, the transportation parameters and the position parameters of the adjacent container, the attribute parameters of the plurality of candidate positions are respectively matched with the characteristic parameters, the transportation parameters and the position parameters of the adjacent container.
[0097] In step S305, the features in the matching result are vectorized to obtain each vectorized feature.
[0098] It should be understood that each vectorized feature refers to the same feature of the container placed in each position, and after obtaining the matching features in the matching result, the features are vectorized, and after the processing is completed, each vectorized feature is obtained.
[0099] In the embodiment, the adjacent position of the plurality of candidate positions is obtained, the attribute parameters of the placed adjacent container are obtained according to the adjacent position, the characteristic parameters, the transportation parameters and the position parameters of the adjacent container are obtained according to the attribute parameters of the adjacent container, the attribute parameters of the plurality of candidate positions are respectively matched with the characteristic parameters, the transportation parameters and the position parameters of the adjacent container, the features in the matching result are vectorized to obtain each vectorized feature, and in the above manner, the attribute parameters of the placed adjacent container are obtained according to the adjacent position of the plurality of positions, then the attribute parameters of the plurality of candidate positions are respectively matched with the characteristic parameters, the transportation parameters and the position parameters of the adjacent container, and the matching features are vectorized, so that the accuracy of obtaining each vectorized feature can be effectively improved.
[0100] In an embodiment, as Figure 4 The third embodiment of the method for optimizing the arrangement of containers in the port yard is based on the first embodiment, and the step S40 includes:
[0101] In step S401, the placement record of the historical container, the yard state and the terminal operation record are obtained.
[0102] It can be understood that the placement record refers to the record of placing the historical container to the yard at the port terminal, the yard state refers to the state of the yard for placing the container, and the yard state includes the idle state and the non-idle state, and the terminal operation record refers to the record of the operator operating the historical container by the vehicle, the crane and the shore crane.
[0103] Further, after step S401, it further includes: calculating the shortest waiting time of the ship transporting the historical container according to the placement record, the yard state and the terminal operation record; and calculating the respective vectorized features by a target weight calculation model to obtain respective feature weights.
[0104] It should be understood that the shortest waiting time refers to the shortest time for the ship transporting the historical container from the berthing terminal to unloading all containers. First, the respective waiting times of the ship are calculated according to the placement record of the historical container, the yard state and the terminal operation record, and then the shortest waiting time is selected from the respective waiting times. Then, when calculating the respective vectorized features, the target weight calculation model needs to consider the shortest waiting time, that is, the shorter the waiting time, the higher the respective feature weights calculated.
[0105] Further, after step S401, it further includes: calculating the lowest personnel operation cost, the lowest vehicle transportation cost and the lowest shore bridge work cost of the historical container from entering the terminal to leaving the terminal according to the placement record, the yard state and the terminal operation record; adding the lowest personnel operation cost, the lowest vehicle transportation cost and the lowest shore bridge work cost to obtain the terminal scheduling cost; and calculating the respective vectorized features by a target weight calculation model according to the terminal scheduling cost to obtain respective feature weights.
[0106] It can be understood that the lowest personnel operation cost refers to the lowest cost of the operator operating the shore bridge vehicle, the lowest vehicle transportation cost refers to the lowest cost of the truck and the crane transporting the historical container, and the lowest shore bridge cost refers to the lowest cost of the shore bridge moving the historical container. First, the personnel operation cost, the vehicle transportation cost and the shore bridge work cost of each time are calculated according to the placement record of the historical container, the yard state and the terminal operation record, then the costs of the three are added, and then the lowest cost, i.e. the terminal scheduling cost, is selected from the added costs. Finally, when calculating the respective vectorized features, the target weight calculation model needs to consider the terminal scheduling cost, that is, the lower the terminal scheduling cost, the greater the feature weights calculated.
[0107] Step S402, determining the minimum number of times of turning over of the historical container according to the placement record, the yard state and the wharf operation record.
[0108] It should be understood that the minimum number of times of turning over refers to the minimum number of times of turning over of other containers in the process of transporting the historical container, i.e. other containers hinder the movement or use of the historical container. After obtaining the placement record, the yard state and the wharf operation record, first, the yard state in the idle state is selected according to the yard state, then the number set of times of turning over of the historical container is obtained through the placement record and the wharf operation record, and then the minimum number of times in the number set is extracted, i.e. the minimum number of times of turning over of the historical container.
[0109] Step S403, calculating the corresponding turning rate according to the minimum number of times of turning over and the total number of movements of the historical container.
[0110] It can be understood that the turning rate refers to the ratio of the number of times of movement hindering the use of the historical container to the total number of movements. The total number of movements refers to the number of movements of transporting the historical container from the yard to the ship. After obtaining the minimum number of times of turning over, the turning rate is calculated according to the minimum number of times of turning over and the total number of movements of the historical container. For example, the minimum number of times of turning over is m, and the total number of movements is M, then the turning rate = m / M*100%.
[0111] Step S404, calculating each vectorized feature through the target weight calculation model according to the turning rate to obtain each feature weight.
[0112] It should be understood that after obtaining the turning rate, the target weight calculation model considers the turning rate when calculating each vectorized feature, i.e. the lower the turning rate, the higher the weight corresponding to the vectorized feature calculated by the target weight calculation model. Then, the other vectorized features are calculated in a loop until all the vectorized features are calculated to obtain each feature weight.
[0113] It can be understood that the above three conditions, i.e. the turning rate, the minimum waiting time and the wharf scheduling cost, can be combined in pairs, i.e. during the calculation of each vectorized feature through the target weight calculation model, the selected consideration conditions need to be comprehensively referred.
[0114] The embodiment obtains the placement record of a historical container, the yard state and the wharf operation record, determines the minimum number of turns of the historical container according to the placement record, the yard state and the wharf operation record, calculates the corresponding container turning rate according to the minimum number of turns and the total number of movements of the historical container, calculates each feature weight according to the target weight calculation model through the vectorized features, and in the above manner, the minimum number of turns is determined according to the placement record, the yard state and the wharf operation record of the historical container, then the corresponding container turning rate is calculated according to the minimum number of turns and the total number of movements, and each feature weight is calculated according to the target weight calculation model through the container turning rate, thereby effectively improving the accuracy of each feature weight, and the finally screened target yard meets the wharf expectation.
[0115] In addition, the embodiment of the present application also provides a storage medium, wherein the storage medium stores a port yard container arrangement optimization program, and the port yard container arrangement optimization program is executed by a processor to implement the steps of the port yard container arrangement optimization method.
[0116] Since the storage medium adopts all the technical solutions of the above-mentioned embodiments, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be repeated here.
[0117] In addition, with reference to Figure 5 , the embodiment of the present application also provides a port yard container arrangement optimization device, which comprises:
[0118] The acquisition module 10 is configured to acquire attribute parameters of a to-be-placed container when receiving container yard request information.
[0119] The determination module 20 is configured to determine a plurality of candidate sites according to the attribute parameters.
[0120] The matching module 30 is configured to obtain each vectorized feature according to the plurality of candidate sites and the to-be-placed container.
[0121] The calculation module 40 is configured to calculate each feature weight by calculating each vectorized feature through a target weight calculation model according to an arrangement optimization object.
[0122] The optimization module 50 is configured to determine a target site for placing the to-be-placed container from the plurality of candidate sites according to the each feature weight, so as to realize the optimization of container arrangement.
[0123] The embodiment obtains attribute parameters of a to-be-placed container when receiving container yard request information, determines a plurality of candidate sites according to the attribute parameters, obtains each vectorized feature according to the plurality of candidate sites and the to-be-placed container, calculates each vectorized feature according to a target weight calculation model of an arrangement optimization object to obtain each feature weight, and determines a target site for placing the to-be-placed container from the plurality of candidate sites according to the each feature weight, so as to realize optimization of container arrangement. In this way, each vectorized feature is calculated according to a target weight calculation model of an arrangement optimization object, and then a target site for placing a to-be-placed container is selected, so as to realize optimization of container arrangement, thereby being capable of optimizing the most suitable target site based on a global state under the premise of meeting the expectation of a terminal.
[0124] It should be noted that the above-described workflow is merely illustrative and does not limit the protection scope of the present application. In actual application, a person skilled in the art can select part or all of the above-described workflow to achieve the purpose of the embodiment according to actual needs, which is not limited herein.
[0125] In addition, technical details not described in detail in the embodiment can be referred to the port yard container arrangement optimization method provided by any embodiment of the present application, which will not be described herein.
[0126] In an embodiment, the determining module 20 is further configured to obtain a type parameter and a height parameter of the to-be-placed container according to the attribute parameters, obtain a candidate container area of a target terminal, filter the candidate container area according to the type parameter and the height parameter to obtain a target candidate container area, obtain a state of each site according to the target candidate container area, and determine a plurality of candidate sites according to the state of each site.
[0127] In an embodiment, the matching module 30 is further configured to obtain adjacent sites of the plurality of candidate sites, obtain attribute parameters of adjacent containers that have been placed according to the adjacent sites, obtain characteristic parameters, transportation parameters, and site parameters of the adjacent containers according to the attribute parameters of the adjacent containers, perform feature matching on the attribute parameters of the plurality of candidate sites and the characteristic parameters, the transportation parameters, and the site parameters of the adjacent containers, and perform vectorization processing on features in a matching result to obtain each vectorized feature.
[0128] In an embodiment, the computing module 40 is further configured to: when the arrangement optimization object comprises a turnover rate, obtain placement records of historical containers, yard states, and terminal operation records; determine minimum turnover times of the historical containers according to the placement records, the yard states, and the terminal operation records; calculate corresponding turnover rates according to the minimum turnover times and total movement times of the historical containers; and calculate each vectorized feature according to the turnover rates through the target weight calculation model to obtain each feature weight.
[0129] In an embodiment, the computing module 40 is further configured to: when the arrangement optimization object comprises a ship waiting time, calculate minimum waiting times of a ship transporting the historical containers according to the placement records, the yard states, and the terminal operation records; and calculate each vectorized feature according to the minimum waiting times through the target weight calculation model to obtain each feature weight.
[0130] In an embodiment, the computing module 40 is further configured to: when the arrangement optimization object comprises a terminal scheduling cost, calculate minimum personnel operation costs, minimum vehicle transportation costs, and minimum quay crane working costs of the historical containers from entering the terminal to leaving the terminal according to the placement records, the yard states, and the terminal operation records; accumulate the minimum personnel operation costs, the minimum vehicle transportation costs, and the minimum quay crane working costs to obtain the terminal scheduling cost; and calculate each vectorized feature according to the terminal scheduling cost through the target weight calculation model to obtain each feature weight.
[0131] In an embodiment, the optimization module 50 is further configured to: sort the feature weights in a target order; select top N feature weights from the sorting result; obtain corresponding top N positions according to the top N feature weights; check the top N positions through a target anomaly checking item; and after the checking is successful, filter a target position for placing the to-be-placed container from the top N positions to achieve optimization of container arrangement.
[0132] Other embodiments of the port yard container arrangement optimization device of the present application or implementation methods can refer to the above method embodiments, which will not be repeated here.
[0133] Moreover, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of "including" "comprising" or "having" and variations thereof herein is intended to encompass the presence of one or more recited elements or steps and not the exclusion of any other integers or steps. The use of "including", "comprising", "having" and "with" and variations thereof herein is intended to encompass the presence of one or more recited elements or steps and not the exclusion of any other integers or steps.
[0134] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.
[0135] Those skilled in the art can clearly understand the above-mentioned embodiment methods by means of software and the necessary general hardware platform, of course, they can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk), and includes a plurality of instructions for making a terminal device (which can be a mobile phone, a computer, an integrated platform workstation, or a network device, etc.) execute the methods described in the embodiments of the present application.
[0136] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, which is made by using the content of the specification and drawings of the present application, is also included in the patent protection scope of the present application.
Claims
1. A method for optimizing the layout of containers in a port yard, characterized in that, The method for optimizing the layout of containers in the port yard includes the following steps: Upon receiving a container yard request, obtain the attribute parameters of the container to be placed. Multiple candidate sites are determined based on the attribute parameters; Each vectorized feature is obtained based on the multiple candidate sites and the container to be placed. Based on the arrangement optimization object, the target weight calculation model is used to calculate the weight of each vectorized feature to obtain the weight of each feature; Based on the weights of each feature, a target location for placing the container is selected from multiple candidate locations to optimize the container layout.
2. The method for optimizing the layout of containers in a port yard as described in claim 1, characterized in that, The step of determining multiple candidate positions based on the attribute parameters includes: Based on the attribute parameters, the type and height parameters of the container to be placed are obtained; Obtain the candidate container area for the target terminal; The candidate box areas are filtered according to the type parameter and height parameter to obtain the target candidate box areas; The state of each field position is obtained based on the target candidate box area; Multiple candidate positions are determined based on the status of each position.
3. The method for optimizing the layout of containers in a port yard as described in claim 1, characterized in that, The step of obtaining various vectorized features based on the multiple candidate sites and the container to be placed includes: Obtain the adjacent positions of the multiple candidate positions; The attribute parameters of the adjacent containers that have been placed are obtained based on the adjacent locations; Based on the attribute parameters of the adjacent containers, the characteristic parameters, transportation parameters, and yard location parameters of the adjacent containers are obtained; The attribute parameters of the multiple candidate sites are respectively matched with the characteristic parameters, transportation parameters and site parameters of the adjacent containers; The features in the matching results are vectorized to obtain individual vectorized features.
4. The method for optimizing the layout of containers in a port yard as described in claim 1, characterized in that, The optimization targets for the layout include the turnover rate; The step of calculating the weights of each vectorized feature based on the arrangement optimization object using a target weight calculation model includes: Obtain historical container placement records, yard status, and terminal operation records; The minimum number of times the historical container was flipped was determined based on the placement record, the yard status, and the terminal operation record. The corresponding container turnover rate is calculated based on the minimum number of turnovers and the total number of historical container movements. The weights of each feature are calculated based on the turnover rate using the target weight calculation model.
5. The method for optimizing the layout of containers in a port yard as described in any one of claims 1 to 4, characterized in that, The optimization targets include ship waiting time; After obtaining historical container placement records, yard status, and terminal operation records, the process also includes: The shortest waiting time for the vessel transporting the historical containers is calculated based on the placement record, the yard status, and the terminal operation record. The target weight is calculated for each vectorized feature based on the shortest waiting time using the target weight calculation model.
6. The method for optimizing the layout of containers in a port yard as described in any one of claims 1 to 4, characterized in that, The optimization targets include dock scheduling costs; After obtaining historical container placement records, yard status, and terminal operation records, the process also includes: Based on the placement records, the yard status, and the terminal operation records, calculate the lowest personnel operation cost, the lowest vehicle transportation cost, and the lowest quay crane operation cost for the historical containers from entering the terminal to leaving the terminal; The minimum personnel operation cost, the minimum vehicle transportation cost, and the minimum quay crane operation cost are added together to obtain the terminal scheduling cost. Based on the terminal scheduling cost, the target weight calculation model is used to calculate the weights of each vectorized feature.
7. The method for optimizing the layout of containers in a port yard as described in claim 1, characterized in that, The step of determining the target location for placing the container from multiple candidate locations based on the weights of the various features, in order to optimize the container layout, includes: The weights of each feature are sorted according to the target order; Select the top N feature weights from the ranking results; The top N field positions are obtained based on the weights of the top N features; The first N field positions are verified using the target anomaly check items; After successful verification, the target location for placing the container is selected from the first N locations to optimize the container layout.
8. A method and apparatus for optimizing the layout of containers in a port yard, characterized in that, The apparatus for optimizing the layout of containers in the port yard includes: The acquisition module is used to obtain the attribute parameters of the container to be placed when a container yard request information is received; The determination module is used to determine multiple candidate sites based on the attribute parameters; The matching module is used to obtain various vectorized features based on the multiple candidate sites and the container to be placed; The calculation module is used to calculate the weights of each vectorized feature based on the layout optimization object using the target weight calculation model. An optimization module is used to determine, based on the weights of each feature, a target location for placing the container from among multiple candidate locations, so as to optimize the container layout.
9. A method and equipment for optimizing the layout of containers in a port yard, characterized in that, The device for optimizing the layout of containers in a port yard includes: a memory, a processor, and a program for optimizing the layout of containers in a port yard stored in the memory and executable on the processor. The program for optimizing the layout of containers in a port yard is configured to implement the method for optimizing the layout of containers in a port yard as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium stores a method program for optimizing the layout of containers in a port yard. When the method program is executed by the processor, it implements the method for optimizing the layout of containers in a port yard as described in any one of claims 1 to 7.