CN117455324B - Large port operation management method and system based on physical model - Google Patents

Abstract

The invention relates to the technical field of port operation management, in particular to a large port operation management method and system based on a physical model. Acquiring a preset operation model diagram of a port, and separating a preset scene three-dimensional model diagram of a preset position of the port from the preset operation model diagram; comparing the actual scene three-dimensional model diagram with a preset scene three-dimensional model diagram to obtain a scene deviation model diagram; and marking the preset position with the idle use state as a storable area, acquiring order information in the ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship. The intelligent recognition method based on the physical model overcomes the limitation of the traditional method by fusing the computer vision, physical modeling and deep learning technologies, and realizes more accurate, efficient and real-time cargo unloading place recognition.

Description

Large port operation management method and system based on physical model

Technical Field

The invention relates to the technical field of port operation management, in particular to a large port operation management method and system based on a physical model.

Background

Large ports serve as key nodes for global trade and logistics, carrying a large number of cargo transportation and unloading campaigns. In order to improve the operational efficiency of ports, optimize cargo management and enhance security monitoring, automated and intelligent solutions are becoming particularly important. The intelligent management method based on the physical model has great potential in realizing automatic identification of goods unloading places. Traditionally, identification of port cargo discharge sites mainly relies on manual patrol and camera monitoring, although traditional manual patrol or camera monitoring can monitor cargo discharge activities to some extent, real-time and accurate discharge site identification cannot be achieved, port operation processes cannot be accurately predicted, planned and optimized, and therefore port operation efficiency is low, and intelligent management methods based on physical models can play a key role in this respect.

Disclosure of Invention

The invention overcomes the defects of the prior art and provides a large port operation management method and system based on a physical model.

The technical scheme adopted by the invention for achieving the purpose is as follows:

the first aspect of the invention discloses a large port operation management method based on a physical model, which comprises the following steps:

Acquiring actual scene image information of each preset position in a port, and constructing an actual scene three-dimensional model diagram of each preset position in the port according to the actual scene image information;

acquiring a preset operation model diagram of a port, and separating a preset scene three-dimensional model diagram of a preset position of the port from the preset operation model diagram; comparing the actual scene three-dimensional model diagram with a preset scene three-dimensional model diagram to obtain a scene deviation model diagram;

Identifying and judging each preset position in the port according to the scene deviation model diagram so as to identify and judge the use state of each preset position in the port;

and marking the preset position with the idle use state as a storable area, acquiring order information in the ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship.

Further, in a preferred embodiment of the present invention, actual scenario image information of each preset position in a port is obtained, and an actual scenario three-dimensional model diagram of each preset position in the port is constructed according to the actual scenario image information, specifically:

Acquiring actual scene image information of a preset position in a port, and carrying out noise reduction and image enhancement processing on the actual scene image information to obtain processed actual scene image information;

Extracting feature points in the processed actual scene image information through an ORB algorithm to obtain a plurality of feature points; searching a preset reference point from the processed actual scene image information, and constructing a relative coordinate system according to the preset reference point;

Acquiring relative coordinate values of each characteristic point in the relative coordinate system, calculating Manhattan distance between each characteristic point and the preset reference point according to the relative coordinate values, and comparing the Manhattan distance between each characteristic point and the preset reference point with the preset Manhattan distance;

Eliminating characteristic points with Manhattan distance larger than a preset Manhattan distance, and reserving characteristic points with Manhattan distance not larger than the preset Manhattan distance to obtain the characteristic points subjected to outlier screening;

And acquiring the point cloud data of the feature points subjected to the outlier screening, and reconstructing according to the point cloud data of the feature points subjected to the outlier screening to obtain an actual scene three-dimensional model diagram of the preset position in the port.

Further, in a preferred embodiment of the present invention, the actual scenario three-dimensional model map is compared with a preset scenario three-dimensional model map to obtain a scenario deviation model map, which specifically includes:

Retrieving the actual scene three-dimensional model diagram to obtain a first identifier in the actual scene three-dimensional model diagram; searching the preset scene three-dimensional model diagram to obtain a second identifier in the preset scene three-dimensional model diagram;

Constructing a virtual pairing space, importing the actual scene three-dimensional model diagram and a preset scene three-dimensional model diagram into the virtual pairing space, and enabling the first identifier to coincide with the second identifier so as to align the actual scene three-dimensional model diagram and the preset scene three-dimensional model diagram;

And after alignment is completed, eliminating the model area where the actual scene three-dimensional model image and the preset scene three-dimensional model image are overlapped, and storing the model area where the actual scene three-dimensional model image and the preset scene three-dimensional model image are not overlapped to obtain a scene deviation model image.

Further, in a preferred embodiment of the present invention, the identifying and judging are performed on each preset position in the port according to the scene deviation model diagram, so as to identify and judge the use state of each preset position in the port, specifically:

calculating a model volume value of the scene deviation model graph by a gridding method, and comparing the model volume value with a preset model volume value;

if the model volume value is not larger than the preset model volume value, marking the preset position in the port as an idle state;

if the model volume value is larger than a preset model volume value, the scene deviation model diagram is identified, so that whether the object existing at the preset position in the port is a preset object or not is identified according to the scene deviation model diagram;

If the object is not the preset object, marking the preset position in the port as an idle state; if the object is a preset object, the preset position in the port is marked as a non-idle state.

Further, in a preferred embodiment of the present invention, the scene deviation model map is identified, so as to identify whether the object existing at the preset position in the port is a preset object according to the scene deviation model map, specifically:

Constructing a database, acquiring preset model diagrams corresponding to all types of preset objects through a big data network, and importing the preset model diagrams corresponding to all types of preset objects into the database to obtain a pairing database;

Importing the scene deviation model diagram into the pairing database, and calculating the similarity between the scene deviation model diagram and each preset model diagram through a Haoskov distance algorithm to obtain a plurality of similarities;

constructing a sequence table, importing a plurality of similarities into the sequence table for size sorting, and extracting the maximum similarity after sorting is completed; comparing the maximum similarity with a preset similarity;

If the maximum similarity is greater than the preset similarity, indicating that the object at the preset position in the port is a preset object; if the maximum similarity is not greater than the preset similarity, the object existing at the preset position in the port is not the preset object.

Further, in a preferred embodiment of the present invention, a preset location with an idle state is marked as a storable area, order information in a ship hong kong cargo is obtained, and searching and pairing are performed on each storable area according to the order information, so as to obtain a final storage area for storing goods in the port entering cargo ship, which specifically includes:

Acquiring order information in hong kong cargo ships, carrying out feature extraction on the order information to obtain order feature data, and acquiring unloading positions and cargo feature information of cargoes according to the order feature data; calculating storage occupation space information required by storing the goods according to the goods characteristic information; the cargo characteristic information comprises cargo quantity and cargo size parameter information;

marking a preset position with an idle state as a storable region, acquiring storable space information of each storable region, and screening out storable regions with the storable space information smaller than the storage space information to obtain the remaining storable regions;

marking a discharge place and each remaining storable region in the preset operation model diagram, and planning an optimal discharge path between the discharge place and each remaining storable region in the preset operation model diagram based on an ant colony algorithm;

Acquiring size parameter information of unloading equipment, and constructing a three-dimensional model diagram of the unloading equipment according to the size parameter information; constructing and obtaining a cargo three-dimensional model diagram according to cargo size parameter information; separating a three-dimensional model diagram of the unloading path of each optimal unloading path from the preset operation model diagram;

importing the unloading path three-dimensional model diagram, the unloading equipment three-dimensional model diagram and the cargo three-dimensional model diagram into three-dimensional simulation software to perform simulation so as to obtain unloading efficiency of unloading and storing cargoes to each remaining storable area;

And extracting the maximum unloading efficiency, and marking the remaining storable area corresponding to the maximum unloading efficiency as a final storage area.

The second aspect of the present invention discloses a large port operation management system based on a physical model, the large port operation management system includes a memory and a processor, the memory stores a large port operation management method program, when the large port operation management method program is executed by the processor, the following steps are implemented:

Acquiring actual scene image information of each preset position in a port, and constructing an actual scene three-dimensional model diagram of each preset position in the port according to the actual scene image information;

acquiring a preset operation model diagram of a port, and separating a preset scene three-dimensional model diagram of a preset position of the port from the preset operation model diagram; comparing the actual scene three-dimensional model diagram with a preset scene three-dimensional model diagram to obtain a scene deviation model diagram;

Identifying and judging each preset position in the port according to the scene deviation model diagram so as to identify and judge the use state of each preset position in the port;

and marking the preset position with the idle use state as a storable area, acquiring order information in the ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship.

Further, in a preferred embodiment of the present invention, the identifying and judging are performed on each preset position in the port according to the scene deviation model diagram, so as to identify and judge the use state of each preset position in the port, specifically:

calculating a model volume value of the scene deviation model graph by a gridding method, and comparing the model volume value with a preset model volume value;

if the model volume value is not larger than the preset model volume value, marking the preset position in the port as an idle state;

if the model volume value is larger than a preset model volume value, the scene deviation model diagram is identified, so that whether the object existing at the preset position in the port is a preset object or not is identified according to the scene deviation model diagram;

If the object is not the preset object, marking the preset position in the port as an idle state; if the object is a preset object, the preset position in the port is marked as a non-idle state.

Further, in a preferred embodiment of the present invention, the scene deviation model map is identified, so as to identify whether the object existing at the preset position in the port is a preset object according to the scene deviation model map, specifically:

Constructing a database, acquiring preset model diagrams corresponding to all types of preset objects through a big data network, and importing the preset model diagrams corresponding to all types of preset objects into the database to obtain a pairing database;

Importing the scene deviation model diagram into the pairing database, and calculating the similarity between the scene deviation model diagram and each preset model diagram through a Haoskov distance algorithm to obtain a plurality of similarities;

constructing a sequence table, importing a plurality of similarities into the sequence table for size sorting, and extracting the maximum similarity after sorting is completed; comparing the maximum similarity with a preset similarity;

If the maximum similarity is greater than the preset similarity, indicating that the object at the preset position in the port is a preset object; if the maximum similarity is not greater than the preset similarity, the object existing at the preset position in the port is not the preset object.

Further, in a preferred embodiment of the present invention, a preset location with an idle state is marked as a storable area, order information in a ship hong kong cargo is obtained, and searching and pairing are performed on each storable area according to the order information, so as to obtain a final storage area for storing goods in the port entering cargo ship, which specifically includes:

Acquiring order information in hong kong cargo ships, carrying out feature extraction on the order information to obtain order feature data, and acquiring unloading positions and cargo feature information of cargoes according to the order feature data; calculating storage occupation space information required by storing the goods according to the goods characteristic information; the cargo characteristic information comprises cargo quantity and cargo size parameter information;

marking a preset position with an idle state as a storable region, acquiring storable space information of each storable region, and screening out storable regions with the storable space information smaller than the storage space information to obtain the remaining storable regions;

marking a discharge place and each remaining storable region in the preset operation model diagram, and planning an optimal discharge path between the discharge place and each remaining storable region in the preset operation model diagram based on an ant colony algorithm;

Acquiring size parameter information of unloading equipment, and constructing a three-dimensional model diagram of the unloading equipment according to the size parameter information; constructing and obtaining a cargo three-dimensional model diagram according to cargo size parameter information; separating a three-dimensional model diagram of the unloading path of each optimal unloading path from the preset operation model diagram;

importing the unloading path three-dimensional model diagram, the unloading equipment three-dimensional model diagram and the cargo three-dimensional model diagram into three-dimensional simulation software to perform simulation so as to obtain unloading efficiency of unloading and storing cargoes to each remaining storable area;

And extracting the maximum unloading efficiency, and marking the remaining storable area corresponding to the maximum unloading efficiency as a final storage area.

The invention solves the technical defects existing in the background technology, and has the following beneficial effects: the method realizes highly accurate identification of the unloading site of the port cargo by integrating a plurality of technologies, thereby reducing the problems of misjudgment and missed judgment, processing the monitoring image under the almost real-time condition, and adapting to the fast-changing unloading scene; the intelligent recognition method based on the physical model overcomes the limitation of the traditional method by fusing the computer vision, physical modeling and deep learning technologies, and realizes more accurate, efficient and real-time cargo unloading place recognition. The method is not only suitable for a specific port, but also has application potential in other ports or similar environments.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a first method of large port operation management method based on a physical model;

FIG. 2 is a flow chart of a second method of large port operation management method based on a physical model;

FIG. 3 is a third method flow chart of a large port operation management method based on a physical model;

Fig. 4 is a system block diagram of a large port operation management system based on a physical model.

Detailed Description

In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.

As shown in fig. 1, the first aspect of the present invention discloses a large port operation management method based on a physical model, which comprises the following steps:

s102: acquiring actual scene image information of each preset position in a port, and constructing an actual scene three-dimensional model diagram of each preset position in the port according to the actual scene image information;

S104: acquiring a preset operation model diagram of a port, and separating a preset scene three-dimensional model diagram of a preset position of the port from the preset operation model diagram; comparing the actual scene three-dimensional model diagram with a preset scene three-dimensional model diagram to obtain a scene deviation model diagram;

S106: identifying and judging each preset position in the port according to the scene deviation model diagram so as to identify and judge the use state of each preset position in the port;

S108: and marking the preset position with the idle use state as a storable area, acquiring order information in the ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship.

It should be noted that, the preset position is a preset cargo storage position area, and there are a plurality of preset cargo storage position areas in the port, and these preset cargo storage position areas are planned and formulated in advance by engineering personnel. The preset operation model diagram is a three-dimensional state model diagram when the goods are not stored in each preset goods storage position area in the port, and the preset operation model diagram is drawn in advance by engineering personnel through three-dimensional modeling software. The preset scene three-dimensional model diagram is separated from the preset operation model diagram, and is a scene three-dimensional structure diagram when the goods are not stored in the preset position.

The method realizes highly accurate identification of the unloading site of the port cargo by integrating a plurality of technologies, thereby reducing the problems of misjudgment and missed judgment, processing the monitoring image under the almost real-time condition, and adapting to the fast-changing unloading scene; the intelligent recognition method based on the physical model overcomes the limitation of the traditional method by fusing the computer vision, physical modeling and deep learning technologies, and realizes more accurate, efficient and real-time cargo unloading place recognition. The method is not only suitable for a specific port, but also has application potential in other ports or similar environments.

Further, in a preferred embodiment of the present invention, actual scenario image information of each preset position in a port is obtained, and an actual scenario three-dimensional model diagram of each preset position in the port is constructed according to the actual scenario image information, specifically:

Acquiring actual scene image information of a preset position in a port, and carrying out noise reduction and image enhancement processing on the actual scene image information to obtain processed actual scene image information;

Extracting feature points in the processed actual scene image information through an ORB algorithm to obtain a plurality of feature points; searching a preset reference point from the processed actual scene image information, and constructing a relative coordinate system according to the preset reference point;

Acquiring relative coordinate values of each characteristic point in the relative coordinate system, calculating Manhattan distance between each characteristic point and the preset reference point according to the relative coordinate values, and comparing the Manhattan distance between each characteristic point and the preset reference point with the preset Manhattan distance;

Eliminating characteristic points with Manhattan distance larger than a preset Manhattan distance, and reserving characteristic points with Manhattan distance not larger than the preset Manhattan distance to obtain the characteristic points subjected to outlier screening;

And acquiring the point cloud data of the feature points subjected to the outlier screening, and reconstructing according to the point cloud data of the feature points subjected to the outlier screening to obtain an actual scene three-dimensional model diagram of the preset position in the port.

It should be noted that, the actual scene image information of the preset position in the port may be obtained through a camera or an unmanned plane, etc. which are arranged in advance, and the actual scene image information is processed through an image preprocessing technology, so as to obtain the processed actual scene image information; the preset reference point can be a center point of the actual scene image information, and the preset reference point is obtained by calibrating the image after preprocessing. In the process of extracting the feature points through the ORB algorithm, part of the feature points have distortion and drift phenomena, namely noise points, namely outliers, the outliers are needed to be screened out at the moment, so that feature points after outlier screening are obtained, then an actual scene three-dimensional model diagram of a preset position in a port is obtained through reconstruction by means of three-dimensional point cloud reconstruction, the actual scene three-dimensional model diagram can be quickly built through the method, system robustness is improved, the obtained model precision is high, and the pairing precision of a subsequent model can be further improved.

As shown in fig. 2, in a further preferred embodiment of the present invention, the actual scene three-dimensional model map is compared with a preset scene three-dimensional model map to obtain a scene deviation model map, which specifically includes:

S202: retrieving the actual scene three-dimensional model diagram to obtain a first identifier in the actual scene three-dimensional model diagram; searching the preset scene three-dimensional model diagram to obtain a second identifier in the preset scene three-dimensional model diagram;

s204: constructing a virtual pairing space, importing the actual scene three-dimensional model diagram and a preset scene three-dimensional model diagram into the virtual pairing space, and enabling the first identifier to coincide with the second identifier so as to align the actual scene three-dimensional model diagram and the preset scene three-dimensional model diagram;

s206: and after alignment is completed, eliminating the model area where the actual scene three-dimensional model image and the preset scene three-dimensional model image are overlapped, and storing the model area where the actual scene three-dimensional model image and the preset scene three-dimensional model image are not overlapped to obtain a scene deviation model image.

It should be noted that, the markers are arranged in advance in the preset position, that is, in advance in the preset cargo storage position area, the markers may be rods with specific shapes, etc., and the markers are used for geometrically aligning the actual scene three-dimensional model map with the preset scene three-dimensional model map. The virtual pairing space is constructed by three-dimensional software such as SketchUp, rhino, and the virtual pairing space can be in the form of a grid three-dimensional coordinate system. The method can pair the actual scene three-dimensional model diagram with the preset scene three-dimensional model diagram, so as to obtain the scene deviation model diagram.

As shown in fig. 3, in a further preferred embodiment of the present invention, the identification and judgment are performed on each preset position in the port according to the scene deviation model diagram, so as to identify and judge the use state of each preset position in the port, specifically:

S302: calculating a model volume value of the scene deviation model graph by a gridding method, and comparing the model volume value with a preset model volume value;

S304: if the model volume value is not larger than the preset model volume value, marking the preset position in the port as an idle state;

S306: if the model volume value is larger than a preset model volume value, the scene deviation model diagram is identified, so that whether the object existing at the preset position in the port is a preset object or not is identified according to the scene deviation model diagram;

S308: if the object is not the preset object, marking the preset position in the port as an idle state; if the object is a preset object, the preset position in the port is marked as a non-idle state.

The three-dimensional model is converted into a mesh structure by using a mesh method (or discretization method) particularly suitable for the volume value of a model of a complex shape. This can be achieved by dividing the three-dimensional space into small cube elements (voxels). These voxels form a discretized grid covering the geometry of the whole model. For each voxel, its volume is calculated. Since voxels are typically regular cubes, their volume can be calculated by the cube of the side length, and their volumes are added up to get the total volume of the model. If the model volume value is not greater than the preset model volume value, the actual scene three-dimensional model diagram is highly overlapped with the preset scene three-dimensional model diagram, and at the moment, the preset position in the port is marked as an idle state if the preset position in the port is indicated to be not used for storing goods.

If the model volume value is greater than the preset model volume value, it is indicated that the overlap ratio between the actual scene three-dimensional model diagram and the preset scene three-dimensional model diagram is lower, and it is indicated that an object exists at the preset position in the port, and it is further determined whether the object in the preset position is a cargo or not, or only the object that can move at any time, such as a temporary vehicle. The preset objects are stacked goods. If the object is not a preset object (such as a temporary vehicle, etc.), it is indicated that no cargo is stacked at the preset position, and when cargo is required to be stacked at the preset position, only a staff member needs to be informed to move away the temporary vehicle, and the preset position in the port is marked as an idle state. If the object is a preset object, indicating that the goods are already stacked at the preset position, marking the preset position in the port as a non-idle state.

Through the steps, the use state of each cargo storage area in the port can be automatically and real-timely identified.

Further, in a preferred embodiment of the present invention, the scene deviation model map is identified, so as to identify whether the object existing at the preset position in the port is a preset object according to the scene deviation model map, specifically:

Constructing a database, acquiring preset model diagrams corresponding to all types of preset objects through a big data network, and importing the preset model diagrams corresponding to all types of preset objects into the database to obtain a pairing database;

Importing the scene deviation model diagram into the pairing database, and calculating the similarity between the scene deviation model diagram and each preset model diagram through a Haoskov distance algorithm to obtain a plurality of similarities;

constructing a sequence table, importing a plurality of similarities into the sequence table for size sorting, and extracting the maximum similarity after sorting is completed; comparing the maximum similarity with a preset similarity;

If the maximum similarity is greater than the preset similarity, indicating that the object at the preset position in the port is a preset object; if the maximum similarity is not greater than the preset similarity, the object existing at the preset position in the port is not the preset object.

It should be noted that, firstly, a preset model diagram corresponding to each type of preset object is obtained through a big data network, namely, preset model diagrams corresponding to goods with various shapes and sizes are obtained, and then a pairing database is obtained. The hausdorff distance is an index for measuring the similarity between two sets, is widely applied to the fields of computer graphics and computer vision, and comprises similarity comparison of three-dimensional models, wherein the hausdorff distance is used for measuring the degree of shape difference between two models in the comparison of the three-dimensional models. If the maximum similarity is greater than the preset similarity, indicating that the object at the preset position in the port is a preset object; if the maximum similarity is not greater than the preset similarity, the object existing at the preset position in the port is not the preset object.

Further, in a preferred embodiment of the present invention, a preset location with an idle state is marked as a storable area, order information in a ship hong kong cargo is obtained, and searching and pairing are performed on each storable area according to the order information, so as to obtain a final storage area for storing goods in the port entering cargo ship, which specifically includes:

Acquiring order information in hong kong cargo ships, carrying out feature extraction on the order information to obtain order feature data, and acquiring unloading positions and cargo feature information of cargoes according to the order feature data; calculating storage occupation space information required by storing the goods according to the goods characteristic information; the cargo characteristic information comprises cargo quantity and cargo size parameter information;

marking a preset position with an idle state as a storable region, acquiring storable space information of each storable region, and screening out storable regions with the storable space information smaller than the storage space information to obtain the remaining storable regions;

marking a discharge place and each remaining storable region in the preset operation model diagram, and planning an optimal discharge path between the discharge place and each remaining storable region in the preset operation model diagram based on an ant colony algorithm;

Acquiring size parameter information of unloading equipment, and constructing a three-dimensional model diagram of the unloading equipment according to the size parameter information; constructing and obtaining a cargo three-dimensional model diagram according to cargo size parameter information; separating a three-dimensional model diagram of the unloading path of each optimal unloading path from the preset operation model diagram;

importing the unloading path three-dimensional model diagram, the unloading equipment three-dimensional model diagram and the cargo three-dimensional model diagram into three-dimensional simulation software to perform simulation so as to obtain unloading efficiency of unloading and storing cargoes to each remaining storable area;

And extracting the maximum unloading efficiency, and marking the remaining storable area corresponding to the maximum unloading efficiency as a final storage area.

It should be noted that the ant colony algorithm is an optimization algorithm inspired by ant colony foraging behavior, and is used for solving the combination optimization problem. The inspiration of this algorithm comes from the actions of the ant to release pheromones and select paths when looking for food. Ant colony algorithm algorithms have demonstrated their effectiveness in a number of fields, such as graph theory, traveller's questions, scheduling questions, path planning, etc. The optimal discharge path between the discharge location and each remaining storable region can be planned iteratively by means of the ant colony algorithm. And then, the three-dimensional model diagram of the unloading path, the three-dimensional model diagram of the unloading equipment and the three-dimensional model diagram of the goods are imported into three-dimensional simulation software such as SolidWorks and the like to carry out unloading path operation simulation analysis, so that unloading efficiency of unloading the goods to each remaining storable area is obtained, the maximum unloading efficiency is extracted, and the remaining storable area corresponding to the maximum unloading efficiency is marked as a final storage area. The method can automatically plan the most efficient and proper unloading place of the cargoes in each port entering cargo ship.

In addition, the large port operation management method based on the physical model further comprises the following steps:

Acquiring preset video frame information of the preset type equipment when performing various behaviors through a big data network, constructing an identification model based on a deep learning network, and importing the preset video frame information of the preset type equipment when performing various behaviors into the identification model for training to obtain a trained identification model;

Constructing a search tag, and searching the preset operation model diagram based on the search tag so as to search the position node of the preset type equipment in the port;

acquiring real-time video frame image information of a preset type of equipment in the position node in a preset time period;

Importing the real-time video frame image information into the trained recognition model to compare the real-time video frame image information with each preset video frame information so as to obtain a plurality of similarities;

Constructing a sorting table, importing a plurality of the similarities into the sorting table for size sorting, extracting the maximum similarity after sorting is completed, and acquiring preset video frame information corresponding to the maximum similarity; and determining the behavior information of the preset type equipment of the position node in the port according to the preset video frame information corresponding to the maximum similarity, and updating the behavior information of the preset type equipment into a preset operation model diagram to obtain a port real-time operation dynamic model diagram.

The preset type of equipment includes lifting equipment, stacking equipment, loading and unloading equipment, communication equipment, energy equipment and the like. The method can monitor the real-time working types of all the equipment in the port in real time, such as loading state or unloading state of the loading and unloading equipment, so as to obtain a port real-time operation dynamic model diagram, collect and visualize the operation state of the port, analyze the operation state of the port more easily, quickly know the operation state and mechanism of the port, help a manager to plan resource allocation better, find the optimal operation strategy, reduce operation time and resource waste, and improve the overall efficiency.

In addition, the large port operation management method based on the physical model further comprises the following steps:

acquiring historical operation parameters of the preset type equipment when performing various behaviors, constructing a knowledge graph, and importing the historical operation parameters of the preset type equipment when performing various behaviors into the knowledge graph;

Acquiring real-time behavior information of a preset type of equipment in the port real-time operation dynamic model diagram, and importing the real-time behavior information into the knowledge graph to obtain preset operation parameters of the preset type of equipment when performing real-time behavior; constructing a preset operation parameter response chart based on the preset operation parameters;

Acquiring real-time operation parameters of a preset type of equipment; constructing a real-time operation parameter response diagram based on the real-time operation parameters;

Constructing a two-dimensional coordinate system, importing the preset operation parameter response diagram and the real-time operation parameter response diagram into the two-dimensional coordinate system for registration, calculating to obtain the coincidence ratio of the preset operation parameter response diagram and the real-time operation parameter response diagram after registration is completed, and comparing the coincidence ratio with the preset coincidence ratio;

And if the contact ratio is greater than the preset contact ratio, marking the equipment of the preset type as fault equipment.

It should be noted that, the overlap ratio is obtained by calculating the length of the overlapping area of the line segment and the length of the non-overlapping area of the line segment between the preset operation parameter response diagram and the real-time operation parameter response diagram. By comparing the real-time operation parameters of the preset type equipment with the preset operation parameters, whether the preset type equipment fails or not is judged rapidly, the function of self-checking the equipment failure in the port is realized, manual monitoring is not needed, and the port operation efficiency is improved.

In addition, the large port operation management method based on the physical model further comprises the following steps:

acquiring order information of corresponding goods in a final storage area, and extracting the goods name information of the goods according to the order information;

Retrieving through a big data network according to the article name information to obtain related facility equipment which can generate a hazard relationship with the goods in the final storage area;

Searching the preset operation model diagram, and judging whether related facility equipment exists in a preset range of a final storage area or not;

If the goods exist, the position of the goods in the final storage area is adjusted, and an adjustment result is generated.

It should be noted that, the hazard relationship is that the cargo and the equipment in the port may react, for example, dangerous articles such as chemicals, gases, explosives and the like are stored in the final storage area, and if relevant facility equipment such as welding and cutting equipment and the like are present in the final storage area, it is indicated that the final storage area is not suitable for storing the dangerous articles, and the storage position needs to be adjusted. The method can effectively improve the safety of the goods during storage and effectively avoid safety accidents such as storage explosion.

As shown in fig. 4, the second aspect of the present invention discloses a large port operation management system based on a physical model, the large port operation management system includes a memory 15 and a processor 16, the memory 5 stores a large port operation management method program, and when the large port operation management method program is executed by the processor 16, the following steps are implemented:

Acquiring actual scene image information of each preset position in a port, and constructing an actual scene three-dimensional model diagram of each preset position in the port according to the actual scene image information;

acquiring a preset operation model diagram of a port, and separating a preset scene three-dimensional model diagram of a preset position of the port from the preset operation model diagram; comparing the actual scene three-dimensional model diagram with a preset scene three-dimensional model diagram to obtain a scene deviation model diagram;

Identifying and judging each preset position in the port according to the scene deviation model diagram so as to identify and judge the use state of each preset position in the port;

and marking the preset position with the idle use state as a storable area, acquiring order information in the ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship.

Further, in a preferred embodiment of the present invention, the identifying and judging are performed on each preset position in the port according to the scene deviation model diagram, so as to identify and judge the use state of each preset position in the port, specifically:

calculating a model volume value of the scene deviation model graph by a gridding method, and comparing the model volume value with a preset model volume value;

if the model volume value is not larger than the preset model volume value, marking the preset position in the port as an idle state;

if the model volume value is larger than a preset model volume value, the scene deviation model diagram is identified, so that whether the object existing at the preset position in the port is a preset object or not is identified according to the scene deviation model diagram;

If the object is not the preset object, marking the preset position in the port as an idle state; if the object is a preset object, the preset position in the port is marked as a non-idle state.

Further, in a preferred embodiment of the present invention, the scene deviation model map is identified, so as to identify whether the object existing at the preset position in the port is a preset object according to the scene deviation model map, specifically:

Constructing a database, acquiring preset model diagrams corresponding to all types of preset objects through a big data network, and importing the preset model diagrams corresponding to all types of preset objects into the database to obtain a pairing database;

Importing the scene deviation model diagram into the pairing database, and calculating the similarity between the scene deviation model diagram and each preset model diagram through a Haoskov distance algorithm to obtain a plurality of similarities;

constructing a sequence table, importing a plurality of similarities into the sequence table for size sorting, and extracting the maximum similarity after sorting is completed; comparing the maximum similarity with a preset similarity;

If the maximum similarity is greater than the preset similarity, indicating that the object at the preset position in the port is a preset object; if the maximum similarity is not greater than the preset similarity, the object existing at the preset position in the port is not the preset object.

Further, in a preferred embodiment of the present invention, a preset location with an idle state is marked as a storable area, order information in a ship hong kong cargo is obtained, and searching and pairing are performed on each storable area according to the order information, so as to obtain a final storage area for storing goods in the port entering cargo ship, which specifically includes:

Acquiring order information in hong kong cargo ships, carrying out feature extraction on the order information to obtain order feature data, and acquiring unloading positions and cargo feature information of cargoes according to the order feature data; calculating storage occupation space information required by storing the goods according to the goods characteristic information; the cargo characteristic information comprises cargo quantity and cargo size parameter information;

marking a preset position with an idle state as a storable region, acquiring storable space information of each storable region, and screening out storable regions with the storable space information smaller than the storage space information to obtain the remaining storable regions;

marking a discharge place and each remaining storable region in the preset operation model diagram, and planning an optimal discharge path between the discharge place and each remaining storable region in the preset operation model diagram based on an ant colony algorithm;

Acquiring size parameter information of unloading equipment, and constructing a three-dimensional model diagram of the unloading equipment according to the size parameter information; constructing and obtaining a cargo three-dimensional model diagram according to cargo size parameter information; separating a three-dimensional model diagram of the unloading path of each optimal unloading path from the preset operation model diagram;

importing the unloading path three-dimensional model diagram, the unloading equipment three-dimensional model diagram and the cargo three-dimensional model diagram into three-dimensional simulation software to perform simulation so as to obtain unloading efficiency of unloading and storing cargoes to each remaining storable area;

And extracting the maximum unloading efficiency, and marking the remaining storable area corresponding to the maximum unloading efficiency as a final storage area.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.

Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.

The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims (4)

1. The large port operation management method based on the physical model is characterized by comprising the following steps of:

Acquiring actual scene image information of each preset position in a port, and constructing an actual scene three-dimensional model diagram of each preset position in the port according to the actual scene image information;

acquiring a preset operation model diagram of a port, and separating a preset scene three-dimensional model diagram of a preset position of the port from the preset operation model diagram; comparing the actual scene three-dimensional model diagram with a preset scene three-dimensional model diagram to obtain a scene deviation model diagram;

Identifying and judging each preset position in the port according to the scene deviation model diagram so as to identify and judge the use state of each preset position in the port;

Marking a preset position with an idle state as a storable area, acquiring order information in the ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship;

The method comprises the steps of identifying and judging each preset position in a port according to the scene deviation model diagram to identify and judge the use state of each preset position in the port, wherein the specific steps are as follows:

calculating a model volume value of the scene deviation model graph by a gridding method, and comparing the model volume value with a preset model volume value;

if the model volume value is not larger than the preset model volume value, marking the preset position in the port as an idle state;

if the model volume value is larger than a preset model volume value, the scene deviation model diagram is identified, so that whether the object existing at the preset position in the port is a preset object or not is identified according to the scene deviation model diagram;

if the object is not the preset object, marking the preset position in the port as an idle state; if the object is a preset object, marking the preset position in the port as a non-idle state;

The scene deviation model diagram is identified, so as to identify whether an object existing at the preset position in the port is a preset object according to the scene deviation model diagram, specifically:

Constructing a database, acquiring preset model diagrams corresponding to all types of preset objects through a big data network, and importing the preset model diagrams corresponding to all types of preset objects into the database to obtain a pairing database;

Importing the scene deviation model diagram into the pairing database, and calculating the similarity between the scene deviation model diagram and each preset model diagram through a Haoskov distance algorithm to obtain a plurality of similarities;

constructing a sequence table, importing a plurality of similarities into the sequence table for size sorting, and extracting the maximum similarity after sorting is completed; comparing the maximum similarity with a preset similarity;

if the maximum similarity is greater than the preset similarity, indicating that the object at the preset position in the port is a preset object; if the maximum similarity is not greater than the preset similarity, indicating that the object at the preset position in the port is not the preset object;

The method comprises the steps of marking a preset position with an idle state as a storable area, acquiring order information in a ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship, wherein the specific steps are as follows:

Acquiring order information in hong kong cargo ships, carrying out feature extraction on the order information to obtain order feature data, and acquiring unloading positions and cargo feature information of cargoes according to the order feature data; calculating storage occupation space information required by storing the goods according to the goods characteristic information; the cargo characteristic information comprises cargo quantity and cargo size parameter information;

marking a preset position with an idle state as a storable region, acquiring storable space information of each storable region, and screening out storable regions with the storable space information smaller than the storage space information to obtain the remaining storable regions;

marking a discharge place and each remaining storable region in the preset operation model diagram, and planning an optimal discharge path between the discharge place and each remaining storable region in the preset operation model diagram based on an ant colony algorithm;

Acquiring size parameter information of unloading equipment, and constructing a three-dimensional model diagram of the unloading equipment according to the size parameter information; constructing and obtaining a cargo three-dimensional model diagram according to cargo size parameter information; separating a three-dimensional model diagram of the unloading path of each optimal unloading path from the preset operation model diagram;

importing the unloading path three-dimensional model diagram, the unloading equipment three-dimensional model diagram and the cargo three-dimensional model diagram into three-dimensional simulation software to perform simulation so as to obtain unloading efficiency of unloading and storing cargoes to each remaining storable area;

And extracting the maximum unloading efficiency, and marking the remaining storable area corresponding to the maximum unloading efficiency as a final storage area.

2. The large-scale port operation management method based on the physical model according to claim 1, wherein the actual scenario image information of each preset position in the port is obtained, and an actual scenario three-dimensional model diagram of each preset position in the port is constructed according to the actual scenario image information, specifically:

Acquiring actual scene image information of a preset position in a port, and carrying out noise reduction and image enhancement processing on the actual scene image information to obtain processed actual scene image information;

Extracting feature points in the processed actual scene image information through an ORB algorithm to obtain a plurality of feature points; searching a preset reference point from the processed actual scene image information, and constructing a relative coordinate system according to the preset reference point;

Acquiring relative coordinate values of each characteristic point in the relative coordinate system, calculating Manhattan distance between each characteristic point and the preset reference point according to the relative coordinate values, and comparing the Manhattan distance between each characteristic point and the preset reference point with the preset Manhattan distance;

Eliminating characteristic points with Manhattan distance larger than a preset Manhattan distance, and reserving characteristic points with Manhattan distance not larger than the preset Manhattan distance to obtain the characteristic points subjected to outlier screening;

And acquiring the point cloud data of the feature points subjected to the outlier screening, and reconstructing according to the point cloud data of the feature points subjected to the outlier screening to obtain an actual scene three-dimensional model diagram of the preset position in the port.

3. The large port operation management method based on the physical model according to claim 1, wherein the actual scenario three-dimensional model diagram is compared with a preset scenario three-dimensional model diagram to obtain a scenario deviation model diagram, specifically:

Retrieving the actual scene three-dimensional model diagram to obtain a first identifier in the actual scene three-dimensional model diagram; searching the preset scene three-dimensional model diagram to obtain a second identifier in the preset scene three-dimensional model diagram;

Constructing a virtual pairing space, importing the actual scene three-dimensional model diagram and a preset scene three-dimensional model diagram into the virtual pairing space, and enabling the first identifier to coincide with the second identifier so as to align the actual scene three-dimensional model diagram and the preset scene three-dimensional model diagram;

And after alignment is completed, eliminating the model area where the actual scene three-dimensional model image and the preset scene three-dimensional model image are overlapped, and storing the model area where the actual scene three-dimensional model image and the preset scene three-dimensional model image are not overlapped to obtain a scene deviation model image.

4. The large-scale port operation management system based on the physical model is characterized by comprising a memory and a processor, wherein the memory stores a large-scale port operation management method program, and when the large-scale port operation management method program is executed by the processor, the following steps are realized:

Acquiring actual scene image information of each preset position in a port, and constructing an actual scene three-dimensional model diagram of each preset position in the port according to the actual scene image information;

acquiring a preset operation model diagram of a port, and separating a preset scene three-dimensional model diagram of a preset position of the port from the preset operation model diagram; comparing the actual scene three-dimensional model diagram with a preset scene three-dimensional model diagram to obtain a scene deviation model diagram;

Identifying and judging each preset position in the port according to the scene deviation model diagram so as to identify and judge the use state of each preset position in the port;

Marking a preset position with an idle state as a storable area, acquiring order information in the ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship;

The method comprises the steps of identifying and judging each preset position in a port according to the scene deviation model diagram to identify and judge the use state of each preset position in the port, wherein the specific steps are as follows:

calculating a model volume value of the scene deviation model graph by a gridding method, and comparing the model volume value with a preset model volume value;

if the model volume value is not larger than the preset model volume value, marking the preset position in the port as an idle state;

if the model volume value is larger than a preset model volume value, the scene deviation model diagram is identified, so that whether the object existing at the preset position in the port is a preset object or not is identified according to the scene deviation model diagram;

if the object is not the preset object, marking the preset position in the port as an idle state; if the object is a preset object, marking the preset position in the port as a non-idle state;

The scene deviation model diagram is identified, so as to identify whether an object existing at the preset position in the port is a preset object according to the scene deviation model diagram, specifically:

Constructing a database, acquiring preset model diagrams corresponding to all types of preset objects through a big data network, and importing the preset model diagrams corresponding to all types of preset objects into the database to obtain a pairing database;

Importing the scene deviation model diagram into the pairing database, and calculating the similarity between the scene deviation model diagram and each preset model diagram through a Haoskov distance algorithm to obtain a plurality of similarities;

constructing a sequence table, importing a plurality of similarities into the sequence table for size sorting, and extracting the maximum similarity after sorting is completed; comparing the maximum similarity with a preset similarity;

if the maximum similarity is greater than the preset similarity, indicating that the object at the preset position in the port is a preset object; if the maximum similarity is not greater than the preset similarity, indicating that the object at the preset position in the port is not the preset object;

The method comprises the steps of marking a preset position with an idle state as a storable area, acquiring order information in a ship hong kong cargo, and searching and pairing the storable areas according to the order information to obtain a final storage area for storing goods in the port entering cargo ship, wherein the specific steps are as follows:

Acquiring order information in hong kong cargo ships, carrying out feature extraction on the order information to obtain order feature data, and acquiring unloading positions and cargo feature information of cargoes according to the order feature data; calculating storage occupation space information required by storing the goods according to the goods characteristic information; the cargo characteristic information comprises cargo quantity and cargo size parameter information;

marking a preset position with an idle state as a storable region, acquiring storable space information of each storable region, and screening out storable regions with the storable space information smaller than the storage space information to obtain the remaining storable regions;

marking a discharge place and each remaining storable region in the preset operation model diagram, and planning an optimal discharge path between the discharge place and each remaining storable region in the preset operation model diagram based on an ant colony algorithm;

Acquiring size parameter information of unloading equipment, and constructing a three-dimensional model diagram of the unloading equipment according to the size parameter information; constructing and obtaining a cargo three-dimensional model diagram according to cargo size parameter information; separating a three-dimensional model diagram of the unloading path of each optimal unloading path from the preset operation model diagram;

importing the unloading path three-dimensional model diagram, the unloading equipment three-dimensional model diagram and the cargo three-dimensional model diagram into three-dimensional simulation software to perform simulation so as to obtain unloading efficiency of unloading and storing cargoes to each remaining storable area;

And extracting the maximum unloading efficiency, and marking the remaining storable area corresponding to the maximum unloading efficiency as a final storage area.