CN115730156B - Matching system and method for new track smelling of ship - Google Patents
Matching system and method for new track smelling of ship Download PDFInfo
- Publication number
- CN115730156B CN115730156B CN202211504875.6A CN202211504875A CN115730156B CN 115730156 B CN115730156 B CN 115730156B CN 202211504875 A CN202211504875 A CN 202211504875A CN 115730156 B CN115730156 B CN 115730156B
- Authority
- CN
- China
- Prior art keywords
- ship
- track
- news
- event
- matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention discloses a matching method and a device for new smelling tracks of ships, wherein the method comprises the following steps: monitoring a ship news website and loading ship news data; the ship news data comprise corresponding water mobile communication service identification codes; analyzing the ship news data to obtain analysis event information of the ship news data; encoding the ship news data analysis event information to obtain ship news data analysis event encoding information; processing the location information and the time information in the ship news data analysis event coding information to obtain a ship news event track; and matching the ship news event track with the known ship position data track in the ship library, and storing the ship news data analysis event coding information and the corresponding water mobile communication service identification code into the ship library if the ship news event track is matched with the known ship position data track in the ship library. The method has higher matching efficiency from the ship news to the track, can greatly liberate manpower and improves the matching accuracy.
Description
Technical Field
The invention relates to the technical field of matching of ship news to tracks, in particular to a system and a method for matching ship news to tracks.
Background
Through the automatic ship identification system (Automatic Identification System, AIS), marine ship track information can be obtained in real time, in order to further monitor the ship dynamics in real time, events in ship news are required to be matched with actual ships, which has great significance for grasping the ship dynamic information in real time, and currently, the matching is performed in a manual mode, so that the scheme needs to consume a great deal of manpower, time and energy when facing a plurality of ships and news thereof, and errors or omission easily occur. Therefore, a method for matching the news of the ship to the track needs to be studied to realize quick and accurate matching, and the application is proposed in view of the fact.
Disclosure of Invention
The invention aims to solve the technical problem of providing a matching system and a matching method for new smelling tracks of ships, which can monitor ship news websites and download ship news data; the ship news data comprise corresponding water mobile communication service identification codes; analyzing the ship news data to obtain analysis event information of the ship news data; encoding the ship news data analysis event information to obtain ship news data analysis event encoding information; processing the location information and the time information in the ship news data analysis event coding information to obtain a ship news event track; and matching the ship news event track with the known ship position data track in the ship library, and storing the ship news data analysis event coding information and the corresponding water mobile communication service identification code into the ship library if the ship news event track is matched with the known ship position data track in the ship library.
In order to solve the technical problems, a first aspect of the embodiment of the invention discloses a matching method for newly smelling tracks of a ship, which comprises the following steps:
s1, monitoring a ship news website and loading ship news data; the ship news data comprise corresponding water mobile communication service identification codes;
s2, analyzing the ship news data to obtain ship news data analysis event information;
s3, encoding the ship news data analysis event information to obtain ship news data analysis event encoding information;
s4, processing the location information and the time information in the ship news data analysis event coding information to obtain a ship news event track;
and S5, matching the ship news event track with the known ship position data track in the ship library, and storing the ship news data analysis event coding information and the corresponding water mobile communication service identification code into the ship library if the ship news event track is matched with the known ship position data track in the ship library.
In a first aspect of the embodiment of the present invention, the analyzing the ship news data to obtain analysis event information of the ship news data includes:
s21, carrying out grammar analysis on the ship news data to obtain a grammar tree;
s22, carrying out syntactic analysis on the grammar tree to obtain analysis event information of the ship news data; the ship news data analysis event information comprises ship news data dependency relations, event roles, event attributes and named entities.
In a first aspect of the embodiment of the present invention, the processing the location information and the time information in the analysis event coding information of the ship news data to obtain a ship news event track includes:
s41, performing reverse geocoding on the location information in the ship news data analysis event coding information to obtain longitude and latitude position information and structured geographic position information;
s42, processing the longitude and latitude position information, the structured geographic position information and the time information to obtain a ship news event track.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the matching the ship news event track with a known ship position data track includes:
s51, processing the ship news event track and the known ship position data track to obtain a unit length area;
and S52, comparing the unit length area with a preset unit length area threshold, and if the unit length area threshold is smaller than the preset unit length area threshold, matching the ship news event track with the known ship position data track.
In a first aspect of the embodiment of the present invention, the processing the ship news event track and the known ship position data track to obtain an area per unit length includes:
s511, processing the ship news event track and the known ship position data track by using an inter-track area calculation model to obtain two inter-track areas;
s512, processing the ship news event track and the known ship position data track to obtain a length average value of the two tracks;
s513, processing the area between the two tracks and the average value of the lengths of the two tracks to obtain the area per unit length.
In a first aspect of the present invention, the processing the ship news event track and the known ship position data track to obtain two inter-track areas by using an inter-track area calculation model includes:
processing discrete points forming a ship news event track and the known ship position data track to form a plurality of continuous non-overlapping triangles between the two tracks;
and calculating the sum of areas of the continuous non-overlapping triangles, wherein the sum of areas is the area between two tracks.
The second aspect of the embodiment of the invention discloses a matching device for newly smelling tracks of a ship, which comprises the following components:
the news data downloading module is used for monitoring the ship news website and loading the ship news data; the ship news data comprise corresponding water mobile communication service identification codes;
the event information analysis module is used for analyzing the ship news data to obtain ship news data analysis event information;
the event information coding module is used for coding the ship news data analysis event information to obtain ship news data analysis event coding information;
the event track generation module is used for processing the location information and the time information in the ship news data analysis event coding information to obtain a ship news event track;
and the track matching and inputting module is used for matching the ship news event track with the known ship position data track in the ship library, and if the ship news event track is matched with the known ship position data track, the ship news data analysis event coding information and the corresponding water mobile communication service identification code are stored in the ship library.
In a second aspect of the embodiment of the present invention, the analyzing the ship news data to obtain analysis event information of the ship news data includes:
s21, carrying out grammar analysis on the ship news data to obtain a grammar tree;
s22, carrying out syntactic analysis on the grammar tree to obtain analysis event information of the ship news data; the ship news data analysis event information comprises ship news data dependency relations, event roles, event attributes and named entities.
In a second aspect of the embodiment of the present invention, the processing the location information and the time information in the analysis event coding information of the ship news data to obtain a ship news event track includes:
s41, performing reverse geocoding on the location information in the ship news data analysis event coding information to obtain longitude and latitude position information and structured geographic position information;
s42, processing the longitude and latitude position information, the structured geographic position information and the time information to obtain a ship news event track.
In a second aspect of the present invention, the matching the ship news event track with a known ship position data track includes:
s51, processing the ship news event track and the known ship position data track to obtain a unit length area;
and S52, comparing the unit length area with a preset unit length area threshold, and if the unit length area threshold is smaller than the preset unit length area threshold, matching the ship news event track with the known ship position data track.
In a second aspect of the present invention, the processing the ship news event track and the known ship position data track to obtain an area per unit length includes:
s511, processing the ship news event track and the known ship position data track by using an inter-track area calculation model to obtain two inter-track areas;
s512, processing the ship news event track and the known ship position data track to obtain a length average value of the two tracks;
s513, processing the area between the two tracks and the average value of the lengths of the two tracks to obtain the area per unit length.
In a second aspect of the present invention, the processing the ship news event track and the known ship position data track to obtain two inter-track areas by using an inter-track area calculation model includes:
processing discrete points forming a ship news event track and the known ship position data track to form a plurality of continuous non-overlapping triangles between the two tracks;
and calculating the sum of areas of the continuous non-overlapping triangles, wherein the sum of areas is the area between two tracks.
The third aspect of the invention discloses another matching device for newly smelling tracks of a ship, which comprises:
a memory storing executable program code;
a processor coupled to the memory;
the processor calls the executable program codes stored in the memory to execute part or all of the steps in the matching method of the new smelling track of the ship disclosed by the first aspect of the embodiment of the invention.
A fourth aspect of the present invention discloses a computer storage medium, where computer instructions are stored, where the computer instructions are used to execute part or all of the steps in the matching method of newly smelling a track by a ship disclosed in the first aspect of the present invention when the computer instructions are called.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
according to the embodiment of the invention, the matching of the ship news event and the actual ship is realized through matching the track, the matching can be realized in a programming mode, the method is used for processing the ship news data in batches through Spark-based packaging, analyzing event information in the ship news data, carrying out event coding, further generating the event track based on the place and time in the event coding, and inputting the event code and a corresponding on-water mobile communication service identification code (MMSI code) into a ship library when the ship position (AIS) track of the ship is matched with the event track, so that the matching efficiency from the ship news to the track is high, labor can be greatly liberated, and the matching accuracy is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for matching news to tracks of a ship, which is disclosed by the embodiment of the invention;
FIG. 2 is a schematic flow diagram of a device for matching news to tracks of a ship according to an embodiment of the present invention;
fig. 3 is a schematic flow diagram of another device for matching news to tracks of a ship according to an embodiment of the present invention.
Detailed Description
In order to make the present invention better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or elements but may, in the alternative, include other steps or elements not expressly listed or inherent to such process, method, article, or device.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses a matching system and a matching method for new smelling tracks of ships, which can acquire ship news data through a news data downloading module; the event information analysis module is communicated with the news data downloading module and the event information encoding module to generate ship news data analysis event information; the event information coding module is communicated with the event track generating module and the track matching input module to generate ship news data analysis event coding information; the event track generation module is communicated with the event information encoding module to generate a ship news event track; the track matching and inputting module is used for communicating with the event track generating module, matching the ship news event track with the known ship position data track in the ship library, and storing the ship news data analysis event coding information and the corresponding water mobile communication service identification code into the ship library if the ship news event track is matched with the known ship position data track.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a method for matching news to tracks of a ship according to an embodiment of the present invention. The matching method of the new track of the ship described in fig. 1 is applied to the technical field of matching of news of the ship to the track, such as judging the type of the ship, positioning and tracking the ship, and the embodiment of the invention is not limited. As shown in fig. 1, the matching method of the new smelling track of the ship may include the following operations:
s1, monitoring a ship news website and loading ship news data; the ship news data comprise corresponding water mobile communication service identification codes;
the optional ship news data also comprises information such as ship names, places, time, events and the like;
s2, analyzing the ship news data to obtain ship news data analysis event information;
s3, encoding the ship news data analysis event information to obtain ship news data analysis event encoding information;
alternatively, the coding may be performed with reference to the coding system camel; CAMEO (Conflict and Mediation Event Observations) is a coding framework for analyzing conflict and reconciliation events in politics areas worldwide. Referring to a CAMEO coding system, event information is analyzed for ship news data to be coded, the ship news data is divided into a plurality of major classes and a plurality of minor classes, each class uses hierarchical coding identification, and each class contains detailed explanation and related examples of the class.
S4, processing the location information and the time information in the ship news data analysis event coding information to obtain a ship news event track;
and S5, matching the ship news event track with the known ship position data track in the ship library, and storing the ship news data analysis event coding information and the corresponding water mobile communication service identification code into the ship library if the ship news event track is matched with the known ship position data track in the ship library.
Optionally, the analyzing the ship news data to obtain analysis event information of the ship news data includes:
s21, carrying out grammar analysis on the ship news data to obtain a grammar tree;
s22, carrying out syntactic analysis on the grammar tree to obtain analysis event information of the ship news data; the ship news data analysis event information comprises ship news data dependency relations, event roles, event attributes and named entities.
Alternatively, the parsing may be performed with reference to NLP techniques;
alternatively, the parsing may be performed using a top-down parsing method (LL parsing), given grammar G and source string r. Starting from the beginning symbol S of G, r is gradually deduced by replacing (deriving) non-terminal symbols in the pattern by repeated use of the generator. This is a method of generation, an object-oriented method. The gist of the analysis is to select the appropriate Hou Xuanshi of the generator to derive, progressively matching the derivation with r. The objective of parsing is to parse the grammatical structure of a sentence and represent it as an easily understood structure.
And carrying out grammar analysis on the ship news data to obtain a grammar tree, wherein each node in the grammar tree is provided with a mark, the grammar tree is a graphic representation of a sentence structure, and represents the derivation result of the sentence, so that the grammar tree is beneficial to understanding the hierarchy of the sentence grammar structure. In short, a syntax tree is a tree formed when a derivation is performed according to a certain rule. A syntax tree includes all possible deductions of a pattern.
Optionally, the processing the location information and the time information in the analysis event coding information of the ship news data to obtain a ship news event track includes:
s41, performing reverse geocoding on the location information in the ship news data analysis event coding information to obtain longitude and latitude position information and structured geographic position information;
reverse geocoding is to reversely code the point position into a readable address or place name;
in combination with geocoding and routing services, reverse geocoding is a key component of mobile location-based services that can translate GPS-derived coordinates into readable addresses that are easier for the end user to understand.
S42, processing the longitude and latitude position information, the structured geographic position information and the time information to obtain a ship news event track.
Optionally, the matching the ship news event track with the known ship position data track includes:
s51, processing the ship news event track and the known ship position data track to obtain a unit length area;
and S52, comparing the unit length area with a preset unit length area threshold, and if the unit length area threshold is smaller than the preset unit length area threshold, matching the ship news event track with the known ship position data track.
The threshold value of the unit length area can be set through a plurality of experiments, and the invention is not limited.
Optionally, the processing the ship news event track and the known ship position data track to obtain a unit length area includes:
s511, processing the ship news event track and the known ship position data track by using an inter-track area calculation model to obtain two inter-track areas;
s512, processing the ship news event track and the known ship position data track to obtain a length average value of the two tracks;
s513, processing the area between the two tracks and the average value of the lengths of the two tracks to obtain the area per unit length.
Optionally, the processing the ship news event track and the known ship position data track by using an inter-track area calculation model to obtain two inter-track areas includes:
processing discrete points forming a ship news event track and the known ship position data track to form a plurality of continuous non-overlapping triangles between the two tracks;
and calculating the sum of areas of the continuous non-overlapping triangles, wherein the sum of areas is the area between two tracks.
The matching of the ship news event and the actual ship is realized through the matching of the track, the method can be realized in a programming mode, the method is used for processing the ship news data in batches through Spark-based packaging, analyzing event information in the ship news data, carrying out event coding, and further generating the event track based on the place and time in the event coding.
Optionally, matching the ship news event track with the known ship position data track may be implemented by the following method:
1) Track data pa= { a of two tracks is input 1 ,a 2 ,…,a n }、PB={b 1 ,b 2 ,…,b m };
2) Performing edge detection on the track data PA and PB to obtain edges of two tracks;
two templates are used to detect the horizontal profile edge and the vertical profile edge in the track, respectively:
when the template scale is 3×3, two convolution templates in the horizontal direction and the vertical direction are respectively:
assuming the track is A, the two templates are convolved with A as:
G x =d*A
G y =d y *A
when G x And G y After the calculation, the value of G can be calculated:
G=|G x |+|G y |
the gradient of the pixel point is denoted by G, and the edge point is a pixel point where G at the position is greater than a preset threshold value, and the setting of the threshold value may be performed through multiple experiments, for example, setting to g=150.
3) Extracting corner points from edges of the two tracks;
calculating partial derivatives of G in the x and y directions by using a difference operator, and calculating to obtain the partial derivatives to form a matrix of 2 multiplied by 2;
the 2 x 2 matrix is processed using a gaussian filter to obtain a structure tensor matrix M.
M=G*L
Wherein L is a Gaussian filter,sigma is a scale space factor, and the larger the numerical value of the sigma is, the more discrete the distribution of pixel points in the track is, and the greater the blurring degree is; the smaller the value of the value is, the smaller the representative scale information is, the lower the map blurring degree is, generally sigma is a numerical value larger than 0 and smaller than 1, and x and y are coordinates of elements in G;
obtaining characteristic value r of matrix determinant from tensor matrix 1 And r 2 According to r 1 And r 2 Judging the pixel point as a strong corner point R by the minimum value of the pixel points;
R=min(r 1 ,r 2 )
such as: r is (r) 1 =90,r 2 =91, r > 0, as corner point, r 1 =0.2,r 2 =0.1, r≡0, is a flat area, r 1 =90,r 2 =1, r < 0, boundary;
alternatively, a threshold T may be set c And Td, constraint is carried out on the number of the extracted corner points and the distance of the phase angle points, so that the number of the matched point pairs is conveniently measured, the overlapping of the description areas is prevented, and N corner points are obtained.
4) Establishing an angle point distance matrix according to the position point information of the angle points, and carrying out standardized processing on the angle point distance matrix;
calculating Euclidean distance of N corner points, thereby establishing an N x N two-dimensional matrix,
the calculation formula is as follows:
X=(x-min)/(x-max)
wherein max and min represent the maximum value and the minimum value of all elements in the two-dimensional matrix, X is the Euclidean distance, X is an element in the two-dimensional matrix, two N×N two-dimensional arrays C and D are obtained, C is a ship news event track, and D is a known ship position data track.
5) The diagonal point distance matrixes C and D are matched, and the specific method is as follows:
(1) Rapidly sequencing each row of the matrix in order from small to large;
(2) Searching the maximum value of each C, D matrix, recording the row where the maximum value is located, and recording the result as a 1 ,a 2 ,b 1 ,b 2 。
(3) Will a 1 ,b 1 Matching, if the matching result is not ideal, then a 1 ,b 2 And (5) matching, and recording the optimal matching result in the two matching processes.
If the matching result is not ideal, then a 1 ,a 2 Or b 1 ,b 2 And changing the corner distance next to the current distance to the row. And (3) if the current corner distance is 25% greater, otherwise, outputting the optimal matching result.
Therefore, the method can realize the matching of the ship news event and the actual ship by matching the tracks, can be realized in a programming mode, is used for processing the ship news data in batches by packaging based on Spark, analyzing the event information in the ship news data, carrying out event coding, further generating the event tracks based on the places and time in the event coding, and inputting the event codes and corresponding on-water mobile communication service identification codes (MMSI codes) into a ship library when the ship position (AIS) track of the ship is matched with the event tracks, thereby having higher matching efficiency from the ship news to the tracks, greatly freeing up labor and improving the matching accuracy.
Example two
Referring to fig. 2, fig. 2 is a flow chart of a device for matching news to tracks of a ship according to an embodiment of the invention. The device for matching the news of the ship to the track described in fig. 2 is applied to the technical field of matching the news of the ship to the track, for example, judging the type of the ship, positioning and tracking the ship, and the embodiment of the invention is not limited. As shown in fig. 2, the matching device of the new smelling track of the ship may include the following operations:
s301, a news data downloading module is used for monitoring a ship news website and loading ship news data; the ship news data comprise corresponding water mobile communication service identification codes;
s302, an event information analysis module is used for analyzing the ship news data to obtain ship news data analysis event information;
s303, an event information coding module, which is used for coding the analysis event information of the ship news data to obtain analysis event coding information of the ship news data;
s304, an event track generation module is used for processing the location information and the time information in the event coding information analyzed by the ship news data to obtain a ship news event track;
and S305, a track matching and inputting module is used for matching the ship news event track with the known ship position data track in the ship library, and if so, storing the ship news data analysis event coding information and the corresponding water mobile communication service identification code into the ship library.
Optionally, the analyzing the ship news data to obtain analysis event information of the ship news data includes:
s21, carrying out grammar analysis on the ship news data to obtain a grammar tree;
s22, carrying out syntactic analysis on the grammar tree to obtain analysis event information of the ship news data; the ship news data analysis event information comprises ship news data dependency relations, event roles, event attributes and named entities.
Optionally, the processing the location information and the time information in the analysis event coding information of the ship news data to obtain a ship news event track includes:
s41, performing reverse geocoding on the location information in the ship news data analysis event coding information to obtain longitude and latitude position information and structured geographic position information;
s42, processing the longitude and latitude position information, the structured geographic position information and the time information to obtain a ship news event track.
Optionally, the matching the ship news event track with the known ship position data track includes:
s51, processing the ship news event track and the known ship position data track to obtain a unit length area;
and S52, comparing the unit length area with a preset unit length area threshold, and if the unit length area threshold is smaller than the preset unit length area threshold, matching the ship news event track with the known ship position data track.
Optionally, the processing the ship news event track and the known ship position data track to obtain a unit length area includes:
s511, processing the ship news event track and the known ship position data track by using an inter-track area calculation model to obtain two inter-track areas;
s512, processing the ship news event track and the known ship position data track to obtain a length average value of the two tracks;
s513, processing the area between the two tracks and the average value of the lengths of the two tracks to obtain the area per unit length.
Optionally, the processing the ship news event track and the known ship position data track by using an inter-track area calculation model to obtain two inter-track areas includes:
processing discrete points forming a ship news event track and the known ship position data track to form a plurality of continuous non-overlapping triangles between the two tracks;
and calculating the sum of areas of the continuous non-overlapping triangles, wherein the sum of areas is the area between two tracks.
Example III
Referring to fig. 3, fig. 3 is a flow chart of another device for matching news to tracks of a ship according to an embodiment of the invention. The matching device of the new track of the ship described in fig. 3 is applied to the technical field of matching of news of the ship to the track, for example, judging the type of the ship, positioning and tracking the ship, etc., and the embodiment of the invention is not limited. As shown in fig. 3, the matching device of the new smelling track of the ship may include the following operations:
a memory 401 storing executable program codes;
a processor 402 coupled with the memory 401;
the processor 402 invokes executable program code stored in the memory 401 for performing the steps in the matching method of newly smelling a track by a ship as described in embodiment one.
Example IV
The embodiment of the invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps in the matching method of the new smelling track of the ship described in the embodiment one.
The apparatus embodiments described above are merely illustrative, in which the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a matching method and a device for ship news to tracks, which are disclosed as preferred embodiments of the invention, and are only used for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (9)
1. A method for matching news to tracks of a ship, the method comprising:
s1, monitoring a ship news website and loading ship news data; the ship news data comprise corresponding water mobile communication service identification codes;
s2, analyzing the ship news data to obtain ship news data analysis event information;
s3, encoding the ship news data analysis event information to obtain ship news data analysis event encoding information;
s4, processing the location information and the time information in the ship news data analysis event coding information to obtain a ship news event track;
s5, matching the ship news event track with the known ship position data track in the ship library, and storing the ship news data analysis event coding information and the corresponding water mobile communication service identification code into the ship library if the ship news event track is matched with the known ship position data track in the ship library, wherein the method comprises the following steps:
track data pa= { a of two tracks is input 1 ,a 2 ,…,a n }、PB={b 1 ,b 2 ,…,b m PA is the ship news event track, PB is the known ship position data track;
performing edge detection on the track data PA and PB to obtain edges of two tracks;
detecting a horizontal profile edge and a vertical profile edge in the two tracks with two templates, respectively, comprising:
when the template scale is 3×3, two convolution templates in the horizontal direction and the vertical direction are respectively:
the two templates and the track are respectively convolved as follows:
G x =d*A
G y =d y *A
wherein A represents a locus;
for G x And G y Processing to obtain a gradient G of the pixel point:
G=|G x |+|G y |
the edge point is a pixel point of the position G which is larger than a preset threshold value, and the setting of the threshold value can be carried out through multiple experiments;
corner extraction is carried out on edges of the two tracks, and the method comprises the following steps:
calculating partial derivatives of G in x and y directions by using a difference operator, wherein the partial derivatives form a matrix of 2 multiplied by 2;
processing the 2 x 2 matrix using a gaussian filter to obtain a structure tensor matrix M:
M=G*L
wherein L is a Gaussian filter,sigma is a scale space factor, and the larger the numerical value of the sigma is, the more discrete the distribution of pixel points in the track is, and the greater the blurring degree is; the smaller the value of the value is, the smaller the representative scale information is, the lower the map blurring degree is, generally sigma is a numerical value larger than 0 and smaller than 1, and x and y are coordinates of elements in G;
calculating to obtain characteristic values R1 and R2 of matrix determinant by using the tensor matrix, and judging the pixel point as a strong angular point R according to the minimum value in R1 and R2;
R=min(r 1 ,r 2 )
the strong angular point position information is used for establishing an angular point distance matrix and carrying out standardized processing on the angular point distance matrix, and the method comprises the following steps:
calculating Euclidean distances of N corner points, and establishing an N multiplied by N two-dimensional matrix:
X=(x-min)/(x-max)
wherein max and min represent the maximum value and the minimum value of all elements in the two-dimensional matrix, X is Euclidean distance, X is an element in the two-dimensional matrix, two N multiplied by N two-dimensional arrays C and D are obtained, C is a ship news event track, and D is a known ship position data track;
matching the angular point distance matrices C and D, comprising:
(1) Rapidly sequencing each row of the matrixes C and D in order from small to large;
(2) Searching the respective maximum value of the C, D matrix, recording the row where the maximum value is located, and recording the results as a1, a2, b1 and b 2 ;
(3) Will a 1 ,b 1 Matching, if the matching result is not ideal, then a 1 ,b 2 Matching is carried out, and the optimal matching result in the two matching processes is recorded;
if the matching result is not ideal, then a 1 ,a 2 Or b 1 ,b 2 Changing the line of the angular point distance next to the current distance; if the current corner distance is the first 25% largeAnd (3) executing, otherwise, ending, and outputting the optimal matching result.
2. The method for matching a new track of a ship according to claim 1, wherein the analyzing the ship news data to obtain analysis event information of the ship news data comprises:
s21, carrying out grammar analysis on the ship news data to obtain a grammar tree;
s22, carrying out syntactic analysis on the grammar tree to obtain analysis event information of the ship news data; the ship news data analysis event information comprises ship news data dependency relations, event roles, event attributes and named entities.
3. The method for matching a new track of a ship according to claim 1, wherein the processing the location information and the time information in the analysis event coding information of the ship news data to obtain the ship news event track comprises:
s41, performing reverse geocoding on the location information in the ship news data analysis event coding information to obtain longitude and latitude position information and structured geographic position information;
s42, processing the longitude and latitude position information, the structured geographic position information and the time information to obtain a ship news event track.
4. The method for matching a new-smelled track of a ship according to claim 1, wherein said matching the ship news event track with a known ship position data track comprises:
s51, processing the ship news event track and the known ship position data track to obtain a unit length area;
and S52, comparing the unit length area with a preset unit length area threshold, and if the unit length area threshold is smaller than the preset unit length area threshold, matching the ship news event track with the known ship position data track.
5. The method for matching a new-smelling track of a ship according to claim 4, wherein said processing said ship news event track and said known ship position data track to obtain an area per unit length comprises:
s511, processing the ship news event track and the known ship position data track by using an inter-track area calculation model to obtain two inter-track areas;
s512, processing the ship news event track and the known ship position data track to obtain a length average value of the two tracks;
s513, processing the area between the two tracks and the average value of the lengths of the two tracks to obtain the area per unit length.
6. The method for matching ship news to a track according to claim 5, wherein the processing the ship news event track and the known ship position data track using the inter-track area calculation model to obtain two inter-track areas includes:
processing discrete points forming a ship news event track and the known ship position data track to form a plurality of continuous non-overlapping triangles between the two tracks;
and calculating the sum of areas of the continuous non-overlapping triangles, wherein the sum of areas is the area between two tracks.
7. A ship news-to-track matching apparatus, the apparatus comprising:
the news data downloading module is used for monitoring the ship news website and loading the ship news data; the ship news data comprise corresponding water mobile communication service identification codes;
the event information analysis module is used for analyzing the ship news data to obtain ship news data analysis event information;
the event information coding module is used for coding the ship news data analysis event information to obtain ship news data analysis event coding information;
the event track generation module is used for processing the location information and the time information in the ship news data analysis event coding information to obtain a ship news event track;
the track matching and inputting module is used for matching the ship news event track with the known ship position data track in the ship library, and if the ship news event track is matched with the known ship position data track, the ship news data analysis event coding information and the corresponding water mobile communication service identification code are stored in the ship library, and the track matching and inputting module comprises the following steps:
track data pa= { a of two tracks is input 1 ,a 2 ,…,a n }、PB={b 1 ,b 2 ,…,b m PA is the ship news event track, PB is the known ship position data track;
performing edge detection on the track data PA and PB to obtain edges of two tracks;
detecting a horizontal profile edge and a vertical profile edge in the two tracks with two templates, respectively, comprising:
when the template scale is 3×3, two convolution templates in the horizontal direction and the vertical direction are respectively:
the two templates and the track are respectively convolved as follows:
G x =d*A
G y =d y *A
wherein A represents a locus;
for G x And G y Processing to obtain a gradient G of the pixel point:
G=|G x |+|G y |
the edge point is a pixel point of the position G which is larger than a preset threshold value, and the setting of the threshold value can be carried out through multiple experiments;
corner extraction is carried out on edges of the two tracks, and the method comprises the following steps:
calculating partial derivatives of G in x and y directions by using a difference operator, wherein the partial derivatives form a matrix of 2 multiplied by 2;
processing the 2 x 2 matrix using a gaussian filter to obtain a structure tensor matrix M:
M=G*L
wherein L is a Gaussian filter,sigma is a scale space factor, and the larger the numerical value of the sigma is, the more discrete the distribution of pixel points in the track is, and the greater the blurring degree is; the smaller the value of the value is, the smaller the representative scale information is, the lower the map blurring degree is, generally sigma is a numerical value larger than 0 and smaller than 1, and x and y are coordinates of elements in G;
calculating the eigenvalue r of matrix determinant by using the tensor matrix 1 And r 2 According to r 1 And r 2 Judging the pixel point as a strong corner point R by the minimum value of the pixel points;
R=min(r 1 ,r 2 )
the strong angular point position information is used for establishing an angular point distance matrix and carrying out standardized processing on the angular point distance matrix, and the method comprises the following steps:
calculating Euclidean distances of N corner points, and establishing an N multiplied by N two-dimensional matrix:
X=(x-min)/(x-max)
wherein max and min represent the maximum value and the minimum value of all elements in the two-dimensional matrix, X is Euclidean distance, X is an element in the two-dimensional matrix, two N multiplied by N two-dimensional arrays C and D are obtained, C is a ship news event track, and D is a known ship position data track;
matching the angular point distance matrices C and D, comprising:
(1) Rapidly sequencing each row of the matrixes C and D in order from small to large;
(2) Searching the maximum value of each C, D matrix, recording the row where the maximum value is located, and recording the result as a 1 ,a 2 ,b 1 ,b 2 ;
(3) Will a 1 ,b 1 Matching, if the matching result is not ideal, then a 1 ,b 2 Matching is carried out, and the optimal matching result in the two matching processes is recorded;
if the matching result is not ideal, then a 1 ,a 2 Or b 1 ,b 2 Changing the line of the angular point distance next to the current distance; and (3) if the current corner distance is 25% greater, executing step (3), otherwise, ending and outputting the optimal matching result.
8. A ship news-to-track matching apparatus, the apparatus comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the matching method of newly smelling a trajectory by a ship as claimed in any one of claims 1-6.
9. A computer storage medium storing computer instructions which, when invoked, are adapted to perform the matching method of a new smelling trajectory of a vessel according to any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211504875.6A CN115730156B (en) | 2022-11-28 | 2022-11-28 | Matching system and method for new track smelling of ship |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211504875.6A CN115730156B (en) | 2022-11-28 | 2022-11-28 | Matching system and method for new track smelling of ship |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115730156A CN115730156A (en) | 2023-03-03 |
CN115730156B true CN115730156B (en) | 2023-06-27 |
Family
ID=85298827
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211504875.6A Active CN115730156B (en) | 2022-11-28 | 2022-11-28 | Matching system and method for new track smelling of ship |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115730156B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20160112188A (en) * | 2015-03-18 | 2016-09-28 | 한국전자통신연구원 | System for extracting ship route trajectory and displaying thereof |
KR20200007200A (en) * | 2018-07-12 | 2020-01-22 | 한국해양과학기술원 | System for Providing Location Data and Location Tracking of Accident Vessel and Method for Controlling the same |
CN114647736A (en) * | 2021-12-10 | 2022-06-21 | 中国人民解放军战略支援部队信息工程大学 | Ship activity knowledge graph construction method |
CN114966771A (en) * | 2022-05-18 | 2022-08-30 | 北方联创通信有限公司 | Message acquisition method and device based on ship track, storage medium and equipment |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8924137B2 (en) * | 2011-09-30 | 2014-12-30 | Lockheed Martin Corporation | Method and apparatus for dynamic air traffic trajectory synchronization |
CN106487828B (en) * | 2015-08-25 | 2022-02-25 | 北京奇虎科技有限公司 | News pushing method and device |
KR101810666B1 (en) * | 2016-06-08 | 2017-12-20 | 한국과학기술원 | APPARATUS AND METHOD FOR MEASURING POSITION of SHIP USING MARINE RADAR AND COASTLINE MAP |
GB201810209D0 (en) * | 2018-06-21 | 2018-08-08 | McGurk Anthony | Container tracking |
CN110487278A (en) * | 2019-08-26 | 2019-11-22 | 中国人民解放军91550部队 | Ship track real-time display method and system based on multisource data fusion |
CN110928967A (en) * | 2019-11-05 | 2020-03-27 | 厦门北斗通信息技术股份有限公司 | Ship behavior analysis method and system based on big data |
-
2022
- 2022-11-28 CN CN202211504875.6A patent/CN115730156B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20160112188A (en) * | 2015-03-18 | 2016-09-28 | 한국전자통신연구원 | System for extracting ship route trajectory and displaying thereof |
KR20200007200A (en) * | 2018-07-12 | 2020-01-22 | 한국해양과학기술원 | System for Providing Location Data and Location Tracking of Accident Vessel and Method for Controlling the same |
CN114647736A (en) * | 2021-12-10 | 2022-06-21 | 中国人民解放军战略支援部队信息工程大学 | Ship activity knowledge graph construction method |
CN114966771A (en) * | 2022-05-18 | 2022-08-30 | 北方联创通信有限公司 | Message acquisition method and device based on ship track, storage medium and equipment |
Non-Patent Citations (4)
Title |
---|
"东方之星"沉船事件与通讯社信息传递:中外主要通讯社报道中国自然灾害关注点差异研究;刘亚南;周玲;宿洁;;风险灾害危机研究(02);第110-144页 * |
Vessel Pattern Recognition Using Trajectory Shape Feature;Jia Li 等;ACM;第84–90页 * |
基于北斗系统的船舶运输通信移动平台研究;陶红飞;;企业技术开发(03);第41-44页 * |
船舶进离港行为捕获算法设计与实现;王永明;饶全成;姚萍;;上海海事大学学报(01);第6-12页 * |
Also Published As
Publication number | Publication date |
---|---|
CN115730156A (en) | 2023-03-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110597799B (en) | Automatic filling method, system and equipment for missing value of time sequence data | |
CN111784673B (en) | Defect detection model training and defect detection method, device and storage medium | |
CN110866115B (en) | Sequence labeling method, system, computer equipment and computer readable storage medium | |
CN110543877A (en) | Identification recognition method, training method and device of model thereof and electronic system | |
CN112487812A (en) | Nested entity identification method and system based on boundary identification | |
CN115221842B (en) | Font style migration method, system and equipment based on small sample dataset | |
CN116994140A (en) | Cultivated land extraction method, device, equipment and medium based on remote sensing image | |
CN114140831B (en) | Human body posture estimation method and device, electronic equipment and storage medium | |
CN115730156B (en) | Matching system and method for new track smelling of ship | |
CN110879972A (en) | Face detection method and device | |
CN111539435A (en) | Semantic segmentation model construction method, image segmentation equipment and storage medium | |
CN116306663B (en) | Semantic role labeling method, device, equipment and medium | |
CN115810215A (en) | Face image generation method, device, equipment and storage medium | |
CN115205738A (en) | Emergency drainage method and system applied to urban inland inundation | |
CN110852102B (en) | Chinese part-of-speech tagging method and device, storage medium and electronic equipment | |
CN116050554A (en) | Scenic spot passenger flow volume prediction method and device, computing equipment and storage medium | |
CN111832610A (en) | 3D printing organization prediction method, system, medium and terminal equipment | |
CN116361816B (en) | Intelligent contract vulnerability detection method, system, storage medium and equipment | |
CN115731477A (en) | Image recognition method, illicit detection method, terminal device, and storage medium | |
CN115082430B (en) | Image analysis method and device and electronic equipment | |
CN115984604A (en) | Target detection method and device, computer equipment and readable storage medium | |
CN116977782A (en) | Training method and related device for small sample detection model | |
CN116152487A (en) | Target detection method, device, equipment and medium based on depth IoU network | |
CN113434635A (en) | Word segmentation method, device, equipment and storage medium based on unsupervised learning | |
CN114764444A (en) | Image generation and sample image expansion method, device and computer storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |