[go: up one dir, main page]

CN116166897A - Hot spot data fusion method based on AIS and ADS-B combination - Google Patents

Hot spot data fusion method based on AIS and ADS-B combination Download PDF

Info

Publication number
CN116166897A
CN116166897A CN202310164364.2A CN202310164364A CN116166897A CN 116166897 A CN116166897 A CN 116166897A CN 202310164364 A CN202310164364 A CN 202310164364A CN 116166897 A CN116166897 A CN 116166897A
Authority
CN
China
Prior art keywords
information
text
vector
ship
ads
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.)
Granted
Application number
CN202310164364.2A
Other languages
Chinese (zh)
Other versions
CN116166897B (en
Inventor
胡波
黄挺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Big Data Research Institute Of Peking University
Original Assignee
Chongqing Big Data Research Institute Of Peking University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Big Data Research Institute Of Peking University filed Critical Chongqing Big Data Research Institute Of Peking University
Priority to CN202310164364.2A priority Critical patent/CN116166897B/en
Publication of CN116166897A publication Critical patent/CN116166897A/en
Application granted granted Critical
Publication of CN116166897B publication Critical patent/CN116166897B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/31—Indexing; Data structures therefor; Storage structures
    • G06F16/316—Indexing structures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Human Computer Interaction (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a hotspot data fusion method based on AIS and ADS-B combination, which comprises the following steps: s1, acquiring ship AIS data and aircraft ADS-B data of a target sea area; s2, acquiring text information of news events of a target sea area, and extracting target news event information from the text information of the news events; s3, information fusion is carried out on the ship AIS data, the airplane ADS-B data and the target news event information to form relevant information, and through the method, the hot event and the ship and airplane related data in the unknown setting range of the hot event are formed into relevant information, so that corresponding ship and airplane related data can be called at the same time when the hot event is analyzed, and subsequent planning of ships, airplane navigation plans and the like is facilitated.

Description

Hot spot data fusion method based on AIS and ADS-B combination
Technical Field
The invention relates to a data fusion method, in particular to a hot spot data fusion method based on combination of AIS and ADS-B.
Background
In some sea areas and airspaces corresponding to the sea areas, a plurality of ships and aircrafts pass through the sea areas and airspaces corresponding to the sea areas, and corresponding news events can also occur in the sea areas, when analysis is performed on data of the ships and aircrafts passing through the sea areas (such as analysis on the journey influence of hot events on the ships or aircrafts) after a certain news event occurs, because of mutual independence of the ships, aircrafts and the hot events, other ways are needed to be used for inquiring, so that the efficiency is low, the states of the ships and aircrafts in the set range of the occurrence position of the hot event cannot be known in time, the establishment of subsequent processing measures is not facilitated, and at present, an effective technical means for fusion and correlation of the three information is not available.
Therefore, in order to solve the above-mentioned technical problems, a new technical means is needed.
Disclosure of Invention
In view of the above, the present invention aims to provide a hotspot data fusion method based on the combination of AIS and ADS-B, which forms a related information from a hotspot event and related data of a ship and an aircraft within an unknown setting range of the occurrence of the hotspot event, so that corresponding related data of the ship and the aircraft can be simultaneously invoked when analyzing the hotspot event, thereby facilitating the formulation of a subsequent ship and an aircraft navigation plan.
The invention provides a hotspot data fusion method based on AIS and ADS-B combination, which comprises the following steps:
s1, acquiring ship AIS data and aircraft ADS-B data of a target sea area;
s2, acquiring text information of news events of a target sea area, and extracting target news event information from the text information of the news events;
s3, information fusion is carried out on the ship AIS data, the airplane ADS-B data and the target news event information to form associated information.
Further, the ship AIS data includes: ship MMSI number, ship name, IMO number, ship type, longitude and latitude trajectory, and arrival and departure time.
Further, the aircraft ADS-B data comprises aircraft flight, departure time, aircraft model number, registration number, aircraft longitude and latitude track and ICAO number.
Further, in step S3, the forming of the association information specifically includes:
extracting news event occurrence time t 0 And the place of occurrence coordinate D 0 (x 0 ,y 0 )；
Extracting state information of the ship and the airplane when the news event occurs, wherein the state information comprises the moment at which the ship and the airplane are positioned and the coordinates under the moment;
calculating the association degree C of ships, planes and news events i ：
Figure BDA0004095398480000021
Wherein N is an effective distance threshold, K is an effective time interval threshold, r=1, 2, r=1 represents a ship, r=2 represents an aircraft, i represents an ith point in time, (x ri ,y ri ) Representing coordinates of the aircraft or the ship at the ith moment;
degree of correlation C i And storing hot event information, ship AIS data and aircraft ADS-B data corresponding to the moment when the hot event information is larger than the set threshold value and forming associated information under the same index.
Further, in step S2, extracting the target news event information includes:
s21, capturing text information of the same news event of a target sea area from a target webpage;
s22, performing word segmentation processing on the text information by adopting a preset word segmentation model, and then performing stop word removal processing;
s23, constructing a word vector by adopting a Bert model, determining the weight of the word vector, and giving the weight of the word vector and the word vector to construct a text vector;
s24, constructing an event vector based on the text vector;
s25, calculating the similarity between the event vector and each text vector, and taking the text information corresponding to the news event with the similarity larger than the set threshold value as final target news event information.
Further, in step S3, a text vector is constructed according to the following method:
T i ＝∑W ij ·ω ij the method comprises the steps of carrying out a first treatment on the surface of the Wherein W is ij Represents the j-th word vector, omega in the text i ij Representing the weight of the jth word in the text;
Figure BDA0004095398480000031
wherein: n is n j For the number of times the jth word appears in the text, N represents the total number of words in the document, tf ij Is the frequency with which the jth word appears in the text.
Further, in step S24, the event vector a is constructed by:
A＝∑w r *T i ；
wherein: w (w) r For a single text vector T i Weights of (2);
w r =a·β+b·δ+c·epsilon+d·λ; wherein: beta is the importance degree of the text information source, delta is the authority of the text information source, epsilon is the completeness of the text information, lambda is the timeliness of the text information, and a, b, c, d is a constant coefficient.
Further, the similarity is determined according to the following method:
Figure BDA0004095398480000032
wherein: d (A, T) i ) For event vector A and text vector T i Euclidean distance between, cos (A, T i ) For event vector A and text vector T i Cosine similarity of (c).
The invention has the beneficial effects that: according to the invention, the hot event and the ship and plane related data in the unknown setting range of the hot event are formed into the related information, so that the corresponding ship and plane related data can be simultaneously called when the hot event is analyzed, and the subsequent preparation of navigation plans of the ship and the plane and the like is facilitated.
Drawings
The invention is further described below with reference to the accompanying drawings and examples:
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a flowchart of a hot event acquisition process according to the present invention.
Detailed Description
The present invention is further described in detail below:
the invention provides a hotspot data fusion method based on AIS and ADS-B combination, which comprises the following steps:
s1, acquiring ship AIS data and aircraft ADS-B data of a target sea area;
s2, acquiring text information of news events of a target sea area, and extracting target news event information from the text information of the news events;
s3, information fusion is carried out on the ship AIS data, the airplane ADS-B data and the target news event information to form relevant information, and through the method, the hot event and the ship and airplane related data in the unknown setting range of the hot event are formed into relevant information, so that corresponding ship and airplane related data can be called at the same time when the hot event is analyzed, and subsequent planning of ships, airplane navigation plans and the like is facilitated.
Wherein: the ship AIS data includes: ship MMSI number, ship name, IMO number, ship type, longitude and latitude trajectory, and arrival and departure time.
The aircraft ADS-B data comprises aircraft flight, departure time, aircraft model, registration number, aircraft longitude and latitude track and ICAO number.
In this embodiment, in step S3, the forming of the association information specifically includes:
extracting news event occurrence time t 0 And the place of occurrence coordinate D 0 (x 0 ,y 0 )；
Extracting state information of the ship and the airplane when the news event occurs, wherein the state information comprises the moment at which the ship and the airplane are positioned and the coordinates under the moment;
calculating the association degree C of ships, planes and news events i ：
Figure BDA0004095398480000051
Wherein N is an effective distance threshold, that is, the corresponding data of the ship or the aircraft passing within the square and round distance of N (unit sea or kilometer) at the occurrence position of the hot event is effective, K is an effective time interval threshold, r=1, 2, when r=1, r=2, i represents the ith moment point, (x) ri ,y ri ) Representing coordinates of the aircraft or the ship at the ith moment; a and b are constant coefficients, and are set according to different sea areas and different moments;
degree of correlation C i Storing hot event information, ship AIS data and aircraft ADS-B data corresponding to the moment when the hot event information is larger than the set threshold value and forming associated information under the same index; when the minimum distance between the ship and the hotspot event occurrence place in the longitude and latitude track of the airplane is larger than N, the current hotspot event is not considered to be associated with the current airplane or the ship, or if the time between the moment when the ship or the airplane passes through the sea area or the airspace within the hotspot event effective distance threshold value range and the hotspot event occurrence time interval is larger than K, the current hotspot event is not considered to be associated with the current airplane or the ship.
In this embodiment, in step S2, extracting the target news event information includes:
s21, capturing text information of the same news event of a target sea area from a target webpage;
s22, performing word segmentation processing on the text information by adopting a preset word segmentation model, and then performing stop word removal processing;
s23, constructing word vectors by adopting a Bert model, namely, constructing a word vector by each word, determining the weight of the word vector, and giving the weight of the word vector and the word vector to construct a text vector;
s24, constructing an event vector based on the text vector;
s25, calculating the similarity between the event vector and each text vector, and taking the text information corresponding to the news event with the similarity larger than the set threshold value as final target news event information.
In this embodiment, in step S3, a text vector is constructed according to the following method:
T i ＝∑W ij ·ω ij the method comprises the steps of carrying out a first treatment on the surface of the Wherein W is ij Represents the j-th word vector, omega in the text i ij Representing the weight of the jth word in the text;
Figure BDA0004095398480000061
wherein: n is n j For the number of times the jth word appears in the text, N represents the total number of words in the document, tf ij Is the frequency with which the jth word appears in the text.
In this embodiment, in step S24, the event vector a is constructed by the following method:
A＝∑w r *T i ；
wherein: w (w) r For a single text vector T i Weights of (2);
w r =a·β+b·δ+c·epsilon+d·λ; wherein: beta is the importance degree of the text information source, delta is the authority of the text information source, epsilon is the completeness of the text information, lambda is the timeliness of the text information, and a, b, c, d is a constant coefficient.
In this embodiment, the similarity is determined according to the following method:
Figure BDA0004095398480000062
wherein: d (A, T) i ) For event vector A and text vector T i Euclidean distance between, cos (A, T i ) For event vector A and text vector T i Cosine similarity of (c).
Finally, it is noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered by the scope of the claims of the present invention.

Claims (8)

1. A hot spot data fusion method based on AIS and ADS-B combination is characterized in that: comprising the following steps:
s1, acquiring ship AIS data and aircraft ADS-B data of a target sea area;
s2, acquiring text information of news events of a target sea area, and extracting target news event information from the text information of the news events;
s3, information fusion is carried out on the ship AIS data, the airplane ADS-B data and the target news event information to form associated information.
2. The hotspot data fusion method based on the combination of AIS and ADS-B as claimed in claim 1, wherein: the ship AIS data includes: ship MMSI number, ship name, IMO number, ship type, longitude and latitude trajectory, and arrival and departure time.
3. The hotspot data fusion method based on the combination of AIS and ADS-B as claimed in claim 1, wherein: the aircraft ADS-B data comprises aircraft flight, departure time, aircraft model, registration number, aircraft longitude and latitude track and ICAO number.
4. The hotspot data fusion method based on the combination of AIS and ADS-B as claimed in claim 1, wherein: in step S3, the forming of the association information specifically includes:
extracting news event occurrence time t 0 And the place of occurrence coordinate D 0 (x 0 ,y 0 )；
Extracting state information of the ship and the airplane when the news event occurs, wherein the state information comprises the moment at which the ship and the airplane are positioned and the coordinates under the moment;
calculating the association degree C of ships, planes and news events i ：
Figure FDA0004095398470000011
Wherein N is an effective distance thresholdThe value K is the effective time interval threshold, r=1, 2, r=1 for the ship, r=2 for the aircraft, i for the ith point in time, (x) ri ,y ri ) Representing coordinates of the aircraft or the ship at the ith moment;
degree of correlation C i And storing target news event information, ship AIS data and aircraft ADS-B data corresponding to the moment when the target news event information is larger than the set threshold value and forming associated information under the same index.
5. The hotspot data fusion method based on the combination of AIS and ADS-B as claimed in claim 1, wherein: in step S2, extracting the target news event information includes:
s21, capturing text information of the same news event of a target sea area from a target webpage;
s22, performing word segmentation processing on the text information by adopting a preset word segmentation model, and then performing stop word removal processing;
s23, constructing a word vector by adopting a Bert model, determining the weight of the word vector, and giving the weight of the word vector and the word vector to construct a text vector;
s24, constructing an event vector based on the text vector;
s25, calculating the similarity between the event vector and each text vector, and taking the text information corresponding to the news event with the similarity larger than the set threshold value as final target news event information.
6. The hotspot data fusion method based on the combination of AIS and ADS-B according to claim 5, wherein: in step S3, a text vector is constructed according to the following method:
T i ＝∑W ij ·ω ij the method comprises the steps of carrying out a first treatment on the surface of the Wherein W is ij Represents the j-th word vector, omega in the text i ij Representing the weight of the jth word in the text;
Figure FDA0004095398470000021
wherein: n is n j Appears in text for the jth wordThe number of times, N, represents the total number of words in the document, tf ij Is the frequency with which the jth word appears in the text.
7. The hotspot data fusion method based on the combination of AIS and ADS-B as claimed in claim 6, wherein: in step S24, the event vector a is constructed by:
A＝∑w r *T i ；
wherein: w (w) r For a single text vector T i Weights of (2);
w r =a·β+b·δ+c·epsilon+d·λ; wherein: beta is the importance degree of the text information source, delta is the authority of the text information source, epsilon is the completeness of the text information, lambda is the timeliness of the text information, and a, b, c, d is a constant coefficient.
8. The hotspot data fusion method based on the combination of AIS and ADS-B as claimed in claim 6, wherein: the similarity is determined according to the following method:
Figure FDA0004095398470000031
wherein: d (A, T) i ) For event vector A and text vector T i Euclidean distance between, cos (A, T i ) For event vector A and text vector T i Cosine similarity of (c). />
CN202310164364.2A 2023-02-24 2023-02-24 Hot spot data fusion method based on AIS and ADS-B combination Active CN116166897B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310164364.2A CN116166897B (en) 2023-02-24 2023-02-24 Hot spot data fusion method based on AIS and ADS-B combination

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310164364.2A CN116166897B (en) 2023-02-24 2023-02-24 Hot spot data fusion method based on AIS and ADS-B combination

Publications (2)

Publication Number Publication Date
CN116166897A true CN116166897A (en) 2023-05-26
CN116166897B CN116166897B (en) 2024-08-13

Family

ID=86419808

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310164364.2A Active CN116166897B (en) 2023-02-24 2023-02-24 Hot spot data fusion method based on AIS and ADS-B combination

Country Status (1)

Country Link
CN (1) CN116166897B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104331419A (en) * 2014-10-13 2015-02-04 北京奇虎科技有限公司 Method and device for measuring importance of news
CN105488092A (en) * 2015-07-13 2016-04-13 中国科学院信息工程研究所 Time-sensitive self-adaptive on-line subtopic detecting method and system
US20180299291A1 (en) * 2017-04-12 2018-10-18 Microsoft Technology Licensing, Llc Generating routes using events
US20190286793A1 (en) * 2012-10-02 2019-09-19 Banjo, Inc. Event-based vehicle operation and event remediation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190286793A1 (en) * 2012-10-02 2019-09-19 Banjo, Inc. Event-based vehicle operation and event remediation
CN104331419A (en) * 2014-10-13 2015-02-04 北京奇虎科技有限公司 Method and device for measuring importance of news
CN105488092A (en) * 2015-07-13 2016-04-13 中国科学院信息工程研究所 Time-sensitive self-adaptive on-line subtopic detecting method and system
US20180299291A1 (en) * 2017-04-12 2018-10-18 Microsoft Technology Licensing, Llc Generating routes using events

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
林筝;: "面向移动端展示的新闻地图发布平台设计", 地理空间信息, no. 12, 31 December 2019 (2019-12-31), pages 31 - 34 *

Also Published As

Publication number Publication date
CN116166897B (en) 2024-08-13

Similar Documents

Publication Publication Date Title
Wang et al. Short-term 4d trajectory prediction using machine learning methods
CA2936382C (en) A computer-implemented method and system for setting up an air traffic simulator
CN113284369A (en) Prediction method for actual measurement airway data based on ADS-B
Jiang et al. Research on method of trajectory prediction in aircraft flight based on aircraft performance and historical track data
Yang Practical method for 4-dimentional strategic air traffic management problem with convective weather uncertainty
US10801841B1 (en) Trajectory prediction via a feature vector approach
CN116166897B (en) Hot spot data fusion method based on AIS and ADS-B combination
CN116543603A (en) Flight path completion prediction method and device considering airspace situation and local optimization
CN103678925A (en) Flight path classification method based on auxiliary information source
CN116363908B (en) Flight track yaw detection method, electronic equipment and storage medium
US10345106B1 (en) Trajectory analysis with geometric features
CN116681413B (en) Flight arrival time determining method, electronic equipment and storage medium
CN113535866A (en) Aircraft track fusion method, system and computer readable storage medium
Silvestre et al. Towards aircraft trajectory prediction using LSTM networks
CN117238177A (en) A method and device for measuring the consistency of approach traffic flow trajectories
Xu et al. Data-Driven Departure Flight Time Prediction Based on Feature Construction and Ensemble Learning
CN113360849B (en) Sea ice density estimation method and system based on ICESat-2 data
CN113705651B (en) Air condition target identification method and device based on radar information
Qin et al. Research on dynamic route planning under adverse weather
Takeichi et al. Feasibility study on modeling of cruise flight time uncertainty
CN115903917A (en) A search and rescue route planning method and device for a large amphibious aircraft
Huang et al. Efficient Real-Time Aircraft ETA Prediction via Feature Tokenization Transformer
Sudarsanan et al. Predicting Air Traffic Congestion at Arrival Fixes Using Deep Learning for Operational Disruption Forecast and Monitoring
Liu et al. Joint kinematic and feature tracking of ships with satellite electronic information
US12475805B1 (en) Methods and systems for cooperative airborne meteorological perception with multiple aircraft

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