CN113626616A - Aircraft safety early warning method, device and system - Google Patents

Aircraft safety early warning method, device and system Download PDF

Info

Publication number
CN113626616A
CN113626616A CN202110981104.5A CN202110981104A CN113626616A CN 113626616 A CN113626616 A CN 113626616A CN 202110981104 A CN202110981104 A CN 202110981104A CN 113626616 A CN113626616 A CN 113626616A
Authority
CN
China
Prior art keywords
knowledge
data
early warning
data source
aircraft
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
CN202110981104.5A
Other languages
Chinese (zh)
Other versions
CN113626616B (en
Inventor
熊壬浩
翟振刚
王彪
章栎
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.)
CETC 36 Research Institute
Original Assignee
CETC 36 Research Institute
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 CETC 36 Research Institute filed Critical CETC 36 Research Institute
Priority to CN202110981104.5A priority Critical patent/CN113626616B/en
Publication of CN113626616A publication Critical patent/CN113626616A/en
Application granted granted Critical
Publication of CN113626616B publication Critical patent/CN113626616B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367Ontology
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/335Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/10Geometric CAD
    • G06F30/15Vehicle, aircraft or watercraft design
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03Data mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Computer Hardware Design (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application discloses an aircraft safety early warning method, device and system, wherein the method comprises the following steps: continuously monitoring the change condition of a plurality of heterogeneous data sources; for the changed data source, extracting entities and relations thereof in the data source, and associating the entities by using the relations to finally form a plurality of knowledge maps corresponding to the data source; fusing a plurality of knowledge maps corresponding to the data source according to the ontology model, wherein the ontology model is obtained by modeling the aviation security threat event; predicting the dangerous case of the target aircraft according to the early warning logic rule and the knowledge graph; and sending an emergency alarm to the ground early warning terminal so that the air traffic controller can respond to the emergency alarm and send a command instruction to the target aircraft. The method breaks through the barrier between multi-source heterogeneous data, integrates historical and real-time data, utilizes the association and reasoning capabilities of the knowledge graph, and can be used for modeling and analyzing the security threat event in a complex scene.

Description

Aircraft safety early warning method, device and system
Technical Field
The application relates to the technical field of air traffic service, in particular to an aircraft safety early warning method, device and system.
Background
Air traffic management (air traffic management) is a process of managing and controlling flight activities by using technical means to ensure safe and orderly flight. The tasks of air traffic management are: effectively maintains and promotes air traffic safety, maintains air traffic order and ensures smooth air traffic. One of the main contents thereof is air traffic service (air traffic service). The air traffic service is provided for civil aircrafts by air traffic control units, and the flight condition of the aircrafts is managed and controlled by using equipment and technical means, so that the air traffic service is an important means for ensuring flight safety. The contents of the air traffic service include traffic control service, flight intelligence service, and alarm service, etc.
Air traffic management (hereinafter "air traffic") generally has the following characteristics: (1) the equipment is various, including communication equipment, navigation management equipment, navigation equipment, meteorological equipment and the like; (2) multiple equipment deployments are required to extend coverage, for example, the coverage of an Automatic Dependent Surveillance-Broadcast (ADS-B) ground station of a single aircraft is limited, and a plurality of ground stations can be associated to form a continuous Surveillance track; (3) the roles participating in communication interaction are various, such as other machines, local machines and ground stations; (4) the data systems are relatively independent, such as an airplane comprehensive data system, a meteorological database system, an aeronautical meteorological network service system and the like. The working principles of the devices are different, the used data models are different, and redundancy exists among data, so that comprehensive analysis and decision making of a controller are difficult.
Existing air traffic control automation systems typically use data fusion techniques to process multi-source data to provide uniform and comprehensive monitoring data. The existing air traffic control data fusion technology mainly has the following problems: (1) the supported application scenes are limited, and the aim is to enlarge the monitoring range or improve the monitoring precision; (2) the fusion object is single, and is usually only aimed at the same type of equipment, such as only aimed at a plurality of ADS-B ground stations, a plurality of radars, or a plurality of same type data systems, such as GRIB meteorological data and AMDAR meteorological data; (3) the modeling and analyzing capability and the automatic emergency processing capability of the security threat event are lacked.
Disclosure of Invention
In order to solve the problems that an application scene supported by the existing data fusion technology in the field of air traffic service is limited, a fusion object is single, modeling analysis capability of a security threat event is lacked, and the like, the embodiment of the application provides an aircraft security early warning method, device and system.
In a first aspect, an aircraft safety precaution method is provided, including:
continuously monitoring the change condition of a plurality of heterogeneous data sources;
for the changed data source, extracting entities and relations thereof in the data source, and associating the entities by using the relations to form a plurality of knowledge maps corresponding to the data source;
fusing a plurality of knowledge maps corresponding to the data source according to the ontology model, wherein the ontology model is obtained by modeling according to the aviation security threat event;
predicting the dangerous case of the target aircraft according to early warning logic rules and the knowledge graph;
and sending an emergency alarm to a ground early warning terminal so that an air traffic controller responds to the emergency alarm and sends a command instruction to the target aircraft.
Optionally, in the above method, the continuously monitoring the change condition of the multiple heterogeneous data sources includes:
polling a plurality of data sources in parallel according to a preset time interval, extracting a current data item and comparing the current data item with a historically extracted data item for each data source, continuing polling the data sources if the current data item does not meet an updating strategy, and determining that the data source is changed if the current data item of a certain data source meets the updating strategy;
wherein the plurality of heterogeneous data sources comprise at least two of a broadcast type automatic correlation monitoring system of the aircraft, a weather testing system of the aircraft, a national weather information center weather big data interface service platform, a global real-time flight information platform and a global flight trajectory real-time tracking platform.
Optionally, in the above method, when the data source is structured data, a direct mapping method is used to extract entities and their relationships in the data source;
and when the data source is semi-structured data, extracting entities and the relation thereof in the data source by adopting a template-based method.
Optionally, in the above method, the fusing, according to the ontology model, a plurality of knowledge graphs corresponding to the data source includes:
modeling an aviation security threat event to obtain an ontology class and an ontology attribute of an ontology model;
fusing a plurality of knowledge maps corresponding to the data source according to the ontology class and the ontology attribute to obtain a fused knowledge map;
aiming at the problems of concept mismatching, synonymous terms, entity redundancy or unmatched coding formats when a plurality of knowledge maps are fused, a rule matching-based method is used for fusing entities and relationships to obtain a fused knowledge map.
Optionally, in the above method, the predicting the dangerous situation of the target aircraft according to the early warning logic rule and the knowledge graph includes:
the early warning logic rules are executed on the knowledge graph by the inference engine;
and generating zero or one or more dangerous case alarm messages after executing the early warning logic rules.
Optionally, the method further comprises the following steps:
and performing knowledge correction on the existing knowledge graph and the early warning logic rule according to the processing condition of the response emergency alarm.
Optionally, in the above method, the performing knowledge correction on the existing knowledge graph and the early warning logic rule according to the processing condition of responding to the alarm of the emergency, includes:
for effective alarm against dangerous case, establishing a copy in an alarm history database for the alarm message against dangerous case and the associated knowledge graph, and using the copy as a basis for judging whether the knowledge correction is correct;
and performing knowledge fusion correction and knowledge base correction on invalid dangerous case alarms, executing the correction and establishing a copy in an alarm history database only when the judged valid alarms are not influenced and new invalid alarms are not generated, and rejecting the correction if the correction is not influenced.
In a second aspect, the present application provides an aircraft safety precaution device, the device comprising:
the monitoring unit is used for continuously monitoring the change conditions of a plurality of heterogeneous data sources;
the extraction unit is used for extracting entities and relations thereof in the data source for the changed data source, and associating the entities by using the relations to form a plurality of knowledge maps corresponding to the data source;
the fusion unit is used for fusing a plurality of knowledge maps corresponding to the data source according to the ontology model, wherein the ontology model is obtained by modeling the aviation security threat event;
the dangerous case prediction unit is used for predicting the dangerous case of the target aircraft according to an early warning logic rule and the knowledge graph;
and the alarm response unit is used for sending an emergency alarm to the ground early warning terminal so that an air traffic controller can respond to the emergency alarm and send a command instruction to the target aircraft.
Optionally, the apparatus further comprises: and the correcting unit is used for performing knowledge correction on the existing knowledge graph and the early warning logic rule according to the processing condition of responding the dangerous case alarm.
In a third aspect, an aircraft safety precaution system is provided, the system comprising: the ground early warning terminal and the aircraft safety early warning device of claim 9, wherein the dangerous case warning message generated by the aircraft safety early warning device is put into a warning message queue of a message distribution system and is sent to the ground early warning terminal through the message distribution system.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects:
1. and multi-source data is comprehensively utilized, and air control capacity is improved. Aviation data is often distributed among multiple relatively independent application systems, making it difficult for related information to interact. The method and the system comprehensively utilize various data sources such as a flight monitoring system, a navigation system, a data platform and the Internet, and fuse heterogeneous information based on the knowledge map. Compared with the early warning method adopting a single data source, the method integrates historical data and real-time data, breaks barriers between multi-source heterogeneous data, and improves the capacity and efficiency of automatic air control.
2. And the modeling and analysis of the security threat event in a complex scene are supported. The safety threat scene is modeled based on the knowledge graph, the mutual connection among knowledge in related fields is constructed, mined, inferred and displayed by the knowledge graph, the safety threat events formed by comprehensive action of various factors under various scenes can be effectively modeled and analyzed, and the events threatening the safety of the aircraft are inferred and predicted on the basis.
3. And the correlation mining and analysis efficiency of the aviation data is improved in a graph-oriented form. A knowledge graph is a technical method for describing the association between knowledge and modeling world everything by using a graph model. The knowledge graph enhances the association between data in a graph-oriented form, and is favorable for more intuitively carrying out association mining and analysis on the data. Compared to hard-coded algorithms, knowledge-graph based reasoning usually focuses on logical rules and does not care about the data structure of the algorithm, and is therefore more flexible and easier to use.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 shows a schematic flow diagram of an aircraft safety warning method according to an embodiment of the application;
fig. 2 shows another flow diagram of an aircraft safety precaution method according to an embodiment of the application;
FIG. 3 illustrates a flow diagram for uninterrupted monitoring of changes to multiple data sources, according to one embodiment of the present application;
FIG. 4 shows a schematic diagram of a knowledge-graph formed from a direct mapping table 1;
FIG. 5 shows a flow diagram of an early warning response and knowledge base revision according to one embodiment of the present application;
fig. 6 shows a schematic structural diagram of an aircraft safety precaution device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
The information required for aircraft security threat analysis is often distributed among a number of relatively independent systems. The relevant data not only comes from the local machine, but also comes from other machines; including not only the airspace range visible to the current ground station, but also other ground stations. For example, an ADS-B message broadcast by an aircraft correlates with information such as its fuselage, airline, and airway weather, but is distributed over different network nodes. Barriers among multi-source heterogeneous data are clear, and challenges are brought to a traditional security threat early warning method.
The aircraft safety early warning method based on multi-source heterogeneous data source fusion monitoring is provided for solving the problems that in the prior art, an air traffic management service is limited in application scene, single in fusion object, lack of modeling analysis capability of a safety threat event and the like. The method makes use of the characteristics of the knowledge graph, and makes modeling and analysis of the security threat event under the complex scene possible.
In one embodiment of the present application, fig. 1 shows a flow diagram of an aircraft safety precaution method. As shown in FIG. 1, the flow of the aircraft safety early warning method comprises steps 1-6.
Wherein, the step 1: data change monitoring, namely monitoring the change condition of a plurality of heterogeneous data sources continuously; step 2: extracting knowledge, namely extracting entities and relations thereof in the changed data sources, and associating the entities by using the relations to form a plurality of knowledge maps corresponding to the data sources; and step 3: the method comprises the following steps of knowledge fusion, namely fusing a plurality of knowledge maps corresponding to a data source according to an ontology model, wherein the ontology model is obtained by modeling according to an aviation security threat event; and 4, step 4: predicting the dangerous case, namely predicting the dangerous case of the target aircraft according to early warning logic rules and the knowledge graph; and 5: and early warning response, namely sending an emergency warning to a ground early warning terminal so that an air traffic controller responds to the emergency warning and sends a command instruction to the target aircraft. Optionally, the method further includes step 6: and (4) knowledge correction, namely performing knowledge correction on the existing knowledge graph and the early warning logic rule according to the processing condition of responding the dangerous case alarm.
The steps of the present application are described in detail below. Fig. 2 shows another schematic flow diagram of an aircraft safety precaution method according to an embodiment of the application. As shown in fig. 2, the aircraft safety precaution method of the present application at least includes the following steps S210 to S250:
step S210: changes to multiple heterogeneous data sources are monitored without interruption.
This step continuously monitors the plurality of data sources to determine an update condition of the data.
The data sources that may be referred to in this application mainly include navigation data of the aircraft, aircraft state data, meteorological data, and the like, including but not limited to: the system comprises a broadcast automatic dependent surveillance system (ADS-B system), an Aircraft Meteorological Data Relay (AMDAR), a national Meteorological information center Meteorological big Data interface service platform, a global real-time flight information platform (flightrad 24), a global flight trajectory real-time tracking platform (Variflight), and the like.
The ADS-B system is an information system integrating communication and monitoring. ADS-B sends messages in a periodic and automatic broadcasting mode, and the message content comprises the identity, longitude and latitude, altitude, speed, airplane state and the like of the local machine. The identity of the machine is marked with a globally unique 24-bit address code specified by the International Civil Aviation Organization (ICAO).
The AMDAR is a weather observation system pursued by the World Meteorological Organization (WMO) that collects, processes, formats weather data, primarily using sensors, computers, and communication systems on existing aircraft, and transmits to ground stations via satellite or radio links. China's weather bureau and civil aviation bureau have formally signed an AMDAR cooperative project as early as 2004.
The global high altitude meteorological station timing value data provided by the national meteorological information center comprises potential height, temperature, dew point temperature, wind direction and wind speed observation data of a specified isobaric surface and a pressure temperature humidity characteristic layer obtained by a domestic communication system and a foreign air detection station obtained by a global communication system during daily routine observation, and is provided in the form of an Application Programming Interface (API).
The global real-time flight information platform is a global flight tracking service of Flightradar24, provides real-time information of thousands of airplanes around the world, including airplane positions, flight heights and the like, and also provides related information of flights, airlines and the like, historical flight record data and the like. Flightradar24 begins 2006 with the establishment of one ADS-B receiver network in Nordic and Central Europe. In 2009, the network was open and anyone with ADS-B receivers could upload data. Currently, Flightradar24 establishes 500 receivers in five continents worldwide to collect the auto-broadcast data of civil aircraft.
The global flight trajectory real-time tracking platform (Variflight) is an aviation data and solution service provider, the flight data of the platform achieves comprehensive coverage in China, the global coverage reaches 94%, and the flight data processing capacity reaches more than 1.6 million pieces per second.
Besides the data sources, available data sources also include an online database platform which is difficult to comprehensively utilize by traditional safety early warning methods, such as airframes.
Data acquisition devices for aircraft typically include communication devices such as transceivers, PES satellites, etc., navigation devices such as primary radars, secondary radars, etc., navigation devices such as directionless beacons, rangefinders, etc., and meteorological devices such as automated weather stations, ceilometers, etc. The raw data collected by the equipment is collected by a recording system such as a recorder and the like, and is usually further used in a message form through analysis and processing.
The purpose of monitoring the change of the data is to capture the change of the data source in time so as to trigger the subsequent processing flow. In particular, one or more data items of multiple data sources may be monitored simultaneously, with subsequent processes being triggered only when a data item change is detected.
In some embodiments of the present application, the plurality of data may be polled according to the following method. As shown in fig. 3, in an embodiment of the present application, fig. 3 shows a flow diagram for uninterrupted monitoring of changes to multiple data sources. As shown in fig. 3, a plurality of processes polls a plurality of data sources in parallel (in the figure, the curves represent the parallel processes, and the horizontal lines where the curved arrows meet represent the synchronous operation of the processes). For each data source, the current data item is extracted and compared to the historical data items to determine if the data item has changed. The main purpose of data item change judgment is to reduce data redundancy and improve processing performance.
Changes to data items are determined by the update policy. For example, in some embodiments of the present application, for a certain data item, the following update policy may be specified: and only when the difference value between the value of the data item extracted at this time and the historical average value exceeds a certain threshold value, judging that the data item is changed. The establishment of the update strategy is determined by the characteristics of the data items and the knowledge extraction task in the face of. For example, the flying height of an aircraft may be measured by different sensors; the barometric altitude is the altitude measured by a barometer, depending on factors such as weather, while the geographic altitude is determined by a GNSS (Global Navigation Satellite System) sensor. Due to different characteristics of the sensors, the measured values of different sensors may be different, and the measured values of two adjacent sensors of the same sensor may deviate from the actual values. When the data are actually used, the updating strategy needs to be made according to the target of the knowledge extraction task by taking the error factor of the measurement into consideration. The updating strategy can be formulated according to business requirements.
Step S220: and for the changed data source, extracting entities and relations thereof in the data source, associating the entities by using the relations, and finally forming a plurality of knowledge maps corresponding to the data source.
According to the data type provided by the data source, the method and the device mainly aim at extracting the structured data and the semi-structured data. In some embodiments of the present application, the primary method of extracting structured data is direct mapping; extracting semi-structured data mainly uses template-based methods.
For example, a table in a relational database is a type of structured data. The locally collected ADS-B data is usually stored in a database, and a direct mapping method can be adopted when extraction is performed. Table 1 lists partial fields of ADS-B data, corresponding exemplary values, and their meanings.
TABLE 1
Field(s) Example values Means of Field(s) Example values Means of
time 1590364810 Time stamp velocity 130.9206917 Speed of flight to ground
icao24 7c01c2 ICAO 24-bit aircraft address heading 27.37056267 Track angle
lat -34.50590515 Latitude vertrate 0 Vertical navigational speed
lon 149.9042433 Longitude (G) callsign AM217 Communication call sign
squawk
4067 Transponder encoding ...... ...... .........
In one embodiment of the present application, FIG. 4 shows a schematic diagram of a knowledge-graph formed from a direct mapping table 1. The knowledge graph shown in fig. 4 may be stored as the following Resource Description Framework (RDF) data:
Figure BDA0003229142180000081
the above RDF data is stored using a Turtle syntax, where exam is an abbreviation for Uniform Resource Identifier (URI) in the example below: http:// ads-b. example #.
In fig. 4, a portion in a dashed box shows a value attribute (data property) used. The boxes in the knowledge-graph shown in fig. 4 represent ontological classes, the gray ovals represent entities, the white ovals represent literal quantities, and the connecting lines with arrows represent relationships between entities or between entities and literal quantities (corresponding to the above-mentioned value attributes). Here 7c01c2 is an example of a body class airframe, representing an Aircraft with an ICAO24 of 7c01c 2. The entity is associated with other literal quantities using value attributes.
And extracting the semi-structured data by adopting a template method. Taking the extraction of the airframes.org as an example, the web page can be regarded as a kind of semi-structured data, and querying the ICAO24(7c01c2) in the example on the airframes.org can obtain information such as the manufacturer (manufacturer), the model (airplane model), the type (see the ICAO 8643 document), and the like of the airplane. The corresponding page source code is:
Figure BDA0003229142180000091
parts of the content are omitted from the ellipses for the sake of brevity. In some embodiments of the present application, one implementation of extracting semi-structured data using a template approach is to use a regular expression (regular expression). For example, the regular expression is matched with target data for multiple times, field names and corresponding values thereof are analyzed through a capture group, entities (or word sizes) are established by using the values, and the field names are used as relationships between the entities (or relationships between the entities and the word sizes).
In this example, the regular expressions for extracting field names and the regular expressions for extracting corresponding data values are:
<th[^>]*>([^<]+)</th>
<td[^>]*>(?:<[^>]+>)*([^<>]+)(?:<[^>]+>)*</td>
by matching the regular expressions with the webpage source codes for multiple times and analyzing a first capture group (corresponding to the matched content in the first bracket of each regular expression), the required data can be extracted. In this example, the regular expressions described above may be referred to as templates from which web page data is extracted. After the required data is extracted, the value corresponding to the field name can be used as the literal quantity, the field name can be used as the attribute, and the related literal quantity can be associated with the entity named 7c01c2 (named by ICAO24 value) in FIG. 4.
In some embodiments of the present application, the specific extraction techniques adopted are different according to different types of data sources, and mainly include a database access technique, a Remote Procedure Call (RPC) technique, and a web page capture technique. The data collected locally by the communication device is usually stored in a database and is extracted mainly by a database access technology. RPC is an efficient technique for creating distributed client/server applications, where a user using RPC only needs to be concerned with the details of the application, and not much with the details of network communications. For data in the form of web pages, extraction is typically performed using web crawling techniques. The general steps of the web page crawling technology are as follows: firstly, accessing a target page through an HTTP (Hypertext Transport protocol) protocol to acquire page content; and secondly, matching the acquired page content by using a predefined template, and extracting the required data. For technical methods not described above, or detailed techniques of each method, reference may be made to the prior art.
Step S230: and fusing a plurality of knowledge maps corresponding to the data sources according to the ontology model, wherein the ontology model is obtained by modeling the aviation security threat event.
In order to deal with the challenge brought by the multi-source heterogeneous data barriers to the traditional safety threat early warning method, the safety early warning scene is analyzed and summarized, and on the basis, an aviation safety threat event is modeled to construct an ontology model; and secondly, fusing a plurality of knowledge maps which are extracted in the previous steps and correspond to the data source according to the ontology model to form a fused knowledge map, and providing a knowledge base for the analysis of the security threat event. Two safety early warning scenes of 'flight rule early warning' and 'airway weather early warning' are described through examples.
In order to ensure that the flight activities are carried out safely and orderly, the flight activities must comply with the flight regulations. The basic rules of flight of the people's republic of China (hereinafter referred to as "flight rules") are the military administrative rules for regulating the flight activities in the environment. The "flight rules" standardize air space management, flight control, airway and course flight, flight intervals, etc. Taking the flight interval as an example, the flight interval is to ensure a sufficient distance between two aircrafts to prevent the aircrafts from dangerously approaching and colliding with each other. The flight intervals include vertical intervals and horizontal intervals, which are further divided into longitudinal intervals and transverse intervals. The captain must fly at the prescribed flight intervals and should be permitted by the flight control authority when changes are required. The vertical interval of the airway, the flight line or the transition flight is configured according to the flight height layer. The preparation standard of the flying height layer in China is that the flying height layer is divided into height layers according to the east-west trend (determined by a true line angle), wherein the height layers are odd times of 600 towards the east and even times of 600 towards the west (see the flying height layer preparation standard described in flying rules). Cases of flight accidents resulting from violations of flight regulations are frequent. For example, the root cause of the air crash of the Nanjing university school yard is that flight crew do not strictly follow the operation rules of the takeoff model; as another example, one of the direct causes of an eschun crash event is an aircraft crew violating an approach procedure.
Furthermore, meteorological causes are also one of the main causes of flight accidents. In the stages of taxiing, taking off, climbing, cruising, descending, approaching, landing and the like of a flight mission, flight accidents caused by meteorological reasons account for one fourth to one third. Wherein, the flight accidents in the landing stage account for about 90 percent of the total accidents; about half of the flight accidents during the cruise phase are directly related to meteorological factors. The weather conditions affecting landing are mainly: side wind, gust, low altitude wind shear; visual range obstacles such as fog, smoke, haze, snowfall, snow blowing and the like; a sand storm; low clouds, heavy rain, thunderstorms; water accumulation, ice accumulation, snow accumulation and the like on the runway. Flight accidents caused by meteorological causes, such as the aircraft B757/2801 encountering low altitude wind shear at the kunming airport; in another example, a military aviation 6.22 crashed aircraft encountered a microburst.
The flight accident is often sudden, and the correct operation is not easy. The root cause of the operation error is the insufficient knowledge of the flight state and the flight condition, which leads to the misjudgment. However, the accident cause is often formed by the combined action of multiple factors, and the information acquired by the unit and the tower often has blind spots or redundancy, so that the control personnel can not analyze and make a decision in a short time.
In order to fuse multi-source heterogeneous information, the ontology model is constructed on the basis of analyzing and summarizing the safety early warning scene. The ontologies and ontological attributes in tables 2 and 3 abstract and summarize the relevant concepts and relationships between entities, using flight interval criteria and travel weather as examples. Specifically, the ontology may be constructed, but not limited to, based on the owl (ontology Web language) language using a project tool.
The self-body classes Aircraft, Airline, Airport, flight level and Coordinate respectively represent an Aircraft, an Airline, an Airport, a flight height layer and coordinates; condition, State and Standard are root classes of relevant conditions, relevant states and relevant standards, respectively; alert is the root class of alarms, and its subclasses include forkflightlevel Alert (forbidden height layer alarm), alteraghtlevel Alert (altered height layer alarm), and the like. Ontology properties link entities. For example, trueCourse, altitude, and flightLevel link an instance of Aircraft to the true line angle, altitude, and altitude of Aircraft flight layers, respectively; takeOffAirport links an instance of Airline to the flight line's takeoff Airport, which is an instance of Airport; context links an instance of Alert or a subclass thereof to the relevant entity for the Alert.
TABLE 2
Figure BDA0003229142180000111
Figure BDA0003229142180000121
TABLE 3
Ontology properties Explaining the meaning
trueCourse True line angle
altitude Flying height
locate Latitude and longitude
flightLevel Flight level
flFrom Flight level starting height
flTo Altitude layer end height
minHorDis Minimum lateral spacing
minLonDis Minimum longitudinal spacing
takeOffAirport Flight airport of air route
landingAirport Airline landing airport
context Alarm context
Knowledge extracted from different data sources is both relatively independent and interrelated. The process of modeling security threat events is also a process of reorganizing the relevant data. Through the fusion of entities and relations, the extracted knowledge graphs are associated together, and a knowledge base is provided for dangerous case analysis.
The main problems faced by entity and relationship fusion include concept mismatch, synonymous terms, entity redundancy, and coding format mismatch. Concept mismatch means that concepts of the same name differ in meaning. When unmatched concepts are eliminated, the crossed part of the two concept ranges can be separated, and then the two concepts are decomposed by using the crossed concepts respectively. Synonymous terms mean terms that have the same meaning but are named differently. Merging synonymous terms should map them or unify them. Entity redundancy refers to the same entity being extracted from multiple different data sources. When removing redundancy, firstly, whether the incidence relation with other entities is matched or not is judged. The mismatch of the encoding formats means that the concepts or entities use different encoding styles, such as date format, measurement units, etc. Inconsistent encoding formats may be unified by translation.
Still taking the extraction of air frames org above as an example, after receiving the broadcast message of ADS-B, the fuselage information of the aircraft can be obtained from the response page by querying ICAO24(7c01c2) in the message of air frames org. Meanwhile, the message displays that the call number (callsign) is AM 217. Typically, the call for communication marks the airline and flight number. Com, the ADS-B data, the fuselage information, the airline, the historical flight record and other information can be fused. The problems of mismatching concepts and mismatching coding formats exist in the fusion process. After grabbing the Air frames, org, the extracted airplane model (model) is "B200C King Air" and type (type) is "BE 20". Com, the extracted aircraft type (aircraft type) is "Beechcraft Super King Air 200(twin-turboprop) (BE 20)". The two are not conceptually consistent, and the latter (aircraft type) includes the former (model and type) in the range. When eliminating mismatches, the airraft type can be decomposed into type and model. After decomposition, the type of both data sources points to "BE 20", one of which can BE determined to BE redundant. The problem of synonymous terms occurs with ICAO 24. In the ADS-B message, ICAO24 bit hexadecimal "7 c01c 2"; whereas in airframes.org, ICAO24 is "7C 01C 2". Both have the same meaning but the characters have different capital and lowercase. Upper or lower case characters can be used uniformly in the fusion. In the encoding format, the three use different date formats, namely, timestamp (ADS-B), "year-month-day" (air frames.org) and "sunday-month-year time zone" (flight. When merging, the date should be converted to the same format.
The fusion method illustrated above implements entity and relationship fusion by a rule matching-based method. Due to the heterogeneity of data sources, rule matching based methods often require manual construction of rules. In order to reduce the manual workload, the example matching rules can be automatically found in an iterative mode by utilizing a rule mining technology with wider application based on a semi-supervised learning method, the quality of the matching rule set is gradually improved, and the updated rule set is utilized to search the high-quality matching pairs.
Step S240: and predicting the dangerous case of the target aircraft according to the early warning logic rule and the knowledge graph.
The knowledge map and the early warning logic rules form a knowledge base together. The step is to execute an early warning logic rule by using an inference engine on a knowledge graph to early warn dangerous cases.
In some embodiments of the present application, this step uses a Jena inference engine, and the early warning logic rules use a triplet syntax, the basic form of which is:
($subject0 predicate0$object0)->($subject1 predicate1$object1)。
the rule is a forward inference rule, and the subject, predicate and object respectively represent the subject, predicate and object of the triple; variables begin with a "$" number. The triplets to the left of the arrow are used to match existing facts in the knowledge-graph (i.e., the if portion of the rule); the triplets to the right of the arrow are used to generate new facts and add the facts to the knowledge-graph (i.e., the then portion of the rule); the newly added fact may trigger other rules, and execution of the inference rule terminates when no rule is triggered.
In addition to triplets of matches, the Jena inference engine provides functional functions (functors) for creating and accessing structured word sizes. A function is a data structure that is independent of the execution of built-in process primitives. A functional function may define a single semantic structure across multiple triples and allow rules to use this structure. The function built in the Jena inference engine comprises equal (judging whether the entities are equal or not), notEqual (judging whether the entities are unequal or not), lessThan (judging the relation of 'less than' of the two entities), noValue (judging whether the fact does not exist) and the like.
Meanwhile, the Jena inference engine supports the self-defined function. To calculate the relevant states and conditions, based on the ontology model constructed above, table 4 lists the custom function and its definitions used in the early warning logic rules. The format of the function is:
functorName(parameter1,parameter2,...)
the functorName represents a function name, and the parameter represents a parameter.
In table 4, the output parameter is represented by a parameter identified in bold, and after the corresponding function is called, the output value is bound to the output parameter. The main purpose of using the function is to fuse existing algorithms and compute indirect variables through existing facts.
TABLE 4
Figure BDA0003229142180000141
Based on the ontology model and the custom function, in the scene of "flight rule early warning", the following early warning logic rule (note starting with "#" sign) about the interval standard can be constructed.
Scene one: flight rules early warning
# forbidden height layer alarms
[ ($ plane true Course $ tc) [, # $ tc is true fairway angle
($ plane altitude $ alti), with # $ alti being the altitude of flight
calcfightlevel ($ alti, $ fl), # calculate input flying height ($ alti) in the height layer that # belongs to in the flying height layer configuration standard, and bind the calculation result to $ fl
notEqual (isstFlightLevel ($ tc, $ fl) # determines whether the flying altitude layer meets the allocation standard or not according to the true flight line angle ($ tc) # of the aircraft flight
->
($ alert rdf: type ForbidFlightLevelAlert), # generate alarm #
($ alert context $ plane) ] # associates alerts to an associated aircraft
# Change height layer alarm
[($plane rdf:type Aircraft),
($plane altitude$alti),
noValue ($ plane flight level $ fl), # height level not yet calculated
->
calcfightlevel ($ alti, $ fl), # calculates the current height level
($plane flightLevel$fl)]
[ ($ plane flight level $ fl), # high level of the previous state
($plane altitude$alti),
calcfightlevel ($ alti, $ nfl), # calculate the current height level
notEqual(isTheSameFlightLevel($fl,$nfl),true)
->
($alert rdf:type AlterFlightLevelAlert),
($alert context$nfl)]
# Cross minimum lateral Interval alarm
($planeA altitude$altiA),
($planeB altitude$altiB),
calcFlightLevel($altiA,$flA),
calcFlightLevel($altiB,$flB),
isthesamefightlevel ($ flA, $ flB), # for aircraft on the same level of altitude
($std rdf:type IntervalStandard),
($ std minHorDis $ mhd), # $ mhd is the minimum lateral spacing specified by the spacing standard
calcHorDis($planeA,$planeB,$hd),
lessThan($hd,$mhd)
->
($alert rdf:type OverstepMinHorizontalDistanceAlert),
($alert context$planeA),
($alert context$planeB)
For simplicity, the above-described warning logic rules only show forbidden height level alarms, altered height level alarms, and alarms that cross the minimum lateral separation. The early warning logic rules fuse the flight state of the aircraft and the interval standard of the flight rules. The data sources include, but are not limited to, the ADS-B system of the target aircraft, the navigation system of the target aircraft, and the Internet-based related information system. And uniformly presenting the multi-source data based on the ontology by the early warning logic rule.
For the scene of 'aeronautical meteorological early warning', the following early warning rules about the landing meteorological conditions can be constructed.
# scene two: airway weather early warning
# crosswind warning
($ plane airline) $ line), where # line is the flight line of the aircraft
($ plane true Course $ tc) which is the true line angle of flight of the aircraft
($ plane locate $ loc) and # $ loc is the current coordinate of the aircraft
($ line landingAirport $ ap) indicating airline landing airport
($ ap locate $ ldLoc), # $ ldLoc denotes the coordinates of the landing airport
calcahedacordinate ($ line, $ tc, $ alti, $ loc, $ aloc), # calculate the adjacent coordinates in front of the airway $ aloc $, # calculate the adjacent coordinates in front of the airway
nearby ($ aloc, $ ldLoc), # determine if the heading is a landing coordinate
landingMeteoCondition ($ ldLoc, $ mc), # calculate weather conditions for landing
airframeType ($ plane, $ type), with $ type being aircraft type
notEqual (meetcrossswindStandard ($ type, $ ap, $ mc), true) # judges whether landing weather conditions meet crosswind criteria
->
($ alert rdf: type CrossSwindAlert) # generates crosswind alerts
($ alert context $ plane) # associates alerts with associated aircraft
The early warning logic rules further integrate meteorological data, the data sources of which include but are not limited to ground meteorological radar, other-aircraft ADS-B messages, and the data interface platform of the national meteorological information center. On the basis of fusing multi-source heterogeneous data, the method utilizes the association and reasoning capabilities of the knowledge graph, can effectively model and analyze the security threat events in complex scenes, and improves the capacity and efficiency of automatic air control.
Step S250: and sending an emergency alarm to the ground early warning terminal so that the air traffic controller can respond to the emergency alarm and send a command instruction to the target aircraft.
The early warning response means that the traffic controller responds to the dangerous case warning and sends a command instruction to the aircraft. The flow of the early warning response is shown in fig. 5. And the warning message generated by executing the warning logic rule enters a warning message queue and is sent to the ground warning terminal by the message distribution system. And the controller judges after receiving the alarm message and processes the alarm message. The inference based on the logic rules has better interpretability, and the traffic controller can know the specific conditions causing the dangerous case alarm by inquiring the inference path of the dangerous case alarm and quickly respond to the alarm.
According to the analysis and judgment of the air traffic controller on the warning message, the warning message is divided into effective warning and ineffective warning. The air traffic controller issues command instructions to the target aircraft only for valid alerts.
According to the above description, the method (as shown in fig. 2) of the present application can achieve at least the following advantages:
1. and multi-source data is comprehensively utilized, and air control capacity is improved. Aviation data is often distributed among multiple relatively independent application systems, making it difficult for related information to interact. The method and the system comprehensively utilize various data sources such as a flight monitoring system, a navigation system, a data platform and the Internet, and fuse heterogeneous information based on the knowledge map. Compared with the early warning method adopting a single data source, the method integrates historical data and real-time data, breaks barriers between multi-source heterogeneous data, and improves the capacity and efficiency of automatic air control.
2. And the modeling and analysis of the security threat event in a complex scene are supported. The safety threat scene is modeled based on the knowledge graph, the mutual connection among knowledge in related fields is constructed, mined, inferred and displayed by the knowledge graph, the safety threat events formed by comprehensive action of various factors under various scenes can be effectively modeled and analyzed, and the events threatening the safety of the aircraft are inferred and predicted on the basis.
3. And the correlation mining and analysis efficiency of the aviation data is improved in a graph-oriented form. A knowledge graph is a technical method for describing the association between knowledge and modeling world everything by using a graph model. The knowledge graph enhances the association between data in a graph-oriented form, and is favorable for more intuitively carrying out association mining and analysis on the data. Compared to hard-coded algorithms, knowledge-graph based reasoning usually focuses on logical rules and does not care about the data structure of the algorithm, and is therefore more flexible and easier to use.
Optionally, the method shown in fig. 1 or fig. 2 further comprises a knowledge correction step. In order to continuously improve the accuracy of the prediction, in an embodiment of the present application, fig. 5 shows a schematic flow chart of the warning response and the knowledge base correction. According to the processing condition of the alarm responding to the dangerous case, the technicians in the field revise the existing knowledge graph and the early warning logic rules:
1. for effective alarm, establishing a copy in an alarm history database for the alarm message and the associated knowledge graph, and using the copy as a basis for judging whether the knowledge correction is correct;
2. and for invalid alarms, performing knowledge fusion correction and knowledge base correction, executing the correction and establishing a copy in an alarm history database only when the determined valid alarms are not influenced and new invalid alarms are not generated, and rejecting the correction if the correction is not influenced.
The purpose of knowledge correction is to perfect the existing knowledge map and the early warning logic rules. As shown in fig. 5, for an invalid alarm, knowledge fusion correction is performed first, and finally, knowledge base correction is performed. The knowledge fusion correction is to improve the extraction and fusion of knowledge and radically reduce the failure rate of the extraction and fusion of knowledge; the knowledge base correction is to perfect the existing knowledge map and the early warning logic rules on the basis of knowledge fusion correction.
In order to guarantee the correctness of knowledge correction, the basis for judging the feasible correction is as follows: the determined valid alarms are not affected and new invalid alarms are not generated. Because the alarm history database stores data copies related to valid alarms, determining whether a modification is feasible can be performed by the following steps:
1. analyzing the invalid alarm, and executing knowledge fusion correction and knowledge base correction on the data copy;
2. executing the corrected early warning logic rules on the corrected knowledge graph;
3. comparing the warning message set S generated after executing the early warning logic rule with the effective warning message set S' judged in the data copy only when
Figure BDA0003229142180000191
And when the S does not contain the invalid alarm, judging that the item of correction is feasible, otherwise, judging that the item of correction is not feasible.
After the feasible correction items are executed, and then the dangerous case prediction is carried out, the corrected knowledge graph and the logic early warning rule are adopted.
The early warning response and the knowledge correction are based on the visualization technology of the knowledge graph, and work in a man-machine cooperation mode. In the early warning response step, a controller uses a human-computer interface to interact with a safety early warning system; in the knowledge correction step, the domain expert perfects the knowledge base using a computer-aided expert system.
In an embodiment of the present application, fig. 6 shows a schematic structural diagram of an aircraft safety precaution device, where the device 600 includes:
a monitoring unit 610, configured to monitor, without interruption, a change situation of a plurality of heterogeneous data sources;
an extracting unit 620, configured to extract, for a changed data source, entities and relationships thereof in the data source, associate the entities using the relationships, and finally form a plurality of knowledge maps corresponding to the data source;
the fusion unit 630 is configured to fuse a plurality of knowledge maps corresponding to the data sources according to an ontology model, where the ontology model is obtained by modeling an aviation security threat event;
an emergency prediction unit 640, configured to predict an emergency of the target aircraft according to an early warning logic rule and the knowledge graph;
and the alarm response unit 650 is configured to send an emergency alarm to the ground early warning terminal, so that the air traffic controller responds to the emergency alarm and sends a command instruction to the target aircraft.
In some embodiments of the present application, in the above apparatus, the monitoring unit 610 is configured to poll multiple data sources in parallel at preset time intervals, and for each data source, extract a current data item and compare the current data item with a historically extracted data item, if the current data item does not satisfy the update policy, continue polling the data sources, and if the current data item of a certain data source satisfies the update policy, determine that the data source is changed;
wherein the plurality of heterogeneous data sources comprise at least two of a broadcast type automatic correlation monitoring system of the aircraft, a weather testing system of the aircraft, a national weather information center weather big data interface service platform, a global real-time flight information platform and a global flight trajectory real-time tracking platform.
Optionally, in the above method, when the data source is structured data, a direct mapping method is used to extract entities and their relationships in the data source;
and when the data source is semi-structured data, extracting entities and the relation thereof in the data source by adopting a template-based method.
In some embodiments of the present application, in the above apparatus, the extracting unit 620 is configured to model the aviation security threat event, and obtain an ontology class and an ontology attribute of the ontology model; fusing a plurality of knowledge maps corresponding to the data source according to the ontology class and the ontology attribute to obtain a fused knowledge map; aiming at the problems of concept mismatching, synonymous terms, entity redundancy or coding format mismatching and the like when a plurality of knowledge maps are fused, a rule matching-based method is used for fusing entities and relations so as to obtain a fused knowledge map.
In some embodiments of the present application, in the above apparatus, the dangerous case prediction unit 640 is configured to generate zero, one or more dangerous case warning messages after the early warning logic rule is executed on the knowledge graph by the inference engine.
In some embodiments of the present application, the apparatus further comprises: and the correcting unit is used for performing knowledge correction on the existing knowledge graph and the early warning logic rule according to the processing condition of responding the dangerous case alarm.
In some embodiments of the present application, the apparatus further comprises: the correcting unit is used for establishing a copy for the alarm-in-danger message and the associated knowledge graph in an alarm historical database for effective alarm-in-danger and used as a basis for judging whether the knowledge correction is correct or not; and performing knowledge fusion correction and knowledge base correction on invalid dangerous case alarms, executing the correction and establishing a copy in an alarm history database only when the judged valid alarms are not influenced and new invalid alarms are not generated, and rejecting the correction if the correction is not influenced.
It can be understood that the above described aircraft safety precaution device and system can implement each step of the aircraft safety precaution method in the foregoing embodiments, and the relevant explanations regarding the aircraft safety precaution method are applicable to the aircraft safety precaution device and system, and are not described herein again.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 7, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 7, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form the aircraft safety early warning device on a logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
continuously monitoring the change condition of a plurality of heterogeneous data sources;
for the changed data source, extracting entities and relations thereof in the data source, and associating the entities by using the relations to form a plurality of knowledge maps corresponding to the data source;
fusing a plurality of knowledge maps corresponding to the data source according to the ontology model, wherein the ontology model is obtained by modeling according to the aviation security threat event;
predicting the dangerous case of the target aircraft according to early warning logic rules and the knowledge graph;
and sending an emergency alarm to a ground early warning terminal so that an air traffic controller responds to the emergency alarm and sends a command instruction to the target aircraft.
The method executed by the aircraft safety precaution device disclosed in the embodiment of fig. 6 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method executed by the aircraft safety warning device in fig. 6, and implement the functions of the aircraft safety warning device in the embodiment shown in fig. 6, which are not described herein again in this embodiment of the present application.
An embodiment of the present application further provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the method performed by the aircraft safety warning apparatus in the embodiment shown in fig. 6, and specifically to perform:
continuously monitoring the change condition of a plurality of heterogeneous data sources;
for the changed data source, extracting entities and relations thereof in the data source, and associating the entities by using the relations to form a plurality of knowledge maps corresponding to the data source;
fusing a plurality of knowledge maps corresponding to the data source according to the ontology model, wherein the ontology model is obtained by modeling according to the aviation security threat event;
predicting the dangerous case of the target aircraft according to early warning logic rules and the knowledge graph;
and sending an emergency alarm to a ground early warning terminal so that an air traffic controller responds to the emergency alarm and sends a command instruction to the target aircraft.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (10)

1. An aircraft safety precaution method, comprising:
continuously monitoring the change condition of a plurality of heterogeneous data sources;
for the changed data source, extracting entities and relations thereof in the data source, and associating the entities by using the relations to form a plurality of knowledge maps corresponding to the data source;
fusing a plurality of knowledge maps corresponding to the data source according to the ontology model, wherein the ontology model is obtained by modeling according to the aviation security threat event;
predicting the dangerous case of the target aircraft according to early warning logic rules and the knowledge graph;
and sending an emergency alarm to a ground early warning terminal so that an air traffic controller responds to the emergency alarm and sends a command instruction to the target aircraft.
2. The method of claim 1, wherein said continuously monitoring changes to a plurality of disparate data sources comprises:
polling a plurality of data sources in parallel according to a preset time interval, extracting a current data item and comparing the current data item with a historically extracted data item for each data source, continuing polling the data sources if the current data item does not meet an updating strategy, and determining that the data source is changed if the current data item of a certain data source meets the updating strategy;
wherein the plurality of heterogeneous data sources comprise at least two of a broadcast type automatic correlation monitoring system of the aircraft, a weather testing system of the aircraft, a national weather information center weather big data interface service platform, a global real-time flight information platform and a global flight trajectory real-time tracking platform.
3. The method of claim 1,
when the data source is structured data, extracting entities and relationships thereof in the data source by adopting a direct mapping method;
and when the data source is semi-structured data, extracting entities and the relation thereof in the data source by adopting a template-based method.
4. The method of claim 1, wherein fusing the plurality of knowledge-graphs corresponding to the data sources according to the ontology model comprises:
modeling an aviation security threat event to obtain an ontology class and an ontology attribute of an ontology model;
fusing a plurality of knowledge maps corresponding to the data source according to the ontology class and the ontology attribute to obtain a fused knowledge map;
aiming at the problems of concept mismatching, synonymous terms, entity redundancy or unmatched coding formats when a plurality of knowledge maps are fused, a rule matching-based method is used for fusing entities and relationships to obtain a fused knowledge map.
5. The method of claim 1, wherein predicting the risk of the target aircraft based on early warning logic rules and the knowledge-graph comprises:
the early warning logic rules are executed on the knowledge graph by the inference engine;
and generating zero or one or more dangerous case alarm messages after executing the early warning logic rules.
6. The method according to claim 1, characterized in that the method further comprises the steps of:
and performing knowledge correction on the existing knowledge graph and the early warning logic rule according to the processing condition of the response emergency alarm.
7. The method of claim 6, wherein the modifying knowledge of the existing knowledge-graph and pre-alarm logic rules based on the handling of the response alarm comprises:
for effective alarm against dangerous case, establishing a copy in an alarm history database for the alarm message against dangerous case and the associated knowledge graph, and using the copy as a basis for judging whether the knowledge correction is correct;
and performing knowledge fusion correction and knowledge base correction on invalid dangerous case alarms, executing the correction and establishing a copy in an alarm history database only when the judged valid alarms are not influenced and new invalid alarms are not generated, and rejecting the correction if the correction is not influenced.
8. An aircraft safety precaution device, characterized in that the device includes:
the monitoring unit is used for continuously monitoring the change conditions of a plurality of heterogeneous data sources;
the extraction unit is used for extracting entities and relations thereof in the data source for the changed data source, and associating the entities by using the relations to form a plurality of knowledge maps corresponding to the data source;
the fusion unit is used for fusing a plurality of knowledge maps corresponding to the data source according to the ontology model, wherein the ontology model is obtained by modeling the aviation security threat event;
the dangerous case prediction unit is used for predicting the dangerous case of the target aircraft according to an early warning logic rule and the knowledge graph;
and the alarm response unit is used for sending an emergency alarm to the ground early warning terminal so that an air traffic controller can respond to the emergency alarm and send a command instruction to the target aircraft.
9. The apparatus of claim 8, further comprising: and the correcting unit is used for performing knowledge correction on the existing knowledge graph and the early warning logic rule according to the processing condition of responding the dangerous case alarm.
10. An aircraft safety precaution system, the system comprising: ground early warning terminal and the aircraft safety early warning device of claim 8 or 9, the dangerous case warning message generated by the aircraft safety early warning device is put into a warning message queue of a message distribution system, and is sent to the ground early warning terminal through the message distribution system.
CN202110981104.5A 2021-08-25 2021-08-25 Aircraft safety early warning method, device and system Active CN113626616B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110981104.5A CN113626616B (en) 2021-08-25 2021-08-25 Aircraft safety early warning method, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110981104.5A CN113626616B (en) 2021-08-25 2021-08-25 Aircraft safety early warning method, device and system

Publications (2)

Publication Number Publication Date
CN113626616A true CN113626616A (en) 2021-11-09
CN113626616B CN113626616B (en) 2024-03-12

Family

ID=78387650

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110981104.5A Active CN113626616B (en) 2021-08-25 2021-08-25 Aircraft safety early warning method, device and system

Country Status (1)

Country Link
CN (1) CN113626616B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115357911A (en) * 2022-10-24 2022-11-18 中国人民解放军国防科技大学 Method for establishing security threat model of satellite navigation system
CN116611581A (en) * 2023-07-14 2023-08-18 中国气象局公共气象服务中心(国家预警信息发布中心) Method for predicting influence of weather on airport terminal area based on knowledge graph
CN117192373A (en) * 2023-08-08 2023-12-08 浙江凌骁能源科技有限公司 Power battery fault analysis method, device, computer equipment and storage medium
CN117273478A (en) * 2023-08-21 2023-12-22 中国民航科学技术研究院 Alarm handling decision method, system and storage medium for fusing rules and cases
CN117436768A (en) * 2023-12-19 2024-01-23 湖南三湘银行股份有限公司 Unified supervision index method based on data management
CN117907242A (en) * 2024-03-15 2024-04-19 贵州省第一测绘院(贵州省北斗导航位置服务中心) Homeland mapping method, system and storage medium based on dynamic remote sensing technology

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018086761A1 (en) * 2016-11-10 2018-05-17 Rowanalytics Ltd Control apparatus and method for processing data inputs in computing devices therefore
CN110619052A (en) * 2019-08-29 2019-12-27 中国电子科技集团公司第二十八研究所 Knowledge graph-based battlefield situation sensing method
CN111553467A (en) * 2020-04-30 2020-08-18 陈永聪 Method for realizing general artificial intelligence
CN111882927A (en) * 2020-07-03 2020-11-03 中国民用航空总局第二研究所 1090ES link ADS-B technology-based command operation management system and method
CN112307217A (en) * 2020-09-16 2021-02-02 北京中兵数字科技集团有限公司 Knowledge graph model construction method and device, and storage medium
CN112804079A (en) * 2020-12-10 2021-05-14 北京浪潮数据技术有限公司 Cloud computing platform alarm analysis method, device, equipment and storage medium
CN113157916A (en) * 2021-03-10 2021-07-23 南京航空航天大学 Civil aviation emergency extraction method based on deep learning
CN113255916A (en) * 2021-05-31 2021-08-13 成都卡莱博尔信息技术股份有限公司 Using method of combat knowledge system and combat decision auxiliary method

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018086761A1 (en) * 2016-11-10 2018-05-17 Rowanalytics Ltd Control apparatus and method for processing data inputs in computing devices therefore
CN110619052A (en) * 2019-08-29 2019-12-27 中国电子科技集团公司第二十八研究所 Knowledge graph-based battlefield situation sensing method
CN111553467A (en) * 2020-04-30 2020-08-18 陈永聪 Method for realizing general artificial intelligence
CN111882927A (en) * 2020-07-03 2020-11-03 中国民用航空总局第二研究所 1090ES link ADS-B technology-based command operation management system and method
CN112307217A (en) * 2020-09-16 2021-02-02 北京中兵数字科技集团有限公司 Knowledge graph model construction method and device, and storage medium
CN112804079A (en) * 2020-12-10 2021-05-14 北京浪潮数据技术有限公司 Cloud computing platform alarm analysis method, device, equipment and storage medium
CN113157916A (en) * 2021-03-10 2021-07-23 南京航空航天大学 Civil aviation emergency extraction method based on deep learning
CN113255916A (en) * 2021-05-31 2021-08-13 成都卡莱博尔信息技术股份有限公司 Using method of combat knowledge system and combat decision auxiliary method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
QIAN ZHAO等: "construction and application research of knowledge graph in aviation risk field", MATEC WEB OF CONFERENCES, pages 1 - 6 *
付雨萌;程瑾;罗准辰;王晓云;: "基于本体的军事活动事件知识建模研究", 中华医学图书情报杂志, vol. 29, no. 03, pages 47 - 52 *
齐小谦;张睿;司召峰;王炳翮;夏丛亮;: "基于知识图谱的直升机飞行指挥模型研究", 无线电工程, vol. 49, no. 01, pages 6 - 10 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115357911A (en) * 2022-10-24 2022-11-18 中国人民解放军国防科技大学 Method for establishing security threat model of satellite navigation system
CN116611581A (en) * 2023-07-14 2023-08-18 中国气象局公共气象服务中心(国家预警信息发布中心) Method for predicting influence of weather on airport terminal area based on knowledge graph
CN117192373A (en) * 2023-08-08 2023-12-08 浙江凌骁能源科技有限公司 Power battery fault analysis method, device, computer equipment and storage medium
CN117192373B (en) * 2023-08-08 2024-05-07 浙江凌骁能源科技有限公司 Power battery fault analysis method, device, computer equipment and storage medium
CN117273478A (en) * 2023-08-21 2023-12-22 中国民航科学技术研究院 Alarm handling decision method, system and storage medium for fusing rules and cases
CN117273478B (en) * 2023-08-21 2024-04-12 中国民航科学技术研究院 Alarm handling decision method and system integrating rules and cases
CN117436768A (en) * 2023-12-19 2024-01-23 湖南三湘银行股份有限公司 Unified supervision index method based on data management
CN117907242A (en) * 2024-03-15 2024-04-19 贵州省第一测绘院(贵州省北斗导航位置服务中心) Homeland mapping method, system and storage medium based on dynamic remote sensing technology

Also Published As

Publication number Publication date
CN113626616B (en) 2024-03-12

Similar Documents

Publication Publication Date Title
CN113626616B (en) Aircraft safety early warning method, device and system
Williams Using random forests to diagnose aviation turbulence
US8200377B2 (en) System for securing an aircraft flight plan
US11501039B2 (en) Optimizing aircraft flows at airports using data driven predicted capabilities
EP3367137B1 (en) Method of gathering and distrubting critical weather event information
CN108230756A (en) To the management of the notice of pilot
US10089886B2 (en) Vehicle decision support system
US8744747B1 (en) Environmental waypoint insertion
CN111123966B (en) Method for judging flight phase based on airborne ground proximity warning system
US11688291B2 (en) Cockpit display systems and methods for displaying taxiing route on airport moving map
Blasch et al. Uncertainty ontology for veracity and relevance
Ostroumov et al. Risk of mid-air collision estimation using minimum spanning tree of air traffic graph.
CN117198095A (en) Wisdom air trip distributed traffic management system
EP3447750B1 (en) Method and system for real-time validation of an operational flight path for an aircraft
US20190122566A1 (en) Method for securing a provisional itinerary for an aircraft, corresponding system and computer program
Palacios et al. Neural network models to detect airplane near-collision situations
Insaurralde et al. Cognitive Decision Support System for Avionics Analytics
Zhuge et al. Aircraft Ground Taxiing Deduction and Conflict Early Warning Method Based on Control Command Information
Payan et al. Review of proactive safety metrics for rotorcraft operations and improvements using model-based parameter synthesis and data fusion
CN205961178U (en) Low -altitude surveillance and management service system
US11830370B2 (en) Methods, systems, and apparatuses for computation and annunciation of Mach tuck
Qamar et al. Framework for Mid-Air Traffic Collision Detection Using Data Analytics
Ge et al. Security assessment algorithm of navigation control system based on big data
Londner et al. Bayesian network model of pilot response to collision avoidance system resolution advisories
EP4141842A1 (en) Methods, systems, and apparatuses for computation and annunciation of mach tuck

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