CN116205584A - Civil aviation event association method based on unified space-time coding - Google Patents
Civil aviation event association method based on unified space-time coding Download PDFInfo
- Publication number
- CN116205584A CN116205584A CN202211463053.8A CN202211463053A CN116205584A CN 116205584 A CN116205584 A CN 116205584A CN 202211463053 A CN202211463053 A CN 202211463053A CN 116205584 A CN116205584 A CN 116205584A
- Authority
- CN
- China
- Prior art keywords
- coding
- event
- time
- space
- code
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 95
- 238000000926 separation method Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 63
- 238000000605 extraction Methods 0.000 claims description 29
- 238000010276 construction Methods 0.000 claims description 9
- 230000014509 gene expression Effects 0.000 claims description 9
- 230000008520 organization Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000007499 fusion processing Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 10
- 238000010219 correlation analysis Methods 0.000 abstract description 5
- 238000013144 data compression Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000010006 flight Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- JIPVGERXYWGOOY-UHFFFAOYSA-N (2-methoxyphenyl) pentanoate Chemical compound CCCCC(=O)OC1=CC=CC=C1OC JIPVGERXYWGOOY-UHFFFAOYSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 231100000279 safety data Toxicity 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000007794 visualization technique Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/174—Redundancy elimination performed by the file system
- G06F16/1744—Redundancy elimination performed by the file system using compression, e.g. sparse files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/387—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/606—Protecting data by securing the transmission between two devices or processes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6227—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database where protection concerns the structure of data, e.g. records, types, queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Bioethics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a civil aviation event association method based on unified space-time coding, which comprises the following steps of S1: and (3) formulating a coding standard: the method comprises the steps of carrying out classification grading and each grade of coding length specification on key elements of 'objects, time, places, attributes and events' in aviation events, carrying out grading retrieval and management by a user, setting coding scheme, including setting of grading, grading and code length, and giving a basic coding form; step S2: constructing an event map: combining the aviation background and the automatic coding flow requirement, step S3: structured codec: utilizing a multi-group relation to carry out automatic coding work, specifically dividing the coding grade into different stages, and separating the grades by using '/' separation; the method has the advantages of data standardization, data compression, data encryption, automation, efficient retrieval and space-time correlation analysis.
Description
Technical Field
The invention relates to the field of civil aviation technology/computer coding, in particular to a civil aviation event correlation method based on unified space-time coding.
Background
The shipping operation safety comprises front-end product safety, safety of all guarantee links in the operation process, investigation and emergency treatment after accidents and government safety supervision. The related data includes QAR data, sensor data, fault cases, maintenance records, unsafe event reports, voyage intelligence, legal regulations, and the like. The civil aviation operation safety is influenced by environment, operation conditions, maintenance conditions, degradation failure of each component and the like, the safety operation randomness is strong, multisource safety data are effectively fused, dynamically interacted and cooperated, so that the hidden danger is timely eliminated for timely finding out the operation safety risk, the aim of cooperative optimization for guaranteeing the continuous safety of civil aviation operation and reducing the operation cost is achieved, and the problem that the civil aviation needs to be solved in the operation process is important in application value.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides a civil aviation event correlation method based on unified space-time coding.
The technical scheme adopted by the invention is that the method comprises the following steps:
step S1: and (3) formulating a coding standard: the method comprises the steps that classification orders and coding lengths of all levels are designated for key elements of 'objects, time, places, attributes and events' in aviation events, classified retrieval and management are carried out for users, coding scheme setting comprises setting of the orders, the orders and the code length, basic coding forms are given, and a conversion mode of codes corresponding to specific information is not involved;
step S2: constructing an event map: combining the aviation technical background and the automatic coding flow demand, referring to a construction strategy of a knowledge graph to strengthen the concept of an event graph, wherein the event graph is a knowledge graph with a specific structure, which is close to a tree structure taking the event flow as a clue and taking space-time positions as branches;
step S3: structured codec: the multi-element relation is used for carrying out automatic coding work, and the coding steps are divided into different stages according to the coding steps, and the steps are separated by using '/' separation.
Further, the number of the segments refers to whether the whole code contains structural loops or not, whether the whole code has specified loop times or not, and the segments are in a vertical structure, so as to distinguish a plurality of processes in an event, therefore, the number of the final segments is equal to the total number of the processes, the length of the final segments is not fixed, and all the process codes of the whole event can be aggregated into a whole long code, or each independent process code can be a short code.
Further, the hierarchy is divided into a plurality of segments in the same structure, whether unnecessary filling items exist or not, the hierarchy presents a transverse structure and is fixed into 3 segments, wherein the third segment is divided into attribute codes and relation codes according to different conditions, and each segment is necessary to be filled.
Further, the code length is the number of bits of each level of coding, is an indefinite length, and floats according to the actual original information amount.
Further, the constructing an event map includes:
step S2.1: and (3) entity construction: the key information worth being concerned in all the original data takes the event as an associated primary key and time as an associated sequence, and people, things and conditions are bound on places to form a complete entity model;
step S2.2: data preprocessing: a corresponding processing strategy is made by combining the data source and the data type;
step S2.3: object extraction: the object extraction is a process of finding out entities, space-time positions, relations and attributes from the sea most text information, so that the object extraction can be divided into four processes of entity extraction, space-time position extraction, relation extraction and attribute extraction;
step S2.4: element fusion: the relationships between elements are currently flattened, lacking hierarchy and logic; and there may be ambiguity and contradiction where matching and correction is performed;
step S2.5: event reduction: a series of knowledge elements are extracted from the original corpus through object extraction, and after a fusion process, ambiguity between entity reference items and entity objects is eliminated, so that a series of basic fact expressions are obtained.
Further, the structured codec includes:
step S3.1: event coding: the event code is unified for all the processes, and the process code is used for sequentially recording the processes in the event;
step S3.2: space-time coding: the method comprises the steps of time coding and space coding, wherein the time coding and the space coding are separated by '-' and the part in front of each part '#' respectively represents the coding format of time and space;
step S3.3: object coding: including object encodings and their properties or relationship encodings;
step S3.4: encoding output: and summarizing all the process short codes in a time or space organization form, merging the process short codes into one event long code output, realizing complete event process tracking, and supporting decoding and query analysis operations.
Further, the code output is used for selecting the content of a certain time period for coding according to actual needs in time operation or selecting a sorting mode according to needs; and selecting the content in a certain spatial range for coding according to the actual requirement in the spatial lesson.
The beneficial effects are that:
the invention provides a civil aviation event association method based on unified space-time coding, which comprises the following steps:
(1) The standardized advantage of the coding technology is that the description of event elements among different systems can be aligned, so that the data standards of different data sources can be unified, a standardized data interface is formed, and quick reading, alignment and understanding of all parties are facilitated, so that unified data knowledge is formed.
(2) Data compression is a natural advantage of encoding, which is a refined representation of important information, especially text information, where most extraneous text is discarded, and useful information is represented in smaller symbols, or further converted into binary, ascii, etc. encoding that is more suitable for computer use scenarios.
(3) The data encryption is mainly embodied in the coding transmission process, although the aviation technical field has higher data security standard, because the related information is often very widely involved in departments, the related information can be subjected to the multi-round transmission process, and partial sensitive information can have exposure risk and be transmitted through coding, so that the information can be effectively prevented from being directly decoded after being revealed.
(4) The automatic, under the addition of standard interface, not only existing data can be quickly put into gear, new data dynamically generated can also be automatically input following the interface standard, thus the data can be quickly put into storage and tabulated, and the code is formed, which will also promote the relevant business party to align to the standard when making the data standard.
(5) The method has the advantages that the efficient retrieval is realized, keywords are mostly adopted in the traditional retrieval mode based on text information, the retrieval mode is not flexible and has high omission ratio, the full information is retrieved without accessing an original database in the code retrieval mode, and the information such as attributes can be rapidly checked directly through bit operation, so that the retrieval efficiency under massive information is greatly improved.
(6) The space-time correlation analysis is the basic capability of space-time technology, and the coding system introducing space-time codes can absorb the advantages of the space-time correlation analysis, and is mainly reflected in the calculation acceleration effect of space-time grid coding in the vector grid analysis process.
Drawings
FIG. 1 is a flow chart of the general steps of the present invention;
FIG. 2 is a diagram of an event map structure according to the present invention;
FIG. 3 is a diagram of a second embodiment of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments and features of the embodiments in the present application may be combined with each other, and the present application will be further described in detail with reference to the drawings and the specific embodiments.
As shown in FIG. 1, the invention is mainly realized based on the aviation event-oriented space-time coding method, all related data parties are connected in series by constructing a unified coding standard, a standardized object association expression mode is provided by knowledge graph construction, and the whole coding and decoding process is realized automatically.
S1-establishing a coding standard: the coding standard scheme, namely a specific coding rule, is to perform classification grade and each grade of coding length specification on key elements such as 'objects, time, places, attributes, events' and the like in aviation events so as to facilitate hierarchical searching and management of users. The coding scheme setting comprises setting of the segment number, the level number and the code length, and gives a basic coding form without involving a conversion mode of the corresponding coding of specific information.
The number of the final segments is equal to the total number of the processes and is not fixed in length. The scheme considers that all process codes of the whole event can be aggregated into a whole long code, and also considers that each independent process code is a short code.
The level refers to whether unnecessary filling items exist or not in the same structure, in the scheme, the level presents a transverse structure and is fixed into 3 sections, wherein the third section is divided into attribute codes and relation codes according to different conditions, and each section is necessary to be filled.
The code length refers to the number of bits per level of coding (and per fragment thereof), which in this case is generally of indefinite length, and floats according to the actual amount of original information.
S2-constructing an event map: the concept of the event map is derived from the knowledge map, but the organization mode of the original knowledge map 'full connection' is deficient in the expression capability of the event flow, and the space-time position and the object relation change mode of the event cannot be highlighted, so that the scheme combines the aviation technical background and the requirement of the automatic coding flow, the concept of the event map is enhanced by the construction strategy of the reference knowledge map, and the knowledge map can be considered to be a knowledge map with a specific structure, which is close to a tree structure taking the event flow as a clue and taking the space-time position as a branch, as shown in fig. 2.
S2.1-entity construction: the concept of the entity is consistent with that in the knowledge graph, namely important information which is worth being concerned in all the original data mainly contains 5 aspects of 'people, places, things' and 'conditions', and the concept also corresponds to several levels in the coding. In a broad sense, there are free edges between the two, such as person-to-person, person-to-object, person-to-emotion, etc., i.e., there is a Relationship between any two, which constitutes a triplet formed by "Entity-Relationship" and "Entity". However, in order to guarantee the tree structure in the event map, the scheme uses the event as the associated primary key and time as the associated sequence, and binds the people, objects and conditions on the places to form a complete entity model, namely, a multi-element relationship is formed by 'what relationship or situation is generated by the people or the people at the moment T, the moment X and the moment Y in the process A-1 of the event A'.
S2.2-data preprocessing: the data preprocessing is a general flow of a data driving method, the construction of an event map is mainly based on a natural language processing process, the requirement of the data preprocessing is mainly to ensure the usability of a data source and the integrity and effectiveness of input information, a processing means generally does not have hard requirements, and a corresponding processing strategy is required to be made by combining the data source and the data type.
S2.3-object extraction: the object extraction is a process of finding entities, space-time positions, relationships and attributes from massive text information, and therefore, the object extraction can be divided into four processes of entity extraction, space-time position extraction, relationship extraction and attribute extraction. The raw data types of event maps are generally of three types:
structured data-such as: relational databases, link data, etc.;
semi-structured data-such as: XML, messages, encyclopedias, etc.;
unstructured data-such as: pictures, audio, video, etc.
Wherein structured data is preferably processed, a relational database is a natural relational expression that can be mapped into a solid model without extraction and fusion processes, and because its structure is fixed, the process can be fully automated after one mapping.
Unstructured data is first converted into semi-structured data by a word recognition technology, manual intervention is often needed in the process, and the processing of the semi-structured data follows the sequence:
entity extraction refers to the automatic identification of named entities, i.e., objects, such as flight numbers, device names, characters, etc., from a text dataset.
The extraction of the space-time position refers to automatically identifying time and place information such as airports, longitude and latitude, date and time from a text data set, and judging events and objects associated with the space-time position.
Relationship extraction refers to loose entity objects obtained from the above. And performing relationship matching. Mainly oriented to both single object and multi-object types, such as a tower giving instructions to flights.
Attribute extraction refers to obtaining attribute information of the entity objects, and is mainly directed to single objects, such as flight altitude falling from 7700 meters to 7300 meters.
S2.4-element fusion: the relationship between the above elements is flattened currently, and lacks hierarchy and logic; and there may be ambiguity and contradiction, so matching and correction need to be done at this step. The following steps may be subdivided:
entity disambiguation and coreference resolution: judging whether the homonymous entities in the extracted elements represent different meanings with the homonymous entities and whether the different entities represent the same meanings, and mainly merging and deleting the extracted elements.
Entity linking: after confirming the corresponding correct entity object in the extracted element, the entity designation is linked to the corresponding entity in the knowledge base, namely the flight xxxmm corresponding to the object-aircraft entity, and the name XXX corresponding to the person-crew entity. It is also necessary to determine the attribution of the reference words, such as the flight, he, etc., according to the context.
Factor reasoning: and some additional entity information can not be directly obtained or omitted from the original corpus, but is an important inquiry field of important composition or coding of event information, so that joint reasoning on attributes and relations is needed, for example, the fault of equipment is inferred according to the fact that a certain indicator light of the equipment on an airplane is lightened, and corresponding changes are generated on the attributes of corresponding equipment, the airplane and the flight. The process may be implemented based on probabilistic graph models or deep learning techniques.
S2.5-event reduction: a series of knowledge elements are extracted from the original corpus through object extraction, and after a fusion process, ambiguity between entity reference items and entity objects is eliminated, so that a series of basic fact expressions are obtained. However, the above information is not enough to restore the whole event, and a structured and networked coding system is finally required to be obtained, and the event restoration process is also required to be carried out. Mainly comprises two processes of process restoration and event reasoning.
And (3) process reduction: according to the context, judging the passing of the event, the scheme takes the space-time position of the person, the object attribute or the relation change as the break point of process switching, so that the whole event is segmented into a plurality of subprocesses, and each process corresponds to one row of codes. It is therefore necessary to identify which of the above elements have changed and which object corresponds. As a flight moves from a location a to a location B, the attribute value M changes from a to β. Thus, an exact multi-element relationship is obtained.
Event reduction: and further organizing continuous front and back processes from a plurality of data sources according to the space-time information, splicing complete event chains, and restoring a final event map structure.
S3-structured codec: the above-mentioned multi-element relation is an objective relation structure, so that it can smoothly support automatic coding operation, and is divided into the following stages according to coding grades, and the grades are separated by using '/' separation:
BJSG001-01.002/T#73618-S#837382a/edj7372%110,09,211
BJSG001-01.002/T#73618-S#837386b/edj7031-edj7372%003
s3.1-event encoding: the event code is unified for all the processes, and the process code sequentially records the processes in the event. Referring to the above example, the event code is BJSG001, the process code is 01.002, and the middle is separated by a '-'.
S3.2-space-time coding: including temporal coding and spatial coding, separated by a '-' where the parts preceding each part represent the coding format of time and space, respectively, such as unix time, geoot spatial coding, and the parts following the '#' represent the time and space information in the corresponding format.
S3.3-object coding: including object code and its attribute or relationship code, refer to the examples above:
for property changes of objects, edj7372-110, 09, 211 or edj7372-s12:211, the format being given as '-' the first edj7372 representing the object code, the second 110, 09, 211 or-s 12:211 represents what the value of three attributes is, or what the attribute becomes, respectively, and it is to be noted here that the two forms are different only in expression form depending on the attribute of the entity object, and the effect is consistent. If the object attributes are too many, the latter form can be adopted, only the s12 attribute is marked to be changed, the changed value is 211, otherwise, the real-time values of the space-time positions or the processes corresponding to all the attributes can be given according to the former form.
For the change of the relationship of the objects, the relationship is given in the form of edj7031-edj7372%003, the part before the '%' represents the object number of each object, the multiple objects are divided by the '-' and the part after the '%' represents the specific relationship or action, such as the object and the action between the objects.
S3.4-code output: and finally, summarizing all the process short codes in a time or space organization form, merging the short codes into one event long code to output, realizing complete event process tracking, supporting operations such as decoding, query analysis and the like.
Specifically, the time operation can select the content of a certain time period for coding according to the actual requirement, and can also select a sorting mode according to the requirement; and selecting the content in a certain spatial range for coding according to the actual requirement in the spatial lesson.
According to the scheme, computer coding is used as a technical base, a knowledge graph technology is used as a main means to carry out unified organization on civil aviation events, and space-time positions are embedded into coding segments, so that efficient query and space-time calculation processes taking space-time relations as clues are realized.
Space-time calculation: the space-time position is used as a key clue to carry out organization and association on the codes and the events, the event retrieval process can be accelerated based on the space-time relationship, and a standardized space-time expression visualization method is provided, and the details of the embodiment II are shown in the specification.
Knowledge graph: a knowledge graph is a data structure made up of entities, relationships, and attributes. The method can be considered as version 2.0 of a database, and based on the structure, knowledge matching can be automatically carried out from massive text information based on some knowledge fusion and reasoning means, so that the method is combined with the depth of the coding process.
Encoding and decoding: the coding does not modify the information of various elements in the event, but an efficient event expression strategy, the event information of the corresponding depth is expressed by data as few as possible and standard, specifically, different original information corresponds to different coding strategies, and the decoding is the inverse process of the coding.
Example 1-specific procedure
Original corpus example: on day 22 of 12 2021, in the XX district, the A aviation B2222 crew flights remain at a height of 3300 meters, and the B aviation A1111 crew flights remain at a height of 3000 meters. After the controller sends out an error instruction, the A aviation B2222 unit flight unit listens to the instruction by mistake, the controller does not correct the unit and recollects, the flight descends from the height 3300 m, the flight of the B aviation A1111 unit is smaller than a specified interval, the two planes trigger TCASRA alarm and carry out emergency avoidance, and the RA alarm lasts for 12-13 seconds. After the alarm is released, the controller commands the two flights to safely land.
S1 coding scheme: following the foregoing encoding structure
S2.1 entity construction:
large class of entities | Entity subclass |
Human body | Staff member |
Article (B) | Avionics department |
Article (B) | Alarm system |
S2.2, preprocessing data: the corpus is already processed information, not illustrated here
S2.3, object extraction:
s2.4 element fusion:
s2.5 event reduction:
s3.1-3.3 coding:
s3.4, coding and outputting, namely, outputting all the codes according to a default time sequence:
short code:
HDTM22143-1.1/T#WXG-H#670C/A1111%HG:3000,ST:1
HDTM22143-1.2/T#WXG-H#670C/B2222%HG:3300,ST:1
HDTM22143-2.1/T#WXG-H#670C/KG-B2222%0054
HDTM22143-2.2/T#WXG-H#670C/B2222-KG%0073
HDTM22143-2.3/T#WXG-H#670C/KG-B2222%0193
HDTM22143-2.3/T#WXG-H#670C/B2222%H12
HDTM22143-3.1/T#WXG-H#670C/A1111%GJ:TCASRA
HDTM22143-3.2/T#WXG-H#670C/B2222%GJ:TCASRA
HDTM22143-3.3/T#WXG-H#670C/A1111%H02
HDTM22143-3.4/T#WXG-H#670C/B2222%H02
HDTM22143-3.5/T#WXG-H#670C/A1111%GJO:TCASRA
HDTM22143-3.6/T#WXG-H#670C/B2222%GJO:TCASRA
HDTM22143-4.1/T#WXG-H#670C/KG-B2222%0004
HDTM22143-4.2/T#WXG-H#670C/KG-A1111%0004
HDTM22143-5.1T#WXG-H#670C/A1111%ST:0
HDTM22143-5.2/T#WXG-H#670C/B2222%ST:0
event long code:
HDTM22143——
″″
1.1/T#WXG-H#670C/A1111%HG:3000,ST:1
1.2/T#WXG-H#670C/B2222%HG:3300,ST:1
2.1/T#WXG-H#670C/KG-B2222%0054
2.2/T#WXG-H#670C/B2222-KG%0073
2.3/T#WXG-H#670C/KG-B2222%0193
2.3/T#WXG-H#670C/B2222%H12
3.1/T#WXG-H#670C/A1111%GJ:TCASRA
3.2/T#WXG-H#670C/B2222%GJ:TCASRA
3.3/T#WXG-H#670C/A1111%H02
3.4/T#WXG-H#670C/B2222%H02
3.5/T#WXG-H#670C/A1111%GJO:TCASRA
3.6/T#WXG-H#670C/B2222%GJO:TCASRA
4.1/T#WXG-H#670C/KG-B2222%0004
4.2/T#WXG-H#670C/KG-A1111%0004
5.1/T#WXG-H#670C/A1111%ST:0
5.2/T#WXG-H#670C/B2222%ST:0
″″
it should be noted that the above codes are only for illustration of the flow, and are not related to the actual code approval,
example two-specific application procedure
As shown in fig. 3, the left and right parts are divided into 17 and 18 standard grids, and coding grid coding is given according to Geosot coding (national standard), and a similar space-time coding technology is adopted, so that the calculation speed in the search and space query calculation process can be accelerated, and specifically:
the figure shows a path segment (arrow in the figure) of the dynamic process under 17 and 18 levels of grids, correspondingly, with 18 levels as space-time coding reference, at least 3 short codes exist in the process record due to space-time position change:
……G#JF03913F0391321……
……G#JF03913F0391322……
……G#JF03913F0391324……
when all dynamic processes under 17-level grids need to be counted, the traditional method such as keywords cannot accurately provide a query accurate means, while the GIS method needs to use GIS operation to be time-consuming, the bit operation can be directly performed by using codes, the nested 17-level grid codes are known to be JF03913F039132, all 18-level grid records under 17-level grids can be quickly obtained by querying JF03913F039132 or performing right shift on all 18-level record space-time codes by 1 bit, and the 3 records can be directly obtained.
The method provided by the invention has the following advantages:
(1) The standardized advantage of the coding technology is that the description of event elements among different systems can be aligned, so that the data standards of different data sources can be unified, a standardized data interface is formed, and quick reading, alignment and understanding of all parties are facilitated, so that unified data knowledge is formed.
(2) Data compression is a natural advantage of encoding, which is a refined representation of important information, especially text information, where most extraneous text is discarded, and useful information is represented in smaller symbols, or further converted into binary, ascii, etc. encoding that is more suitable for computer use scenarios.
(3) The data encryption is mainly embodied in the coding transmission process, although the aviation technical field has higher data security standard, because the related information is often very widely involved in departments, the related information can be subjected to the multi-round transmission process, and partial sensitive information can have exposure risk and be transmitted through coding, so that the information can be effectively prevented from being directly decoded after being revealed.
(4) The automatic, under the addition of standard interface, not only existing data can be quickly put into gear, new data dynamically generated can also be automatically input following the interface standard, thus the data can be quickly put into storage and tabulated, and the code is formed, which will also promote the relevant business party to align to the standard when making the data standard.
(5) The method has the advantages that the efficient retrieval is realized, keywords are mostly adopted in the traditional retrieval mode based on text information, the retrieval mode is not flexible and has high omission ratio, the full information is retrieved without accessing an original database in the code retrieval mode, and the information such as attributes can be rapidly checked directly through bit operation, so that the retrieval efficiency under massive information is greatly improved.
(6) The space-time correlation analysis is the basic capability of space-time technology, and the coding system introducing space-time codes can absorb the advantages of the space-time correlation analysis, and is mainly reflected in the calculation acceleration effect of space-time grid coding in the vector grid analysis process.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "disposed," "mounted," "connected," and "fixed" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art in a specific case.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. A civil aviation event association method based on unified space-time coding is characterized by comprising the following steps:
step S1: and (3) formulating a coding standard: the method comprises the steps that classification orders and coding lengths of all levels are designated for key elements of 'objects, time, places, attributes and events' in aviation events, classified retrieval and management are carried out for users, coding scheme setting comprises setting of the orders, the orders and the code length, basic coding forms are given, and a conversion mode of codes corresponding to specific information is not involved;
step S2: constructing an event map: combining the aviation technical background and the automatic coding flow demand, referring to a construction strategy of a knowledge graph to strengthen the concept of an event graph, wherein the event graph is a knowledge graph with a specific structure, which is close to a tree structure taking the event flow as a clue and taking space-time positions as branches;
step S3: structured codec: the multi-element relation is used for carrying out automatic coding work, and the coding steps are divided into different stages according to the coding steps, and the steps are separated by using '/' separation.
2. The civil aviation event association method based on unified space-time coding as claimed in claim 1, wherein the segment refers to whether the whole code contains structural loops or not, whether the whole code has a designated number of loops, and the segment presents a vertical structure in order to distinguish a plurality of processes in an event, so that the number of final segments is equal to the total number of processes, and the length of the whole process code of the whole event is not fixed, and all the process codes of the whole event can be aggregated into a whole long code, or each independent process code can be a short code.
3. The civil aviation event association method based on unified space-time coding as claimed in claim 1, wherein the hierarchy is divided into several segments in the same structure, whether unnecessary filling items exist or not, the hierarchy presents a transverse structure and is fixed into 3 segments, wherein the third segment is divided into attribute codes and relation codes according to different conditions, and each segment is necessary to be filled.
4. A civil aviation event association method based on unified space-time coding as claimed in claim 1, wherein the code length is the number of bits of each level of coding, is an indefinite length, and floats according to the actual amount of original information.
5. The civil aviation event association method based on unified space-time coding as claimed in claim 1, wherein the constructing the event map comprises:
step S2.1: and (3) entity construction: the key information worth being concerned in all the original data takes the event as an associated primary key and time as an associated sequence, and people, things and conditions are bound on places to form a complete entity model;
step S2.2: data preprocessing: a corresponding processing strategy is made by combining the data source and the data type;
step S2.3: object extraction: the object extraction is a process of finding entities, space-time positions, relations and attributes from massive text information, so that the process can be divided into four processes of entity extraction, space-time position extraction, relation extraction and attribute extraction;
step S2.4: element fusion: the relationships between elements are currently flattened, lacking hierarchy and logic; and there may be ambiguity and contradiction where matching and correction is performed;
step S2.5: event reduction: a series of knowledge elements are extracted from the original corpus through object extraction, and after a fusion process, ambiguity between entity reference items and entity objects is eliminated, so that a series of basic fact expressions are obtained.
6. The civil aviation event association method based on uniform space-time coding as claimed in claim 1, wherein the structured codec comprises:
step S3.1: event coding: the event code is unified for all the processes, and the process code is used for sequentially recording the processes in the event;
step S3.2: space-time coding: the method comprises the steps of time coding and space coding, wherein the time coding and the space coding are separated by '-' and the part in front of each part '#' respectively represents the coding format of time and space;
step S3.3: object coding: including object encodings and their properties or relationship encodings;
step S3.4: encoding output: and summarizing all the process short codes in a time or space organization form, merging the process short codes into one event long code output, realizing complete event process tracking, and supporting decoding and query analysis operations.
7. The civil aviation event association method based on unified space-time coding as claimed in claim 6, wherein the coding output is used for selecting the content of a certain time period for coding according to actual needs or selecting a sorting mode according to needs; and selecting the content in a certain spatial range for coding according to the actual requirement in the spatial lesson.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211463053.8A CN116205584B (en) | 2022-11-21 | 2022-11-21 | Civil aviation event association method based on unified space-time coding |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211463053.8A CN116205584B (en) | 2022-11-21 | 2022-11-21 | Civil aviation event association method based on unified space-time coding |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116205584A true CN116205584A (en) | 2023-06-02 |
CN116205584B CN116205584B (en) | 2023-08-22 |
Family
ID=86510187
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211463053.8A Active CN116205584B (en) | 2022-11-21 | 2022-11-21 | Civil aviation event association method based on unified space-time coding |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116205584B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109977237A (en) * | 2019-05-27 | 2019-07-05 | 南京擎盾信息科技有限公司 | A kind of dynamic law occurrence diagram spectrum construction method towards legal field |
CN113961662A (en) * | 2021-11-02 | 2022-01-21 | 贵州图智信息技术有限公司 | Place name address data fusion method based on multi-source data |
CN114218932A (en) * | 2021-11-26 | 2022-03-22 | 中国航空综合技术研究所 | Aviation fault text abstract generation method and device based on fault cause and effect map |
CN114417004A (en) * | 2021-11-10 | 2022-04-29 | 南京邮电大学 | Method, device and system for fusing knowledge graph and case graph |
CN115114409A (en) * | 2022-07-19 | 2022-09-27 | 中国民航大学 | Civil aviation unsafe event combined extraction method based on soft parameter sharing |
-
2022
- 2022-11-21 CN CN202211463053.8A patent/CN116205584B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109977237A (en) * | 2019-05-27 | 2019-07-05 | 南京擎盾信息科技有限公司 | A kind of dynamic law occurrence diagram spectrum construction method towards legal field |
CN113961662A (en) * | 2021-11-02 | 2022-01-21 | 贵州图智信息技术有限公司 | Place name address data fusion method based on multi-source data |
CN114417004A (en) * | 2021-11-10 | 2022-04-29 | 南京邮电大学 | Method, device and system for fusing knowledge graph and case graph |
CN114218932A (en) * | 2021-11-26 | 2022-03-22 | 中国航空综合技术研究所 | Aviation fault text abstract generation method and device based on fault cause and effect map |
CN115114409A (en) * | 2022-07-19 | 2022-09-27 | 中国民航大学 | Civil aviation unsafe event combined extraction method based on soft parameter sharing |
Non-Patent Citations (3)
Title |
---|
王红 等, 安全与环境学报, vol. 20, no. 2, pages 602 - 609 * |
王红 等: "航空安全事件关联分析方法研究", 安全与环境学报, vol. 20, no. 2, pages 602 - 608 * |
郭静, 万方学位论文, pages 10 - 54 * |
Also Published As
Publication number | Publication date |
---|---|
CN116205584B (en) | 2023-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111680025B (en) | Method and system for intelligently assimilating space-time information of multi-source heterogeneous data oriented to natural resources | |
Hammer et al. | Database description with SDM: A semantic database model | |
CN101799835B (en) | Ontology-driven geographic information retrieval system and method | |
CN110188979A (en) | Water industry Emergency decision generation method and device | |
CN111966746B (en) | Meteorological disaster prevention and reduction process monitoring system and monitoring method thereof | |
CN113254507B (en) | Intelligent construction and inventory method for data asset directory | |
CN114282534A (en) | Meteorological disaster event aggregation method based on element information extraction | |
CN113240046A (en) | Knowledge-based multi-mode information fusion method under visual question-answering task | |
CN116187771A (en) | Scene flood control plan management system and method based on structural decomposition | |
CN103150632B (en) | Flood control based on water conservation cloud platform is taked precautions against drought the construction method of bulletin generation system | |
CN116205584B (en) | Civil aviation event association method based on unified space-time coding | |
Halterman | Mordecai 3: A neural geoparser and event geocoder | |
Terblanche et al. | Ontology‐based employer demand management | |
Li et al. | Application of text mining techniques in railway safety supervision system | |
Elgarroussi et al. | Aconcagua: A novel spatiotemporal emotion change analysis framework | |
Panrungsri et al. | Business Intelligence Model for Disaster Management: A Case Study in Phuket, Thailand. | |
Yu et al. | An Integrated Approach for Massive Sequential Data Processing in Civil Infrastructure Operation and Maintenance | |
Bi et al. | Identifying environmental and health threats in unconventional oil and gas violations: evidence from Pennsylvania compliance reports | |
Galhardas et al. | A framework for classifying scientific metadata | |
CN117290299B (en) | Airport security management system dynamic association matching method and system and electronic equipment | |
CN115658795B (en) | Maritime business data index management method and system supporting multi-scene evaluation | |
CN117453717B (en) | Data query statement generation method, device, equipment and storage medium | |
Mu et al. | Construction of Knowledge Graph for Emergency Resources | |
Rezaei Ghahroodi et al. | Address matching using machine learning methods: An application to register-based census | |
CN116539055A (en) | Natural disaster emergency road network map service method and system |
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 |