CN109635272A - A kind of ontology interaction models construction method in air traffic control field - Google Patents
A kind of ontology interaction models construction method in air traffic control field Download PDFInfo
- Publication number
- CN109635272A CN109635272A CN201811242103.3A CN201811242103A CN109635272A CN 109635272 A CN109635272 A CN 109635272A CN 201811242103 A CN201811242103 A CN 201811242103A CN 109635272 A CN109635272 A CN 109635272A
- Authority
- CN
- China
- Prior art keywords
- concept
- ontology
- class
- blank pipe
- structured document
- 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.)
- Pending
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 17
- 238000010276 construction Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims description 24
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000012550 audit Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000008520 organization Effects 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- BYACHAOCSIPLCM-UHFFFAOYSA-N 2-[2-[bis(2-hydroxyethyl)amino]ethyl-(2-hydroxyethyl)amino]ethanol Chemical compound OCCN(CCO)CCN(CCO)CCO BYACHAOCSIPLCM-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 229910003460 diamond Inorganic materials 0.000 description 1
- 239000010432 diamond Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of ontology interaction models construction methods in air traffic control field to enumerate the common concept in blank pipe field by obtaining and analyzing blank pipe field structureization and irrelevant document；Classify to all concepts, and determines the hierarchical structure of class；The relationship between class is extracted, the attribute of ontology is constructed.The present invention proposes the sentence based on user query, Dynamic expansion ontology；And the Chinese and English dictionary of keyword is constructed, the multilingual expansion scheme of support body.
Description
Technical field
The present invention relates to a kind of buildings of the ontology interaction models in knowledge services field more particularly to air traffic control field
Method.
Background technique
Staan etc. to forefathers define carry out research summary after, it is believed that: " ontology is the formalization rule of shared conceptual model
Model explanation ", it embodies four levels of ontology:
(1) conceptual model model as obtained from taking out the related notion of some phenomenons in objective world indicates
Meaning independently of specific ambient condition.
(2) it defines used concept and has specific definition using the constraint of these concepts.
(3) Formal Ontology can be readable by a computer and handle.
(4) what is embodied in shared ontology is the knowledge approved jointly, and reflection is the concept set generally acknowledged in related fields, it
Targeted is collective rather than it is individual.
Concept is regarded as a class, and hereinafter concept and the two words of class are of equal value.Ontology is provided using the vocabulary of agreement
A set of good construction, by one it is clear and clearly in a manner of establish significant high-level language in specified term system
Adopted knowledge.To a specific field, ontology is provided more complicated using a kind of type of language abundant to resource and its attribute
Constraint condition.Compared with common classification, ontology increases semantic term for providing richer relationship in lexical terms.
Ontology is expressed usually using a kind of very strong language of logicality, therefore can be in class, attribute, realized between relationship in detail,
Significant expression, main application aspect have: for assisting interpersonal communication；For the mutual behaviour between air traffic control system
Make and communicates with each other；For universe information management system (System Wide Information Management, SWIM)
Web service discovery.
However, current blank pipe lacks unified knowledge model, lacks the standardization to domain knowledge and define, cause to same
The description of one knowledge may be different, influence user to the understanding of this knowledge and share.In relevant search information, for synonymous
Keyword not of the same name is not found completely due to actually meeting the service of user demand, and it is low to result in recall ratio；For of the same name
The service that not synonymous keyword can be not theed least concerned due to query result, so resulting in the low problem of precision ratio.Therefore,
How blank pipe ontology is accurately constructed, to improve precision and the SWIM system Web service discovery of subsequent semantics recognition
Accuracy is a technical problem to be solved urgently.
Summary of the invention
Goal of the invention: the technical problem to be solved by the present invention is to not have the ontological construction in blank pipe field for the prior art
Method provides the construction method and extended method of a kind of blank pipe domain body interaction models, has good operability and can
Scalability specifically comprises the following steps:
Step 1, the relevant document in blank pipe field is obtained；
Step 2, from concept required for extraction blank pipe domain body in the relevant document in blank pipe field；
Step 3, classify to the concept of extraction, and determine the hierarchical structure of class；
Step 4, the relationship between class is extracted, the attribute of ontology is constructed；
Step 5, based on the sentence of user query, Dynamic expansion ontology；
Step 6, the Chinese and English dictionary for constructing keyword, supports multilingual ontology.
Step 1 includes:
Step 1-1 obtains structured document, flight information, aviation information, meteorological letter including International Civil Aviation Organization's standard
Cease exchange model；
Step 1-2 obtains non-structured document, including Web service description, Web page information disclosed in blank pipe mechanism；
Step 1-3, the structured document and non-structured document of acquisition are as the relevant document in blank pipe field.
Step 2 includes:
Step 2-1, the concept of appearance is counted from structured document: structured document is xml structure, each structuring text
Shelves include two or more xml label, and each label mapping is a concept of ontology, then each structured document forms one generally
Read collection SCi, to all structured documents, more than two concept sets are formed, the concept set from n structured document is SC
=SC1∪SC2∪…∪SCn, SCnIndicate the concept set that n-th of structured document is formed；
Step 2-2 carries out participle and part-of-speech tagging to non-structured document using participle tool, removes stop words, and needle
The word segmentation result of non-structured document is counted, the frequency of occurrences is that preceding 50% word of all words is used as one by audit
Concept set UCi, the concept set from m non-structured document is UC=UC1∪UC2∪…∪UCm, UCmIndicate m-th of non-knot
The concept set that structure document is formed；
Step 2-3, concept set required for blank pipe domain body are C=SC ∪ UC.
Step 3 includes:
Blank pipe domain body is divided into disjoint class by step 3-1, when original state, each concept in blank pipe field
For a class；
Step 3-2 is based on step 3-1, calculates the similarity of all classes between any two using WordNet, obtain between class
Similarity matrix, and using spectral clustering formed N1A class；
Step 3-3 is manually N1A class name, and it is directed to this N1A class carries out the operation in step 3-2, forms N2, N3Deng
Different number, successively class up.To the last form the blank pipe domain class of a totality.These classes, shape are organized from top to bottom
At the hierarchical structure of ontology.Step 4 includes:
Step 4-1, flight information, aviation information, weather information exchange model be XML structure, itself contain information it
Between relationship.Information has corresponded to the class in ontology in step 3, and the relationship between information can then correspond between ontology class
Relationship；
Step 4-2, according to the participle of step 2-2 and part-of-speech tagging as a result, two words of statistics occur simultaneously in a document
Frequency determine between two words to return by this there may be relationship if the frequency of occurrences is related preceding 50% simultaneously
Body building person determines.
Step 5 includes:
Step 5-1 is segmented using sentence of the participle tool to user query；
Step 5-2, if the word segmentation result of the sentence of user query is present in the ontology that step 4 and step 5 construct,
Terminate；
Step 5-3 matches the word segmentation result of the sentence of user query with the concept in concept set C, if user looks into
The word segmentation result of the sentence of inquiry is not present in the body, searches for similar concept in the body according near synonym query software, searches
Rope to close concept submit as new concept and audited by ontological construction person, if audit passes through, concept set C is added in new concept
In.
Step 6 includes:
Step 6-1, construct blank pipe field Chinese and English dictionary: by the Chinese conceptual translation in concept set C at English, English is turned over
It is translated into Chinese；；
Step 6-2 is first converted into Chinese according to blank pipe field Chinese and English dictionary for English searching request, completes search
After be converted into English output.Ontology interaction models to be built.
Using the ontology interaction models of building, the blank pipe information inquiry across language is completed, the category between Ontological concept is utilized
Associated information is searched in sexual intercourse, and support universe information management (System Wide Information Management,
SWIM Web Service service discovery).
The utility model has the advantages that remarkable advantage of the present invention is:
1, ontology is constructed towards blank pipe field, data source is reliable, and ontology is practical.
2, the design of ontology hierarchical structure passes through iterative process realization, high reliablity.
3, the sentence based on user's user query extends ontology, and ontology scalability is strong.
4, multilingual extension is carried out based on Chinese and English dictionary, is supported in the case where not increasing body size multilingual.
Detailed description of the invention
The present invention is done with reference to the accompanying drawings and detailed description and is further illustrated, it is of the invention above-mentioned or
Otherwise advantage will become apparent.
Fig. 1 is ontology hierarchical structure building process schematic diagram of the invention.
Fig. 2 is Noumenon property preparation method schematic diagram of the invention.
Fig. 3 is the ontology expansion method schematic diagram of the invention based on search.
Fig. 4 is the multilingual extended method schematic diagram of ontology of the invention.
Fig. 5 is flow chart of the present invention.
Fig. 6 is the structure chart of ontology.
Fig. 7 is the schematic diagram of the application of ontology.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings and embodiments.
As shown in figure 5, the present invention provides a kind of ontology interaction models construction methods in air traffic control field, including
Obtain the relevant document in blank pipe field；Enumerate the common concept in blank pipe field；Classify to all concepts, and determines class
Hierarchical structure；The relationship between class is extracted, the attribute of ontology is constructed；Sentence based on user query, Dynamic expansion ontology；Building
The Chinese and English dictionary of keyword, supports multilingual ontology.
Blank pipe domain body interaction models are constructed firstly the need of the concept for obtaining the field.And the source of concept is blank pipe neck
The relevant document in domain.What general domain body constructed selection is non-structured text and therefrom extracts concept.And blank pipe is led
There are the data model and non-structured document of many structurings in domain.Suitable concept source is selected to help to promote the complete of ontology
Property.Data source includes: in the present invention
Structured document: the exchange models such as flight information, aviation information, weather information；
Non-structured document: Web service description disclosed in well-known blank pipe mechanism, Web page information
For above-mentioned document, concept needed for needing to extract blank pipe domain body.The present invention for structured document and
Non-structured document devises different schemes.
Structured document is generally xml structure, and each structured document includes multiple xml labels, and each label mapping is
One concept of ontology.Therefore, each structured document, which forms a concept, collects SCi.To all structured documents, formed multiple
Concept set.It therefore, is SC=SC from the concept set of n structured document1∪SC2∪…∪SCn。
Non-structured document is typically from text description information, can not be done directly the mapping to Ontological concept.This hair
Bright proposition first segments non-structured document, and carries out part-of-speech tagging.Part work can be by softwares works such as jieba participles
Tool is completed.It is counted for the word segmentation result of some non-structured document, the word more than frequency of occurrence passes through manual examination and verification conduct
One concept set UCi.Concept set from m non-structured document is UC=UC1∪UC2∪…∪UCm。
Therefore, Ontological concept integrates as C=SC ∪ UC.
There is hierarchical structure between the class and class of ontology.Hierarchical structure can pass through top-down body design and concept
Automatic classification obtains.Blank pipe domain body is divided into several disjoint classes, such as mechanism, personnel, equipment first.Ontology is general
The concept and above-mentioned class read in collection C calculate concept similarity, and concept is classified as in most like class.The calculation method of concept similarity
It can be calculated with software tools such as synonyms.Persistently classify to the concept under each classification --- calculate similarity --- return
Generic operation, until forming complete ontology hierarchical structure.Detailed process is as shown in Figure 1.
Ontology not only has class, and there are also relevant data attribute (DataProperty) and object properties
(ObjectProperty).For structured document, data attribute can be directly obtained.Object properties are disappeared by counting all interactions
The case where different objects occur simultaneously in breath, extracts both sides relation.It repeatedly appears in and thinks between the two in same message simultaneously
There are object properties relationships.Non-structured document needs to be obtained according to word segmentation result by extraction mode identical with structured document
Take data attribute and object properties.Process is as shown in Figure 2.
Ontology model needs dynamically to extend as software, to meet the needs of increasing concept.And extend ontology model
Method be usually that expert rule of thumb manually extends.The present invention proposes a kind of side being extended according to search input to ontology
Method.Since ontology is generally used for supporting search, and during searching for, user can input different query statements.Inquire language
Sentence has certain probability and word occurs not in the concept that ontology includes.At this time using the information pair of the sentence of user query
Ontology is extended.The process of extension is to carry out participle and memory mark to the sentence of user query first.Then by word with
Concept in ontology is matched.If some concept in the body, does not calculate new concept using software tools such as synonyms
With the similarity in current Ontological concept, provides classification and suggest transferring to manual examination and verification.If audit passes through, current ontology is added
In.Process is as shown in Figure 3.
Since blank pipe field is related to the interaction between multiple national different institutions, ontology is as the shared general of support interaction
Model is read, is needed support multilingual.A kind of method of multilingual extension is that all corresponding Chinese and English are defined as equivalent concepts.
The problem of the method, can generate a large amount of equivalence class after being in ontology more than concept, influence the management of ontology.The present invention mentions
Out based on the multilingual expansion scheme of Chinese and English dictionary, equivalence class is mapped in this external completion.If input is English, first
First it is segmented, then according to the mapping relations of its field concept, corresponds to corresponding Chinese concept in ontology.In
After query text, English return is converted the result to.Process is as shown in Figure 4.
Embodiment
Select flight information exchange model (FIXM), aviation information exchange model (AIXM), weather information exchange model
(WXXM) as the source of structured document, the official websites such as FAA, EUROCONTROL, China Civil Aviation office and document are as unstructured
The source of document.
Concept from FIXM model has flying quality, airport, aircraft, landing, ability, dangerous material, takes off, urgent thing
Part, it is estimated leap boundary, flight path etc., concept organic field, maneuverability area availability from AIXM model, stop at airplane parking area
Seat in the plane, road, passenger boarding air bridge, runway etc., the concept from WXXM have core measurement, geometric object, general meteorologic survey,
Air themperature, ceiling of clouds, depth etc..
Sentence from non-structured document need to select suitable concept by segmenting, selecting noun.Such as it " searches and flies
Whether row device in homeplate ", the result after segmenting are as follows: search v, aircraft n, whether v, in p, this r, airport n.Pick out noun
For aircraft and airport.Wherein, v indicates that verb, n indicate that noun, p indicate that preposition, r indicate pronoun.
Therefore, final concept set is data, airport, aircraft, landing, ability, dangerous material, takes off, is emergency, pre-
Meter leaps boundary, flight path, maneuverability area availability, airplane parking area, aircraft gate, road, passenger boarding air bridge, runway, core
Measurement, geometric object, general meteorologic survey, air themperature, ceiling of clouds, depth etc..
According to above-mentioned concept, if the disjoint Ganlei of setting, the element in all concept sets calculates the phase with each class name
It is a kind of like spending or belonging to certain by expertise.Subclass includes: event, personnel, service, data, mechanism, equipment.For
Every a kind of this step of repetition, until forming final body construction.
Attribute section between class is directly acquired by structured document, such as there are title, address in airport.Another part from
It is obtained in unstructured participle, " " this attribute definition domain is aircraft, and codomain is airport.All categories are obtained according to the method
Property.
The search information dynamic extending ontology interaction models of user.For example, when user searches for " local radar information ", when
When concept " radar " is not deposited in ontology library, the phase of " radar " and concept each in ontology is calculated using software tools such as synonyms
Like degree, returns to decision recommendation " whether by ' radar ' ' equipment ' is added " and submit to ontology editing personnel and audit.
Chinese and English dictionary is realized by the corresponding database table of structure concept.It is a database fragment shown in table 1:
Table 1
Therefore, the multilingual extension of ontology can be realized by updating above-mentioned dictionary.
After the completion of the building of ontology interaction models, data query abundant and universe information management can be supported
The Web Service of (System Wide Information Management, SWIM) has found.SWIM is each machine in blank pipe field
Structure (airport, airline, blank pipe part) provides the frame of data to other interests associated mechanisms in the form of Web Service
Structure.When user's search " inquiry flight plan FP01 ", if ontology is not used to only rely on keyword search, can only return with
The relevant information such as " inquiry ", " flight ", " plan ".According to the blank pipe domain body interaction models that the present invention constructs, then may be used
More relevant informations are returned to, below in conjunction with Fig. 6, Fig. 7 explanation.Fig. 6 is the schematic diagram of part class and example after the completion of ontological construction.
Round icon representation class, diamond shape indicate example.Fig. 7 illustrates more specific information between Fig. 6 example.According to the input of user,
Corresponding example in ontology is found first.Then application program constructs SPARQL query statement according to all properties of the example,
Inquire associated example (note: SPARQL is a kind of common Ontology query language).Find " flight plan FP01 " this example
Afterwards, SPARQL query statement be " select? DepAirport
Where { http://www.semanticweb.org/shengyin/ontologies/2018/9# flight plan
FP01 http://www.semanticweb.org/shengyin/ontologies/2018/9#Departure Airport?
DepAirport } ", " select? CarrierName where { http://www.semanticweb.org/shengyin/
Ontologies/2018/9# flight plan FP01http: //www.semanticweb.org/shengyin/ontologies/
2018/9#Carrier? CarrierName } " and " select? ArrAirport
Where { http://www.semanticweb.org/shengyin/ontologies/2018/9# flight plan
FP01 http://www.semanticweb.org/shengyin/ontologies/2018/9#ArrivalAi rport?
ArrAirport}”
Above-mentioned query statement can show that original base is the Capital Airport, and landing station is Pudong International Airport, is navigated by east
Air transportion battalion.
When in ontology without corresponding information, according to the corresponding Web Service of attribute query and it can request to service.With
It inquires for " runway 9R/27L ", building SPARQL query statement " select? WebService where? WebService
http://www.semanticweb.org/shengyin/ontologies/2018/9#ProvideData http://
Www.semanticweb.org/shengyin/ontologies/2018/9# runway 9R/27L } " it can get Airport Operation service
The information of this WebService.The information of the service includes that the information such as import of services, output, WSDL are deposited in ontological construction
Enter.
When request is Beijing Capital International Airport, according to Chinese and English dictionary, the request
It is the Capital Airport for inquiry, relevant weather information and runway information can be inquired according to the example Capital Airport.
Therefore, compared with traditional information retrieval based on keyword, the blank pipe domain body constructed based on the present invention can
Effectively to promote recall ratio and precision ratio, blank pipe realm information retrieval effectiveness is promoted.
The present invention provides a kind of ontology interaction models construction methods in air traffic control field, implement the technology
There are many method and approach of scheme, the above is only a preferred embodiment of the present invention, it is noted that for the art
Those of ordinary skill for, various improvements and modifications may be made without departing from the principle of the present invention, these change
It also should be regarded as protection scope of the present invention into retouching.The available prior art of each component part being not known in the present embodiment adds
To realize.
Claims (7)
1. a kind of ontology interaction models construction method in air traffic control field, which comprises the steps of:
Step 1, the relevant document in blank pipe field is obtained；
Step 2, from concept required for extraction blank pipe domain body in the relevant document in blank pipe field；
Step 3, classify to the concept of extraction, and determine the hierarchical structure of class；
Step 4, the relationship between class is extracted, the attribute of ontology is constructed；
Step 5, based on the sentence of user query, Dynamic expansion ontology；
Step 6, the Chinese and English dictionary for constructing keyword, supports multilingual ontology.
2. the method according to claim 1, wherein step 1 includes:
Step 1-1 obtains structured document, and flight information, aviation information, weather information including International Civil Aviation Organization's standard are handed over
Mold changing type；
Step 1-2 obtains non-structured document, including Web service description, Web page information disclosed in blank pipe mechanism；
Step 1-3, the structured document and non-structured document of acquisition are as the relevant document in blank pipe field.
3. according to the method described in claim 2, it is characterized in that, step 2 includes:
Step 2-1, the concept of appearance is counted from structured document: structured document is xml structure, each structured document packet
Containing more than two xml labels, each label mapping is a concept of ontology, then each structured document forms a concept collection
SCi, to all structured documents, more than two concept sets are formed, the concept set from n structured document is SC=SC1
∪SC2∪…∪SCn, SCnIndicate the concept set that n-th of structured document is formed；
Step 2-2 carries out participle and part-of-speech tagging to non-structured document using participle tool, removes stop words, and for non-
The word segmentation result of structured document is counted, and the frequency of occurrences is that preceding 50% word of all words is used as a concept by audit
Collect UCi, the concept set from m non-structured document is UC=UC1∪UC2∪…∪UCm, UCmIndicate m-th it is unstructured
The concept set that document is formed；
Step 2-3, concept set required for blank pipe domain body are C=SC ∪ UC.
4. according to the method described in claim 3, it is characterized in that, step 3 includes:
Blank pipe domain body is divided into disjoint class by step 3-1, and when original state, each concept in blank pipe field is one
A class；
Step 3-2 is based on step 3-1, calculates the similarity of all classes between any two using WordNet, obtain the phase between class
N is formed like degree matrix, and using spectral clustering1A class；
Step 3-3 is N1A class name, and it is directed to this N1A class carries out the operation in step 3-2, forms class successively up, directly
The blank pipe domain class for forming a totality to the end, organizes these classes from top to bottom, forms the hierarchical structure of ontology.
5. according to the method described in claim 4, it is characterized in that, step 4 includes:
Step 4-1, flight information, aviation information, weather information exchange model are XML structure, itself is contained between information
Relationship, information have corresponded to the class in ontology in step 3, and the relationship between information then corresponds to the relationship between ontology class；
Step 4-2, according to the participle of step 2-2 and part-of-speech tagging as a result, the frequency that two words of statistics occur simultaneously in a document
Rate determines that there may be relationships between two words, return by ontology structure if the frequency of occurrences is related preceding 50% simultaneously
The person of building determines.
6. according to the method described in claim 5, it is characterized in that, step 5 includes:
Step 5-1 is segmented using sentence of the participle tool to user query；
Step 5-2 is tied if the word segmentation result of the sentence of user query is present in the ontology that step 4 and step 5 construct
Beam；
Step 5-3 matches the word segmentation result of the sentence of user query with the concept in concept set C, if user query
The word segmentation result of sentence is not present in the body, searches for similar concept in the body according near synonym query software, searches
Close concept submit as new concept and audited by ontological construction person, if audit passes through, new concept is added in concept set C.
7. according to the method described in claim 6, it is characterized in that, step 6 includes:
Step 6-1 constructs blank pipe field Chinese and English dictionary: by the Chinese conceptual translation in concept set C at English, translator of English at
Chinese；
Step 6-2 is first converted into Chinese according to blank pipe field Chinese and English dictionary for English searching request, turns after completing search
Change English output into.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811242103.3A CN109635272A (en) | 2018-10-24 | 2018-10-24 | A kind of ontology interaction models construction method in air traffic control field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811242103.3A CN109635272A (en) | 2018-10-24 | 2018-10-24 | A kind of ontology interaction models construction method in air traffic control field |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109635272A true CN109635272A (en) | 2019-04-16 |
Family
ID=66066657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811242103.3A Pending CN109635272A (en) | 2018-10-24 | 2018-10-24 | A kind of ontology interaction models construction method in air traffic control field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635272A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020244023A1 (en) * | 2019-06-06 | 2020-12-10 | 中国电子科技集团公司第二十八研究所 | Information aggregation method and apparatus based on knowledge graph, and device |
| CN113761226A (en) * | 2021-11-10 | 2021-12-07 | 中国电子科技集团公司第二十八研究所 | Ontology construction method of multi-modal airport data |
| CN114385819A (en) * | 2022-03-23 | 2022-04-22 | 湖南工商大学 | Environment judicial domain ontology construction method and device and related equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609512A (en) * | 2012-02-07 | 2012-07-25 | 北京中机科海科技发展有限公司 | System and method for heterogeneous information mining and visual analysis |
| CN105701193A (en) * | 2016-01-11 | 2016-06-22 | 同济大学 | Method for rapidly searching for traffic big data dynamic information and application thereof |
| CN106445990A (en) * | 2016-06-25 | 2017-02-22 | 上海大学 | Event ontology construction method |
| CN107885749A (en) * | 2016-09-30 | 2018-04-06 | 南京理工大学 | Ontology extends the process knowledge search method with collaborative filtering Weighted Fusion |
-
2018
- 2018-10-24 CN CN201811242103.3A patent/CN109635272A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609512A (en) * | 2012-02-07 | 2012-07-25 | 北京中机科海科技发展有限公司 | System and method for heterogeneous information mining and visual analysis |
| CN105701193A (en) * | 2016-01-11 | 2016-06-22 | 同济大学 | Method for rapidly searching for traffic big data dynamic information and application thereof |
| CN106445990A (en) * | 2016-06-25 | 2017-02-22 | 上海大学 | Event ontology construction method |
| CN107885749A (en) * | 2016-09-30 | 2018-04-06 | 南京理工大学 | Ontology extends the process knowledge search method with collaborative filtering Weighted Fusion |
Non-Patent Citations (1)
| Title |
|---|
| 王庆林 等: "《气候变化领域本体手册》", 北京：北京理工大学出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020244023A1 (en) * | 2019-06-06 | 2020-12-10 | 中国电子科技集团公司第二十八研究所 | Information aggregation method and apparatus based on knowledge graph, and device |
| CN113761226A (en) * | 2021-11-10 | 2021-12-07 | 中国电子科技集团公司第二十八研究所 | Ontology construction method of multi-modal airport data |
| CN114385819A (en) * | 2022-03-23 | 2022-04-22 | 湖南工商大学 | Environment judicial domain ontology construction method and device and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800284B (en) | Task-oriented unstructured information intelligent question-answering system construction method | |
| CN110633409B (en) | Automobile news event extraction method integrating rules and deep learning | |
| CN104090907B (en) | A kind of method and apparatus for providing a user with information | |
| KR101060594B1 (en) | Keyword Extraction and Association Network Configuration for Document Data | |
| CN113806563B (en) | Architect knowledge graph construction method for multi-source heterogeneous building humanistic historical material | |
| CN108021718A (en) | Capability of Internet of things knowledge mapping and its construction method | |
| CN108763333A (en) | A kind of event collection of illustrative plates construction method based on Social Media | |
| CN110781670B (en) | Chinese place name semantic disambiguation method based on encyclopedic knowledge base and word vectors | |
| US20090070298A1 (en) | Iterators for Applying Term Occurrence-Level Constraints in Natural Language Searching | |
| CN109308321A (en) | A kind of knowledge question answering method, knowledge Q-A system and computer readable storage medium | |
| KR20160060253A (en) | Natural Language Question-Answering System and method | |
| KR20120061133A (en) | Question type and domain identifying apparatus and method | |
| CN103440314A (en) | Semantic retrieval method based on Ontology | |
| CN109635272A (en) | A kind of ontology interaction models construction method in air traffic control field | |
| US9201905B1 (en) | Semantically mediated access to knowledge | |
| CN113157859A (en) | Event detection method based on upper concept information | |
| KR20220074576A (en) | A method and an apparatus for extracting new words based on deep learning to generate marketing knowledge graphs | |
| CN114996549A (en) | Intelligent tracking method and system based on active object information mining | |
| CN112084312A (en) | Intelligent customer service system constructed based on knowledge graph | |
| CN113377739A (en) | Knowledge graph application method, knowledge graph application platform, electronic equipment and storage medium | |
| CN111104492B (en) | Civil aviation field automatic question and answer method based on layering Attention mechanism | |
| CN116662549A (en) | Cross-language retrieval classification method for aviation accident report | |
| CN112328855A (en) | Multi-source military equipment knowledge association organization method | |
| CN105488062A (en) | Accurate information system data searching method | |
| KR102371224B1 (en) | Apparatus and methods for trend analysis in airport and aviation technology |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |