CN107766556B - Interactive ontology matching method based on evolutionary algorithm and computer equipment - Google Patents

Interactive ontology matching method based on evolutionary algorithm and computer equipment Download PDF

Info

Publication number
CN107766556B
CN107766556B CN201711070247.0A CN201711070247A CN107766556B CN 107766556 B CN107766556 B CN 107766556B CN 201711070247 A CN201711070247 A CN 201711070247A CN 107766556 B CN107766556 B CN 107766556B
Authority
CN
China
Prior art keywords
ontology
matching
user
inspection
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711070247.0A
Other languages
Chinese (zh)
Other versions
CN107766556A (en
Inventor
薛醒思
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.)
Fujian University of Technology
Original Assignee
Fujian University of Technology
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 Fujian University of Technology filed Critical Fujian University of Technology
Priority to CN201711070247.0A priority Critical patent/CN107766556B/en
Publication of CN107766556A publication Critical patent/CN107766556A/en
Application granted granted Critical
Publication of CN107766556B publication Critical patent/CN107766556B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/90335—Query processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Genetics & Genomics (AREA)
  • Physiology (AREA)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides an interactive ontology matching method based on an evolutionary algorithm, which comprises an ontology partitioning stage, wherein a large-scale ontology is partitioned into small-scale ontology blocks, so that the subsequent ontology matching process is carried out in the ontology blocks; in the ontology matching stage based on the evolutionary algorithm, the evolutionary algorithm is utilized to realize an automatic ontology matching process, and the time point of user intervention is determined in a self-adaptive manner; in the user inspection and inspection result diffusion stage, automatically determined candidate ontology matching results are presented to a user for inspection, the remaining candidate ontology matching results are automatically processed in the user inspection process, and finally, credible user inspection results are diffused; and integrating the matching results of the body blocks and evaluating the matching results, integrating the matching results of different body blocks, and calculating the f measurement of the final result by using the reference matching result of the body.

Description

Interactive ontology matching method based on evolutionary algorithm and computer equipment
Technical Field
The invention relates to an ontology matching method and a computer device capable of executing the method.
Background
A body: a specification that is definitively conceptual to knowledge in a certain domain, i.e., a formal and canonical description of objects, concepts, other entities, and the relationships between them that exist in a certain domain.
The body matching process: a process of determining a set of semantically identical pairs of entities in two heterogeneous ontologies.
The ontology matching technology can solve the problem of ontology heterogeneity (the same concept has different names in different ontologies), and realizes the cooperation of ontology-based application programs on a semantic level.
An ontology, a core technology of semantic networks, is a shared and formal reference model for information exchange, which describes objects, concepts, other entities and relationships among them existing in a certain domain [1 ]. Ontology technology has important application in the fields of knowledge management, information retrieval, electronic commerce, biomedicine and the like, and the entity scale contained in the ontology published on the semantic web at present reaches 31 hundred million. However, the heterogeneous problem among these ontologies (the same concept has different names in different ontologies) is the biggest obstacle to realizing semantic cooperation among different applications in the semantic web, and is also the bottleneck problem restricting the development of the semantic web. The ontology matching technique is currently the most effective method for solving the problem of ontology heterogeneity [2 ]. However, until the patent application is completed (2 months 2017), the existing ontology matching technology is about 45% wrong for 5 hundred million entity matching results published on the semantic web [3,4 ]. Therefore, there is a need for a technique capable of obtaining high quality ontology matching results. Due to the complexity of the ontology matching process, the ontology matching result obtained by the automated ontology matching technology needs to be verified by a user to ensure the quality of the ontology matching result. The process of making user and automated ontology matching techniques cooperate in a reasonable time to obtain high quality ontology matching results is called interactive ontology matching process. The ontology matching system cannot require the user to verify all entity matching pairs in one ontology matching result, so one of the main challenge problems in the interactive ontology matching process is how to maximize the value of the user inspection result while minimizing the workload of the user.
In minimizing user workload, Shi et al [5] propose to select the most informative problem matching pairs for user authentication by means of thresholds and similarity diffusion maps determined by an interactive algorithm. Jime nez-Ruiz et al [6] propose three principles (i.e., consistency, locality and retention) to filter candidate entity matching pairs. Beisswanger et al [7] propose some quality check criteria to measure the reusability of ontology matching results and use it to determine a candidate entity match set. Cruz [8], etc. select problem entity matching pairs for users that different ontology matchers cannot achieve consistent results. Similarly, SAMBO [9] reduces unnecessary user intervention through knowledge previously verified by the user. GOMMA [10] employs a combination and diversity based adaptive algorithm to multiplex unaffected entity matched pairs. PROMPT [11] determines the set of candidate entity matches by the results of the most recent user intervention.
The similarity diffusion algorithm can diffuse the user verification result to the neighbor concept according to the ontology concept architecture, and is an effective method for maximizing the user verification result. Shi et al [5] propose an active learning framework that can provide the most informative candidate match results to the user for user verification and spread the user verification results according to an ontology concept architecture to improve the accuracy of matching. The agrementmaker [8] uses the signature vector to spread the feedback result of the user to other entity matching pairs, and the increase and decrease of the similarity value of the related matching pair are realized through a linear function.
In summary of the existing ontology matching methods, the following disadvantages exist:
(1) because each iteration process needs user intervention, unnecessary workload of the user is increased;
(2) the user is required to verify the candidate matching results one by one, and the rest candidate matching results cannot be automatically processed according to the verification result of the user, so that the workload of the user is increased;
(3) erroneous user authentication results are easily diffused, thereby degrading the quality of ontology matching.
[1]Garrido A.Logical Foundations of Artificial Intelligence[J].BRAIN.Broad Research in Artificial Intelligence and Neuroscience,2010,1(2):149-152.
[2]Shvaiko P,Euzenat J.Ontology matching:state of the art and future challenges[J].IEEE Transactions on knowledge and data engineering,2013,25(1):158-176.
[3]Liu W.Truth discovery to resolve object conflicts in linked data[J].arXiv preprint arXiv:1509.00104,2015.
[4]Liu W,Liu J,Duan H,et al.Exploiting Source-Object Network to Resolve Object Conflicts in Linked Data[J].arXiv preprint arXiv:1604.08407,2016.
[5]F.Shi,J.Li,J.Tang,G.Xie,and H.Li,“Actively learning ontology matching via user interaction,”in International Semantic Web Conference.Springer,2009,pp.585–600.
[6]E.Jiménez-Ruiz,B.C.Grau,I.Horrocks,and R.Berlanga,“Logic-based assessment of the compatibility of umls ontology sources,”Journal of biomedical semantics,vol.2,no.1,p.S2,2011.
[7]E.Beisswanger and U.Hahn,“Towards valid and reusable reference
Figure GDA0002970714710000031
basic quality checks for ontology alignments and their application to three different reference data sets,”Journal of biomedical semantics,vol.3,no.1,p.S4,2012.
[8]I.F.Cruz,C.Stroe,and M.Palmonari,“Interactive user feedback in ontology matching using signature vectors,”in 2012IEEE 28th International Conference on Data Engineering.IEEE,2012,pp.1321–1324.
[9]P.Lambrix and R.Kaliyaperumal,“A session-based approach for aligning large ontologies,”in Extended Semantic Web Conference.Springer,2013,pp.46–60.
[10]A.Groβ,J.C.Dos Reis,M.Hartung,C.Pruski,and E.Rahm,“Semi-automatic adaptation of mappings between life science ontologies,”in International Conference on Data Integration inthe Life Sciences.Springer,2013,pp.90–104.
[11]N.F.Noy,M.A.Musen et al.,“Algorithm and tool for automated ontology merging and alignment,”in Proceedings of the 17th National Conference on Artificial Intelligence(AAAI-00).Available as SMI technical report SMI-2000-0831,2000.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an interactive ontology matching method based on an evolutionary algorithm, which can adaptively determine the time point of user intervention, automatically determine a limited number of ontology matching candidate sets for user inspection, and spread the results of the user inspection to achieve the purpose of maximizing the value of the user inspection results.
The method of the invention is realized as follows: an interactive ontology matching method based on an evolutionary algorithm comprises the following steps:
a body division stage, wherein a large-scale body is divided into small-scale body blocks, so that the subsequent body matching process is carried out in the body blocks;
in the ontology matching stage based on the evolutionary algorithm, the evolutionary algorithm is utilized to realize an automatic ontology matching process, and the time point of user intervention is determined in a self-adaptive manner;
in the user inspection and inspection result diffusion stage, automatically determined candidate ontology matching results are presented to a user for inspection, the remaining candidate ontology matching results are automatically processed in the user inspection process, and finally, credible user inspection results are diffused;
and integrating the matching results of the body blocks and evaluating the matching results, integrating the matching results of different body blocks, and calculating the f measurement of the final result by using the reference matching result of the body.
Further, the specific process of the ontology partitioning stage is as follows:
(1) firstly, measuring the dispersibility and the unbalance of an ontology structure through SemanticAccuracy to select an ontology with stronger reliability as a source ontology;
(2) then, dividing the source body into source body blocks by using a body division algorithm of an extended self-SCAN algorithm;
(3) for each source ontology partition, a similar target ontology partition is determined using the conceptual relatedness metric.
Further, the ontology matching stage based on the evolutionary algorithm comprises a modeling process and a matching process;
the modeling process specifically comprises:
s11, defining an ontology O as O ═ { C, P, I }, where C, P, and I respectively represent a concept set, an attribute set, and an instance set in the ontology, where the concepts, attributes, and instances collectively refer to entities of the ontology; the ontology matching result A is a set of entity matching pairs, each entity matching pair can be represented as a quadruple { e, e ', n, rel }, wherein e and e' respectively represent entities of a meta ontology and a target ontology, n is a reliability value of a relation between e and e ', and rel is an equivalent relation between e and e';
s12, given the ontology matching result a, its quality is measured by f (a):
Figure GDA0002970714710000041
where | A | is the number of matching pairs in A, MF (A) is the MatchFmeasure value for calculating A, δiIs the similarity value of the ith matching pair in A, and is alpha epsilon [0,1]Is a main adjusting parameter for balancing recall ratio and precision ratio of the ontology matching result;
s13, giving Source ontology Block OsrcAnd target body block OtgtDesigning an optimization model of the single-target ontology matching problem as follows:
Figure GDA0002970714710000051
wherein f isi(X), i ═ 1, 2.. m, m calculates the f () value, | O, of the ith matcher resultsrcI and OtgtRespectively represents an ontology OsrcAnd OtgtRadix of the entity set of (1), xi,i＝1,2,...,|OsrcI represents the ith entity matching pair;
the matching process specifically comprises the following steps:
s21, configuring algorithm control parameters including numerical precision, population scale, selection probability, cross probability and variation probability;
s22, randomly initializing the population, and selecting the individual with the highest fitness value in the population as the initialization value of the elite solution;
s23, entering an evolution process, namely, firstly evaluating the fitness value f () of each individual in the population, selecting through a roulette wheel, and selecting to generate a next generation of population after the operation of a single-point crossing and single-point mutation standard evolution operator;
and S24, re-evaluating the fitness value f () of the population and trying to update the elite solution until the termination condition is met, outputting an ontology block matching result, and if the elite solution cannot be updated for a plurality of successive generations and evolves, enabling a user to intervene in the evolution direction of the guiding algorithm.
Further, the specific process of the user inspection and inspection result diffusion stage is as follows:
(1) firstly, checking a 'problem' matching pair of an entity matching pair in an elite solution near a similarity threshold value of 0.4 by a user;
(2) then, for one entity in the target body, a plurality of source body entities are matched correspondingly, so that a user selects one correct matching pair, and the credibility of the rest matching pairs is set to be 0;
(3) and finally, diffusing credibility of the matched pairs with the similarity values higher than the threshold value of 0.9 into the peripheral concepts of the matched pairs for the user verified results.
Furthermore, the alpha value is in direct proportion to the recall ratio and in inverse proportion to the precision ratio. The suggested value of a is 0.35.
Furthermore, the present invention also provides a computer device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor is capable of executing the procedures of the method of the present invention when executing the program.
The invention has the following advantages:
(1) the time of user intervention is adaptively determined by using an evolutionary algorithm, so that unnecessary user interaction is reduced;
(2) the residual candidate matching pairs are automatically processed according to the user inspection result, so that the workload of the user is reduced, and the efficiency of the user inspection process is improved;
(3) entity matching pairs higher than a threshold value and detected by a user are diffused into a peripheral concept, so that adverse effects caused by wrong user detection results are reduced, the value of the user detection results is maximized, and meanwhile, the efficiency of an ontology matching process and the quality of final ontology matching results are improved.
Drawings
The invention will be further described with reference to the following examples with reference to the accompanying drawings.
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a flow chart of the execution of the user verification and verification result diffusion stage in the method of the present invention.
Detailed Description
Referring to fig. 1, the interactive ontology matching method based on the evolutionary algorithm of the present invention includes an ontology partitioning stage, an ontology matching stage based on the evolutionary algorithm, a user inspection and inspection result diffusion stage, and an ontology block matching result integration and evaluation stage.
In the body division stage, a large-scale body is divided into small-scale body blocks, so that the subsequent body matching process is carried out in the body blocks; the specific process is as follows:
(1) firstly, an ontology with stronger reliability is selected as a source ontology by measuring the dispersity and unbalance of an ontology structure through a SemanticAccuracy (S < n > nchez D, Batet M, Martinz S, et al Semantic variance: an innovative media for the iterative evaluation [ J ]. Engineering Applications of intellectual interest, 2015,39: 89-99);
(2) then, dividing the source body into source body blocks by using a body division algorithm of an extended self-SCAN algorithm;
(3) for each source ontology partition, a conceptual relevance metric is used to determine its similar target ontology partition (x.xue, j.pan, a segment-based approach for large-scale integration Systems, Knowledge and Information Systems (2017) 1-18).
In the ontology matching stage based on the evolutionary algorithm, the evolutionary algorithm is utilized to realize an automatic ontology matching process, and the time point of user intervention is determined in a self-adaptive manner; the ontology matching stage based on the evolutionary algorithm comprises a modeling process and a matching process;
the modeling process specifically comprises:
s11, defining an ontology O as O ═ { C, P, I }, where C, P, and I respectively represent a concept set, an attribute set, and an instance set in the ontology, where the concepts, attributes, and instances collectively refer to entities of the ontology; the ontology matching result A is a set of entity matching pairs, each entity matching pair can be represented as a quadruple { e, e ', n, rel }, wherein e and e' respectively represent entities of a meta ontology and a target ontology, n is a reliability value of a relation between e and e ', and rel is an equivalent relation between e and e';
s12, given the ontology matching result a, its quality is measured by f (a):
Figure GDA0002970714710000071
where | A | is the number of matching pairs in A, MF (A) is the MatchFmeasure value for calculating A, δiIs the similarity value of the ith matching pair in A, and is alpha epsilon [0,1]Is used forBalancing the recall ratio and precision ratio main adjustment parameters of the ontology matching result; the alpha value is in direct proportion to recall ratio and in inverse proportion to precision ratio; the suggested value of α is 0.35;
s13, giving Source ontology Block OsrcAnd target body block OtgtDesigning an optimization model of the single-target ontology matching problem as follows:
Figure GDA0002970714710000072
wherein f isi(X), i ═ 1, 2.. m, m calculates the f () value, | O, of the ith matcher resultsrcI and OtgtRespectively represents an ontology OsrcAnd OtgtRadix of the entity set of (1), xi,i＝1,2,...,|OsrcI represents the ith entity matching pair;
the matching process specifically comprises the following steps:
s21, configuring algorithm control parameters including numerical precision, population scale, selection probability, cross probability and variation probability;
s22, randomly initializing the population, and selecting the individual with the highest fitness value in the population as the initialization value of the elite solution;
s23, entering an evolution process, namely, firstly evaluating the fitness value f () of each individual in the population, selecting through a roulette wheel, and selecting to generate a next generation of population after the operation of a single-point crossing and single-point mutation standard evolution operator;
and S24, re-evaluating the fitness value f () of the population and trying to update the elite solution until the termination condition is met, outputting an ontology block matching result, and if the elite solution cannot be updated for a plurality of successive generations and evolves, enabling a user to intervene in the evolution direction of the guiding algorithm.
In the user inspection and inspection result diffusion stage, automatically determined candidate ontology matching results are presented to a user for inspection, the remaining candidate ontology matching results are automatically processed in the user inspection process, and finally, credible user inspection results are diffused; the specific process is as follows:
(1) firstly, checking a 'problem' matching pair of an entity matching pair in an elite solution near a similarity threshold value of 0.4 by a user;
(2) then, for one entity in the target body, a plurality of source body entities are matched correspondingly, so that a user selects one correct matching pair, and the credibility of the rest matching pairs is set to be 0;
(3) finally, for the result checked by the user, diffusing credibility of the matching pairs with similarity values higher than a threshold value of 0.9 into peripheral concepts of the matching pairs;
for example, for a matching pair { e, e ',0.92, } checked by the user, all parent concept sets Sup of e and e' in the respective ontology concept architectures are found respectivelyeHe SueIf it is
Figure GDA0002970714710000081
And
Figure GDA0002970714710000082
if it is already the entity pair on the match, then its trustworthiness is increased by 0.3.
And in the body block matching result integration and evaluation stage, integrating different body block matching results through a greedy algorithm, and calculating f measurement of a final result by using a reference matching result of the body.
It should be noted that: the ontology division algorithm can be replaced by other ontology division algorithms; the measuring technology of the approximate ontology matching result adopted by the invention can also be replaced by other measuring technologies of the approximate ontology matching result; the evolutionary algorithm adopted by the invention can be replaced by other group intelligence algorithms. Furthermore, the present invention also provides a computer device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor is capable of executing the procedures of the method of the present invention when executing the program.
Although specific embodiments of the invention have been described above, it will be understood by those skilled in the art that the specific embodiments described are illustrative only and are not limiting upon the scope of the invention, and that equivalent modifications and variations can be made by those skilled in the art without departing from the spirit of the invention, which is to be limited only by the appended claims.

Claims (10)

1. An interactive ontology matching method based on an evolutionary algorithm is characterized in that: the method comprises the following steps:
a body division stage, wherein a large-scale body is divided into small-scale body blocks, so that the subsequent body matching process is carried out in the body blocks;
in the ontology matching stage based on the evolutionary algorithm, the evolutionary algorithm is utilized to realize an automatic ontology matching process, and the time point of user intervention is determined in a self-adaptive manner;
in the user inspection and inspection result diffusion stage, automatically determined candidate ontology matching results are presented to a user for inspection, the remaining candidate ontology matching results are automatically processed in the user inspection process, and finally, credible user inspection results are diffused;
integrating the matching results of different body blocks and calculating the f measurement of the final result by using the reference matching result of the body;
wherein the ontology matching stage based on the evolutionary algorithm comprises a modeling process and a matching process;
the modeling process specifically comprises:
s11, defining an ontology O as O ═ { C, P, I }, where C, P, and I respectively represent a concept set, an attribute set, and an instance set in the ontology, where the concepts, attributes, and instances collectively refer to entities of the ontology; the ontology matching result A is a set of entity matching pairs, each entity matching pair can be represented as a quadruple { e, e ', n, rel }, wherein e and e' respectively represent entities of a meta ontology and a target ontology, n is a reliability value of a relation between e and e ', and rel is an equivalent relation between e and e';
s12, given the ontology matching result a, its quality is measured by f (a):
Figure FDA0003019752700000011
where | A | is the number of matching pairs in A, MF (A) is the MatchFmeasure value for calculating A, δiIs the similarity value of the ith matching pair in A, and is alpha epsilon [0,1]Is a main adjusting parameter for balancing recall ratio and precision ratio of the ontology matching result;
s13, giving Source ontology Block OsrcAnd target body block OtgtDesigning an optimization model of the single-target ontology matching problem as follows:
Figure FDA0003019752700000021
wherein f isi(X), i ═ 1, 2.. m, m calculates the f () value, | O, of the ith matcher resultsrcI and OtgtRespectively represents an ontology OsrcAnd OtgtRadix of the entity set of (1), xi,i＝1,2,...,|OsrcI represents the ith entity matching pair;
the matching process specifically comprises the following steps:
s21, configuring algorithm control parameters including numerical precision, population scale, selection probability, cross probability and variation probability;
s22, randomly initializing the population, and selecting the individual with the highest fitness value in the population as the initialization value of the elite solution;
s23, entering an evolution process, namely, firstly evaluating the fitness value f () of each individual in the population, selecting through a roulette wheel, and selecting to generate a next generation of population after the operation of a single-point crossing and single-point mutation standard evolution operator;
and S24, re-evaluating the fitness value f () of the population and trying to update the elite solution until the termination condition is met, outputting the ontology block matching result, and if the elite solution cannot be updated for a plurality of successive generations and evolves, enabling a user to intervene in the evolution direction of the guide algorithm, and performing user inspection and inspection result diffusion.
2. The interactive ontology matching method based on evolutionary algorithm as claimed in claim 1, wherein: the specific process of the body division stage is as follows:
(1) firstly, measuring the dispersibility and the unbalance of an ontology structure through SemanticAccuracy to select an ontology with stronger reliability as a source ontology;
(2) then, dividing the source body into source body blocks by using a body division algorithm of an extended self-SCAN algorithm;
(3) for each source ontology partition, a similar target ontology partition is determined using the conceptual relatedness metric.
3. The interactive ontology matching method based on evolutionary algorithm as claimed in claim 1, wherein: the specific process of the user inspection and inspection result diffusion stage is as follows:
(1) firstly, checking a 'problem' matching pair of an entity matching pair in an elite solution near a similarity threshold value of 0.4 by a user;
(2) then, for one entity in the target body, a plurality of source body entities are matched correspondingly, so that a user selects one correct matching pair, and the credibility of the rest matching pairs is set to be 0;
(3) and finally, diffusing credibility of the matched pairs with the similarity values higher than the threshold value of 0.9 into the peripheral concepts of the matched pairs for the user verified results.
4. The interactive ontology matching method based on evolutionary algorithm as claimed in claim 1, wherein: the alpha value is in direct proportion to recall ratio and in inverse proportion to precision ratio.
5. An interactive ontology matching method based on evolutionary algorithm, as claimed in claim 1 or 4, characterized in that: the value of alpha is 0.35.
6. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the processes of:
a body division stage, wherein a large-scale body is divided into small-scale body blocks, so that the subsequent body matching process is carried out in the body blocks;
in the ontology matching stage based on the evolutionary algorithm, the evolutionary algorithm is utilized to realize an automatic ontology matching process, and the time point of user intervention is determined in a self-adaptive manner;
in the user inspection and inspection result diffusion stage, automatically determined candidate ontology matching results are presented to a user for inspection, the remaining candidate ontology matching results are automatically processed in the user inspection process, and finally, credible user inspection results are diffused;
integrating the matching results of different body blocks and calculating the f measurement of the final result by using the reference matching result of the body;
wherein the ontology matching stage based on the evolutionary algorithm comprises a modeling process and a matching process;
the modeling process specifically comprises:
s11, defining an ontology O as O ═ { C, P, I }, where C, P, and I respectively represent a concept set, an attribute set, and an instance set in the ontology, where the concepts, attributes, and instances collectively refer to entities of the ontology; the ontology matching result A is a set of entity matching pairs, each entity matching pair can be represented as a quadruple { e, e ', n, rel }, wherein e and e' respectively represent entities of a meta ontology and a target ontology, n is a reliability value of a relation between e and e ', and rel is an equivalent relation between e and e';
s12, given the ontology matching result a, its quality is measured by f (a):
Figure FDA0003019752700000041
where | A | is the number of matching pairs in A, MF (A) is the MatchFmeasure value for calculating A, δiIs the similarity value of the ith matching pair in A, and is alpha epsilon [0,1]Is a main adjusting parameter for balancing recall ratio and precision ratio of the ontology matching result;
s13, supplyFixed source body block OsrcAnd target body block OtgtDesigning an optimization model of the single-target ontology matching problem as follows:
Figure FDA0003019752700000042
wherein f isi(X), i ═ 1, 2.. m, m calculates the f () value, | O, of the ith matcher resultsrcI and OtgtRespectively represents an ontology OsrcAnd OtgtRadix of the entity set of (1), xi,i＝1,2,...,|OsrcI represents the ith entity matching pair;
the matching process specifically comprises the following steps:
s21, configuring algorithm control parameters including numerical precision, population scale, selection probability, cross probability and variation probability;
s22, randomly initializing the population, and selecting the individual with the highest fitness value in the population as the initialization value of the elite solution;
s23, entering an evolution process, namely, firstly evaluating the fitness value f () of each individual in the population, selecting through a roulette wheel, and selecting to generate a next generation of population after the operation of a single-point crossing and single-point mutation standard evolution operator;
and S24, re-evaluating the fitness value f () of the population and trying to update the elite solution until the termination condition is met, outputting the ontology block matching result, and if the elite solution cannot be updated for a plurality of successive generations and evolves, enabling a user to intervene in the evolution direction of the guiding algorithm and entering the user inspection and inspection result diffusion stage.
7. A computer device according to claim 6, wherein: the specific process of the body division stage is as follows:
(1) firstly, measuring the dispersibility and the unbalance of an ontology structure through SemanticAccuracy to select an ontology with stronger reliability as a source ontology;
(2) then, dividing the source body into source body blocks by using a body division algorithm of an extended self-SCAN algorithm;
(3) for each source ontology partition, a similar target ontology partition is determined using the conceptual relatedness metric.
8. A computer device according to claim 6 or 7, characterized in that: the specific process of the user inspection and inspection result diffusion stage is as follows:
(1) firstly, checking a 'problem' matching pair of an entity matching pair in an elite solution near a similarity threshold value of 0.4 by a user;
(2) then, for one entity in the target body, a plurality of source body entities are matched correspondingly, so that a user selects one correct matching pair, and the credibility of the rest matching pairs is set to be 0;
(3) and finally, diffusing credibility of the matched pairs with the similarity values higher than the threshold value of 0.9 into the peripheral concepts of the matched pairs for the user verified results.
9. A computer device according to claim 7, wherein: the alpha value is in direct proportion to recall ratio and in inverse proportion to precision ratio.
10. A computer device according to claim 7 or 9, characterized in that: the value of alpha is 0.35.
CN201711070247.0A 2017-11-03 2017-11-03 Interactive ontology matching method based on evolutionary algorithm and computer equipment Active CN107766556B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711070247.0A CN107766556B (en) 2017-11-03 2017-11-03 Interactive ontology matching method based on evolutionary algorithm and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711070247.0A CN107766556B (en) 2017-11-03 2017-11-03 Interactive ontology matching method based on evolutionary algorithm and computer equipment

Publications (2)

Publication Number Publication Date
CN107766556A CN107766556A (en) 2018-03-06
CN107766556B true CN107766556B (en) 2021-07-30

Family

ID=61273656

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711070247.0A Active CN107766556B (en) 2017-11-03 2017-11-03 Interactive ontology matching method based on evolutionary algorithm and computer equipment

Country Status (1)

Country Link
CN (1) CN107766556B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112860913B (en) * 2021-02-24 2024-03-08 广州汇通国信科技有限公司 Ontology creation method of knowledge graph

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103631882A (en) * 2013-11-14 2014-03-12 北京邮电大学 Semantization service generation system and method based on graph mining technique
CN103810388A (en) * 2014-02-19 2014-05-21 福建工程学院 Large-scale ontology mapping method based on partitioning technology oriented towards mapping
CN104866626A (en) * 2015-06-15 2015-08-26 ***通信集团黑龙江有限公司 Method and device for recommending telecommunication service
WO2016093405A1 (en) * 2014-12-12 2016-06-16 University-Industry Cooperation Group Of Kyung Hee University Adaptive semantic based mediation system and method
CN106227798A (en) * 2016-07-21 2016-12-14 福州职业技术学院 A kind of Ontology Matching method based on compact Cooperative Evolutionary Algorithm
CN106855886A (en) * 2016-12-26 2017-06-16 武汉大学 The position concept structuring extracting method of the conspicuousness structure based on location expression
CN107193858A (en) * 2017-03-28 2017-09-22 福州金瑞迪软件技术有限公司 Towards the intelligent Service application platform and method of multi-source heterogeneous data fusion

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9747563B2 (en) * 2013-11-27 2017-08-29 University-Industry Cooperation Group Of Kyung Hee University Apparatus and method for matching large-scale biomedical ontologies

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103631882A (en) * 2013-11-14 2014-03-12 北京邮电大学 Semantization service generation system and method based on graph mining technique
CN103810388A (en) * 2014-02-19 2014-05-21 福建工程学院 Large-scale ontology mapping method based on partitioning technology oriented towards mapping
WO2016093405A1 (en) * 2014-12-12 2016-06-16 University-Industry Cooperation Group Of Kyung Hee University Adaptive semantic based mediation system and method
CN104866626A (en) * 2015-06-15 2015-08-26 ***通信集团黑龙江有限公司 Method and device for recommending telecommunication service
CN106227798A (en) * 2016-07-21 2016-12-14 福州职业技术学院 A kind of Ontology Matching method based on compact Cooperative Evolutionary Algorithm
CN106855886A (en) * 2016-12-26 2017-06-16 武汉大学 The position concept structuring extracting method of the conspicuousness structure based on location expression
CN107193858A (en) * 2017-03-28 2017-09-22 福州金瑞迪软件技术有限公司 Towards the intelligent Service application platform and method of multi-source heterogeneous data fusion

Also Published As

Publication number Publication date
CN107766556A (en) 2018-03-06

Similar Documents

Publication Publication Date Title
Lin et al. CIDR: Ultrafast and accurate clustering through imputation for single-cell RNA-seq data
Xue et al. Collaborative ontology matching based on compact interactive evolutionary algorithm
Peng et al. Lime: Low-cost and incremental learning for dynamic heterogeneous information networks
Yu et al. A three-way cluster ensemble approach for large-scale data
Xue et al. Using NSGA‐III for optimising biomedical ontology alignment
Zhang et al. Hybrid fuzzy clustering method based on FCM and enhanced logarithmical PSO (ELPSO)
EP3001329A1 (en) Method, controller, program and data storage system for performing reconciliation processing
Xue et al. Using MOEA/D for optimizing ontology alignments
Srivastava et al. A parallel framework for constraint-based Bayesian network learning via Markov blanket discovery
Lv et al. Solving ontology meta-matching problem through an evolutionary algorithm with approximate evaluation indicators and adaptive selection pressure
Huang et al. Semantic integration of sensor knowledge on artificial internet of things
CN107766556B (en) Interactive ontology matching method based on evolutionary algorithm and computer equipment
Chen et al. Forest Fire Clustering for single-cell sequencing combines iterative label propagation with parallelized Monte Carlo simulations
Cruz et al. Quality-based model for effective and robust multi-user pay-as-you-go ontology matching 1
Ma et al. Learning code representations using multifractal-based graph networks
CN112131587A (en) Intelligent contract pseudo-random number security inspection method, system, medium and device
Liang et al. Optimization of basic clustering for ensemble clustering: an information-theoretic perspective
de Araujo et al. Impact of feature selection methods on the classification of DDoS attacks using XGBoost
CN111897809A (en) Command information system data generation method based on generation countermeasure network
CN116705192A (en) Drug virtual screening method and device based on deep learning
Du et al. Combining quantum-behaved PSO and K2 algorithm for enhancing gene network construction
Sun et al. An evolutionary many-objective algorithm based on decomposition and hierarchical clustering selection
Yan [Retracted] Audience Evaluation and Analysis of Symphony Performance Effects Based on the Genetic Neural Network Algorithm for the Multilayer Perceptron (GA‐MLP‐NN)
Pirgazi et al. TIGRNCRN: Trustful inference of gene regulatory network using clustering and refining the network
Zeng et al. Local epochs inefficiency caused by device heterogeneity in federated learning

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