Method and system for text understanding in an ontology driven platform

• US 8,433,715 B1
• Filed: 12/13/2010
• Issued: 04/30/2013
• Est. Priority Date: 12/16/2009
• Status: Active Grant

• Current Assignee: Board of Regents of the University of Texas System (University of Texas System)
• Original Assignee: Board of Regents of the University of Texas System (University of Texas System)
• Inventors: Mirhaji, Parsa
• Primary Examiner(s): Perveen, Rehana
• Assistant Examiner(s): HAVAN, HUNG T
• Application Number:
  US12/928,489
• Time in Patent Office: 869 Days
• Field of Search: 707/739, 707/756
• US Class Current: 707/756
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

Embodiments of methods and systems for informatics systems are disclosed. Such informatics systems may utilize a unifying format to represent text to facilitate linking between data from the text and one or more ontologies, and the commensurate ability to mine such data.

Claims

1. A system for ontology driven data mining, comprising:

an informatics system coupled to a plurality of data sources, the informatics system comprising a processor and a non-transitory computer readable medium comprising instructions for;

receiving a clinical text as input from one or more of the plurality of data sources;

creating a graph representation of the input, wherein creating the graph representation of the input comprises parsing the input to create a parse graph by creating a set of evidence spaces comprising a set of related concepts within a distance of one another in the input;

obtaining a graph representation of a semantic ontology, wherein the semantic ontology comprises a set of concepts and a set of relationships;

mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprising the graph representation of the input and the graph of the semantic ontology;

constructing a query based on at least one of the set of concepts or at least one of the set of relationships of the semantic ontology; and

searching the unified graph based on the query to obtain data of the input associated with the at least one concept or the at least one relationship.

2. The system of claim 1, wherein the distance is five plus or minus two.

3. The system of claim 1, wherein mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprises mapping the parse graph to a domain ontology and using the mapping between the parse graph and the domain ontology to map the parse graph to the semantic ontology.

4. The system of claim 3, wherein the domain ontology comprises UMLS-SKOS.

5. A method for ontology driven data mining implemented at an informatics system coupled to a plurality of data sources, comprising:

receiving a clinical text as input from one or more of the plurality of data sources;

creating a graph representation of the input, wherein creating the graph representation of the input comprises parsing the input to create a parse graph by creating a set of evidence spaces comprising a set of related concepts within a distance of one another in the input;

obtaining a graph representation of a semantic ontology, wherein the semantic ontology comprises a set of concepts and a set of relationships;

mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprising the graph representation of the input and the graph of the semantic ontology;

constructing a query based on at least one of the set of concepts or at least one of the set of relationships of the semantic ontology; and

searching the unified graph based on the query to obtain data of the input associated with the at least one concept or the at least one relationship.

6. The method of claim 5, wherein the distance is five plus or minus two.

7. The method of claim 5, wherein mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprises mapping the parse graph to a domain ontology and using the mapping between the parse graph and the domain ontology to map the parse graph to the semantic ontology.

8. The method of claim 7, wherein the domain ontology comprises UMLS-SKOS.

9. A non-transitory computer readable medium, comprising instructions for:

receiving a clinical text as input from one or more of the plurality of data sources;

creating a graph representation of the input, wherein creating the graph representation of the input comprises parsing the input to create a parse graph by creating a set of evidence spaces comprising a set of related concepts within a distance of one another in the input;

obtaining a graph representation of a semantic ontology, wherein the semantic ontology comprises a set of concepts and a set of relationships;

mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprising the graph representation of the input and the graph of the semantic ontology;

constructing a query based on at least one of the set of concepts or at least one of the set of relationships of the semantic ontology; and

searching the unified graph based on the query to obtain data of the input associated with the at least one concept or the at least one relationship.

10. The computer readable medium of claim 9, wherein the distance is five plus or minus two.

11. The computer readable medium of claim 9, wherein mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprises mapping the parse graph to a domain ontology and using the mapping between the parse graph and the domain ontology to map the parse graph to the semantic ontology.

12. The computer readable medium of claim 11, wherein the domain ontology comprises UMLS-SKOS.

13. A system for ontology driven data mining, comprising:

an informatics system coupled to a plurality of data sources, the informatics system comprising a processor and a non-transitory computer readable medium comprising instructions for;

receiving a clinical text as input from one or more of the plurality of data sources;

creating a graph representation of the input, wherein creating the graph representation of the input comprises parsing the input to create a parse graph;

obtaining a graph representation of a semantic ontology, wherein the semantic ontology comprises a set of concepts and a set of relationships;

mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprising the graph representation of the input and the graph of the semantic ontology, wherein mapping the graph representation of the input to the graph representation of the ontology to create a unified graph comprises mapping the parse graph to a domain ontology and using mapping between the parse graph and the domain ontology to map the parse graph to the semantic ontology;

constructing a query based on at least one of the set of concepts or at least one of the set of relationships of the semantic ontology; and

searching the unified graph based on the query to obtain data of the input associated with the at least one concept or the at least one relationship.

14. The system of claim 13, wherein the domain ontology comprises UMLS-SKOS.

15. The system of claim 14, wherein parsing the input comprises creating a set of evidence spaces.

16. The system of claim 15, wherein each evidence space comprises a set of related concepts.

17. The system of claim 16, wherein the set of related concepts are within a distance of one another in the clinical text.

18. The system of claim 17, wherein the distance is five plus or minus two.

19. A method for ontology driven data mining implemented at an informatics system coupled to a plurality of data sources, comprising:

receiving a clinical text as input from one or more of the plurality of data sources;

creating a graph representation of the input, wherein creating the graph representation of the input comprises parsing the input to create a parse graph;

obtaining a graph representation of a semantic ontology, wherein the semantic ontology comprises a set of concepts and a set of relationships;

mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprising the graph representation of the input and the graph of the semantic ontology, wherein mapping the graph representation of the input to the graph representation of the ontology to create a unified graph comprises mapping the parse graph to a domain ontology and using mapping between the parse graph and the domain ontology to map the parse graph to the semantic ontology;

constructing a query based on at least one of the set of concepts or at least one of the set of relationships of the semantic ontology; and

searching the unified graph based on the query to obtain data of the input associated with the at least one concept or the at least one relationship.

20. The method of claim 19, wherein the domain ontology comprises UMLS-SKOS.

21. The method of claim 20, wherein parsing the input comprises creating a set of evidence spaces.

22. The method of claim 21, wherein each evidence space comprises a set of related concepts.

23. The method of claim 22, wherein the set of related concepts are within a distance of one another in the clinical text.

24. The method of claim 23, wherein the distance is five plus or minus two.

25. A non-transitory computer readable medium, comprising instructions for:

receiving a clinical text as input from one or more of the plurality of data sources;

creating a graph representation of the input, wherein creating the graph representation of the input comprises parsing the input to create a parse graph;

obtaining a graph representation of a semantic ontology, wherein the semantic ontology comprises a set of concepts and a set of relationships;

mapping the graph representation of the input to the graph representation of the semantic ontology to create a unified graph comprising the graph representation of the input and the graph of the semantic ontology, wherein mapping the graph representation of the input to the graph representation of the ontology to create a unified graph comprises mapping the parse graph to a domain ontology and using mapping between the parse graph and the domain ontology to map the parse graph to the semantic ontology;

constructing a query based on at least one of the set of concepts or at least one of the set of relationships of the semantic ontology; and

searching the unified graph based on the query to obtain data of the input associated with the at least one concept or the at least one relationship.

26. The computer readable medium of claim 25, wherein the domain ontology comprises UMLS-SKOS.

27. The computer readable medium of claim 26, wherein parsing the input comprises creating a set of evidence spaces.

28. The computer readable medium of claim 27, wherein each evidence space comprises a set of related concepts.

29. The computer readable medium of claim 28, wherein the set of related concepts are within a distance of one another in the clinical text.

30. The computer readable medium of claim 29, wherein the distance is five plus or minus two.