Method and system to augment vehicle domain ontologies for vehicle diagnosis

• US 8,666,982 B2
• Filed: 10/06/2011
• Issued: 03/04/2014
• Est. Priority Date: 10/06/2011
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Rajpathak, Dnyanesh, Khare, Vineet R, Chougule, Rahul
• Primary Examiner(s): Boccio, Vincent F
• Application Number:
  US13/267,173
• Publication Number:
  US 20130091139A1
• Time in Patent Office: 880 Days
• Field of Search: 707/736, 707/737, 707/748, 707/750
• US Class Current: 707/736
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding

Abstract

A document may be received at a processing module. One or more tags may be applied to the document, each tag applied to a term, each tag representing a part of speech. One or more terms may be extracted from the document based on the tag. A weighting assignment parameter may be determined for each of the one or more extracted terms. Based on the weighting assignment parameter associated with each of the extracted terms, it may be determined whether the domain ontology includes the one or more extracted terms. If the domain ontology does not include the one or more extracted terms, the domain ontology may be augmented such that the domain ontology comprises the one or more extracted terms.

Claims

1. A method comprising:

receiving a document;

applying one or more tags to the document, each tag applied to a term, each tag representing a part of speech;

extracting one or more terms from the document based on the tags;

determining a frequency parameter for each of the one or more extracted terms, wherein the frequency parameter is proportional to a logarithm of a total number of documents in the domain ontology divided by a number of documents in which the term appears;

determining, based on the frequency parameter associated with each of the extracted terms, whether a domain ontology comprises the one or more extracted terms; and

augmenting, if the domain ontology does not comprise the one or more extracted terms, such that the domain ontology comprises the one or more extracted terms.

2. The method of claim 1, wherein augmenting, if the domain ontology does not comprise the one or more extracted terms, such that the domain ontology comprises the one or more extracted terms comprises:

rendering semantically the one or more extracted terms not in the domain ontology; and

adding the semantically rendered one or more extracted terms to the domain ontology.

3. The method of claim 1, wherein applying the tags comprises applying a tag to the one or more words corresponding to the part of speech of the word.

4. The method of claim 1, wherein the one or more parts of speech comprise nouns, verbs, conjunctions and prepositions.

5. The method of claim 1, wherein determining the frequency parameter for each of the one or more extracted terms comprises:

generating a sorted list of extracted terms arranged according to frequency parameter.

6. The method of claim 1, wherein extracting the one or more terms from the document based on the tag comprises:

extracting one or more nouns and one or more verbs from the document;

extracting symptoms from the document with one or more nouns and one or more verbs extracted; and

outputting the one or more nouns, verbs, and symptoms to a weight assignment module.

7. The method of claim 1, wherein determining, based on the frequency parameter associated with each of the extracted terms whether the domain ontology comprises the one or more extracted terms comprises:

determining whether the frequency parameter associated with each of the one or more extracted terms is above a threshold frequency parameter;

comparing the one or more extracted terms associated with a frequency parameter above the threshold frequency parameter to existing terms in the domain ontology; and

determining whether the one or more extracted terms match existing terms in the domain ontology.

8. The method of claim 5, wherein determining, based on the frequency parameter associated with each of the extracted terms, whether the domain ontology comprises the one or more extracted terms comprises:

outputting the sorted list of extracted terms arranged according to frequency parameter to a user; and

prompting the user to verify the one or more extracted terms not represented in the domain ontology.

9. A system comprising:

a non-transitory memory; and

a processor to;

receive a document;

apply one or more tags to the document, each tag applied to a term, each tag representing a part of speech;

extract one or more terms from the document based on the tag;

determine a frequency parameter for each of the one or more extracted terms, wherein the frequency parameter is proportional to a logarithm of a total number of documents in the domain ontology divided by a number of documents in which the term appears;

determine, based on the frequency parameter associated with each of the extracted terms, whether a domain ontology comprises the one or more extracted terms; and

augment, if the domain ontology does not comprise the one or more extracted terms, such that the domain ontology comprises the one or more extracted terms.

10. The system of claim 9, wherein to augment, if the domain ontology does not comprise the one or more extracted terms, such that the domain ontology comprises the one or more extracted terms the processor is to:

render semantically the one or more extracted terms not in the domain ontology; and

add the semantically rendered one or more extracted terms to the domain ontology.

11. The system of claim 9, wherein to apply the tag to the one or more words in the document based on one or more parts of speech the processor is to apply a tag to the one or more words corresponding to the part of speech of the word.

12. The system of claim 9, wherein to determine the frequency parameter for each of the one or more extracted terms the processor is to:

generate a sorted list of extracted terms arranged according to frequencies.

13. The system of claim 9, wherein to extract the one or more terms from the document based on the tag the processor is to:

extract one or more nouns and one or more verbs from the document;

extract symptoms from the document with one or more nouns and one or more verbs extracted; and

output the one or more nouns, verbs, and symptoms to a weight assignment module.

14. The system of claim 9, wherein to determine, based on the frequency parameter associated with each of the extracted terms, whether a domain ontology comprises the one or more extracted terms the processor is to:

determine whether the frequency parameter associated with each of the one or more extracted terms is above a threshold frequency parameter;

compare the one or more extracted terms associated with a frequency parameter above the threshold frequency parameter to existing terms in the domain ontology; and

determine whether the one or more extracted terms match existing terms in the domain ontology.

15. The system of claim 9, wherein to determine a frequency parameter for each of the one or more extracted terms the processor is to determine a criticality of the one or more terms.

16. A method comprising:

receiving a technician verbatim;

categorizing one or more terms in the technician verbatim based on one or more types of speech;

applying metadata to the one or more terms based on the categorization;

determining a frequency parameter for each of the one or more terms, wherein the frequency parameter is proportional to a logarithm of a total number of verbatims in the domain ontology divided by a number of verbatims in which the one or more terms appears;

extracting one or more terms from the technician verbatim based on the metadata and the frequency parameter;

determining, based on the frequency parameter, whether an ontology comprises the one or more extracted terms; and

adding, if the ontology does not comprise the one or more extracted terms, the one or more extracted terms to the ontology.

17. The method of claim 16, wherein extracting one or more terms from the technician verbatim based on the metadata comprises extracting one or more nouns corresponding to one or more parts and one or more verbs corresponding to one or more actions from the technician verbatim.

18. The method of claim 16, wherein adding, if the ontology does not comprise the one or more extracted terms, the one or more extracted terms to the ontology comprises:

applying semantics to the one or more extracted terms; and

adding the one or more terms with applied semantics to the ontology.

19. The method of claim 16, wherein determining whether the ontology comprises the one or more extracted terms comprises:

measuring similarity between the one or more extracted terms and one or more terms in the ontology; and

verifying whether the one or more terms matches the one or more terms in the ontology based on the measured similarity.