An Ontology-based Automatic Semantic Annotation Approach for Patent Document Retrieval in Product Innovation Design Feng Wang, Lanfen Lin, Zhou Yang College.

Please download to get full document.

View again

of 17
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Information Report
Category:

Software

Published:

Views: 2 | Pages: 17

Extension: PDF | Download: 0

Share
Related documents
Description
Product innovation design  Brain storming  Literature review  Build on existing inventions and develop novel technologies/products Background
Transcript
  • 1 An Ontology-based Automatic Semantic Annotation Approach for Patent Document Retrieval in Product Innovation Design Feng Wang, Lanfen Lin, Zhou Yang College of Computer Science Zhejiang University Energy Procedia 13(2011) 790-800
  • 2 Outline  Background  Semantic representation  Automatic semantic annotation Outline
  • 3 Product innovation design  Brain storming  Literature review  Build on existing inventions and develop novel technologies/products Background
  • 4 Literature review  Refer to existing and relevant patent documents  Professional patent retrieval tools  PatentCafe – keywords and Boolean operator search  BioPatentMiner – keywords and query linkage  SooPAT – keywords and International Patent Classification code  Etc.  Semantic representation is rarely used Background
  • 5 Structure Domain Content (concepts) Syntax (relations)
  • 6 Semantic representation Semantic Representation
  • 7 Patent Document Semantic Representation
  • 8 Patent ontology Semantic Representation  Patent structure ontology  Specific document structure  First page, description, claims, figures (media), etc
  • 9 Patent ontology Semantic Representation  Patent structure ontology  Specific document structure  First page, description, claims, figures (media), etc  Patent content ontology  Basic parameter ontology
  • 10 Patent ontology Semantic Representation  Patent structure ontology  Specific document structure  First page, description, claims, figures (media), etc  Patent content ontology  Basic parameter ontology  Technical feature ontology
  • 11 Semantic representation Semantic Representation  Patent structure ontology  Specific document structure  First page, description, claims, figures (media), etc  Patent content ontology  Basic parameter ontology  Technical feature ontology  Common oncology = syntax  Domain oncology = domain-specific terms
  • 12 Patent document semantics Semantic Representation
  • 13 Automatic semantic annotation Automatic Semantic Annotation  Structure level  Pre-defined template schemes  Regular expression-based parsing  Logical structure: basic parameters, description, claim, etc  Physical structure: headings, sections, subsections, body, etc  Content level  Technical feature level
  • 14 Automatic semantic annotation Automatic Semantic Annotation  Structure level  Content level  Content parsing & filtering: filter out irrelevant sentences  POS tagging: identify nouns, verbs, etc  Entity identification: pick up nouns and verbs  Semantic Recognition  Concept recognition: select nouns by domain oncology (using IPC codes)  Relation recognition: using common oncology  Technical feature level
  • 15 Automatic semantic annotation Automatic Semantic Annotation  Structure level  Content level  Technical feature level  Regular expression method + active learning  prefixTerms + pattern + postfixTerms  A “associated with” B  Given prefixTerms/postfixTerms, learn new patterns  A “is a component of” B  Heuristic rules to remove unreasonable patterns
  • 16 Automatic Semantic Annotation
  • 17 Discussion  Multi-level semantic representation  Allow the precision information extraction  Leverage NLP and domain knowledge  Document type dependent  Difficult to generalize Discussion
Recommended
View more...
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks
SAVE OUR EARTH

We need your sign to support Project to invent "SMART AND CONTROLLABLE REFLECTIVE BALLOONS" to cover the Sun and Save Our Earth.

More details...

Sign Now!

We are very appreciated for your Prompt Action!

x