Mere-parsing with boundary and semantic driven scoping

• US 10,061,764 B2
• Filed: 05/15/2015
• Issued: 08/28/2018
• Est. Priority Date: 04/13/2007
• Status: Active Grant

• Current Assignee: Optum360, LLC (UnitedHealth Group Incorporated)
• Original Assignee: A-Life Medical, LLC
• Inventors: Heinze, Daniel T., Morsch, Mark L.
• Primary Examiner(s): Huynh, Cong-Lac
• Application Number:
  US14/713,672
• Publication Number:
  US 20150248396A1
• Time in Patent Office: 1,201 Days
• Field of Search: 715256
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A method for building a tree of parse items involves receiving a plurality of parse items stored in an ordered data structure, processing semantic attributes associated with the plurality of parse items, generating a merged parse item from at least two parse items of the plurality of parse items, and forming a portion of a tree data structure such that the merged parse item is a parent of the at least two parse items.

Claims

1. A method for building a tree of parse items, the method comprising the steps of:

receiving a plurality of parse items stored in an ordered data structure;

processing semantic attributes associated with the plurality of parse items;

generating a merged parse item from at least two parse items of the plurality of parse items, wherein generating comprises;

selecting a first parse item of the plurality of parse items;

selecting a second parse item of the plurality of parse items;

comparing the first parse item against a predetermined set of target semantic data definitions to obtain a first semantic match;

comparing the second parse item against the predetermined set to obtain a second semantic match;

comparing a combined text of the first and second parse items against the predetermined set to obtain a merged semantic match;

determining whether the merged semantic match is better than either the first or second semantic matches by testing semantic goodness; and

merging the first and second parse items responsive to determining that the merged semantic match is better; and

forming a portion of a tree data structure such that the merged parse item is a parent of the at least two parse items.

2. The method of claim 1, wherein the step of processing semantic attributes comprises:

merging semantic attributes with a parse item of the plurality of parse items responsive to determining that the parse item is associated with one or more semantic attributes.

3. The method of claim 1, wherein a parse item of the plurality of parse items is associated with one or more boundary based attributes.

4. A computer-implemented mere-parser system comprising:

a semantic test application configured to test a semantic goodness of a merged semantic match;

a semantic data storage configured to store semantic data received from the semantic test application;

a source data analysis unit comprising a mere-parser application configured to normalize source data, wherein the mere-parser application comprises a parse item bounding system that comprises instructions that when executed cause a processor to;

normalize formatting of the source data;

perform morphological processing on the source data;

normalize special phrases of the source data;

identify boundaries and form parse items from the source data; and

identify propagating attributes of the source data;

a source data storage configured to store source data;

a first bi-directional communication link that couples the semantic test application with the semantic data storage;

a second bi-directional communication link that couples the semantic test application with the source data analysis unit; and

a third bi-directional communication link that couples the source data analysis unit with the source data storage.

5. The system of claim 4 wherein the semantic test application comprises a vector processing application.

6. The system of claim 4, wherein the mere-parser application comprises a linear propagation system.

7. The system of claim 6, wherein the linear propagation system comprises instructions that when executed cause a processor to:

identify a propagating attribute associated with a parse item of a plurality of parse items of the source data;

determine a direction of propagation of the propagating attribute; and

selectively associate the propagating attribute with parse items of the plurality of parse items located in the direction of propagation.

8. The system of claim 4 wherein the mere-parser application comprises a tree building system.

9. The system of claim 8 wherein the tree building system comprises instructions that when executed cause a processor to:

receive parse items stored in an ordered data structure;

process semantic attributes associated with the parse items;

process through the parse items to create at a merged parse item from at least two parse items; and

form a portion of a tree data structure such that the merged parse item is a parent of the at least two parse items.