Segmenting and interpreting a document, and relocating document fragments to corresponding sections

• US 10,176,889 B2
• Filed: 02/09/2017
• Issued: 01/08/2019
• Est. Priority Date: 02/09/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Alba, Alfredo, Coden, Anni R., Drews, Clemens, Gruhl, Daniel F., Lewis, Neal R., Mendes, Pablo N., Ramakrishnan, Cartic, Terdiman, Joseph F.
• Primary Examiner(s): Paula, Cesar B
• Assistant Examiner(s): Nguyen, Luu-Phuong T
• Application Number:
  US15/428,429
• Publication Number:
  US 20180225258A1
• Time in Patent Office: 698 Days
• Field of Search: 715209
• CPC Class Codes: G06F 16/17 Details of further file system functions
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 3/038 Control and interface arrangements therefor, e.g. drivers or device-embedded control circuitry
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing
• CPC Class Codes: G06F 40/131 Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• 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 40/237 Lexical tools
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/258 Heading extraction; Automatic titling; Numbering
• 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: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof

Abstract

A computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to receive a document having multiple section headers, segment the document into at least first and second sections based on the section headers, segment items in the first section into fragments and identify a section type for each of the fragments, determine that the identified section type for at least one of the fragments better matches a type of the second section than it matches a type of the first section, and re-locate the at least one of the fragments to the second section.

Claims

1. A computer program product comprising a non-transitory computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

receive a document having section headers;

segment the document into at least first and second sections based on the section headers;

segment items in the first section into fragments including a first fragment and a second fragment;

identify a section type for each of the fragments using multiple section type-specific lexicons that include a first section type-specific lexicon that corresponds to a section type of the first section and a second section type-specific lexicon that corresponds to a section type of the second section, wherein the first fragment is identified as corresponding to a different section type than the second fragment;

determine a first quantity of first fragments of the multiple fragments and a second quantity of second fragments of the multiple fragments, wherein the first fragments correspond to a first section type of the first section and the second fragments correspond to a second section type of a second section of the document;

determine that the first quantity of the first fragments exceeds the second quantity of the second fragments by a predetermined quantity; and

based on exceeding the predetermined quantity, re-locate the second fragments to the second section in the document or reclassify the second fragments to correspond to the first section type.

2. The computer program product of claim 1, wherein the document comprises an electronic health record.

3. The computer program product of claim 1, wherein the items include non-alphabetical and non-numerical symbols.

4. The computer program product of claim 1, wherein, to segment the items into fragments, the program instructions are executable by the processor to cause the processor to identify a portion of the items that match one of the multiple section type-specific lexicons.

5. The computer program product of claim 1, wherein, to segment the items into fragments, the program instructions are executable by the processor to identify individual words in the first section that correspond to one of the multiple section type-specific lexicons.

6. The computer program product of claim 1, wherein, to segment the items into fragments, the program instructions are executable by the processor to identify phrases and sentences in the first section that correspond to one of the multiple section type-specific lexicons.

7. A computer program product comprising a non-transitory computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

segment items in a first section of a document into multiple fragments;

determine a section type of each of the multiple fragments;

determine a first quantity of first fragments of the multiple fragments and a second quantity of second fragments of the multiple fragments, wherein the first fragments correspond to a first section type of the first section and the second fragments correspond to a second section type of a second section of the document;

determine that the first quantity of the first fragments exceeds the second quantity of the second fragments by a predetermined quantity; and

based on exceeding the predetermined quantity, re-locate the second fragments to the second section in the document or reclassify the second fragments to correspond to the first section type.

8. The computer program product of claim 7, wherein the program instructions executable by the processor cause the processor to reclassify the second fragments to correspond to the first section type when the first quantity of the first fragments exceeds the second quantity of the second fragments by the predetermined quantity, and wherein the program instructions are further executable by the processor to cause the processor to update a section type-specific lexicon corresponding to the first section type to reflect the reclassification.

9. The computer program product of claim 7, wherein the program instructions are executable to cause the processor to generate the second section based on exceeding the predetermined quantity.

10. The computer program product of claim 7, wherein the document comprises a written representation of an oral document.

11. A computer program product comprising a non-transitory computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

segment the document into multiple sections, wherein each of the multiple sections corresponds to a respective section type of multiple section types;

segment items in a first section of the multiple sections into multiple fragments, wherein the first section corresponds to a first section type of the multiple section types;

determine a section type of each of the multiple fragments in the first section;

determine whether the multiple fragments include fragments that correspond to different section types and that are interspersed among each other in even proportions; and

based on the multiple fragments in the first section including fragments that correspond to different section types and that are interspersed among each other in even proportions;

determine that the fragments that correspond to different section types and that are interspersed among each other in even proportions do not belong in the first section;

generate a new section corresponding to a section type that corresponds to a section type that is different than the multiple section types; and

re-locate the fragments that correspond to different section types and that are interspersed among each other in even proportions to the new section.

12. The computer program product of claim 11, wherein the program instructions are executable by the processor to cause the processor to determine that the multiple fragments include fragments that correspond to different section types and that are interspersed among each other in even proportions when the fragments that correspond to different section types and that are interspersed among each other in even proportions are in an alternating fashion.