Disambiguation of ambiguous portions of content for processing by automated systems

Patent metadata

Field	Value
Publication number	US-11101037-B2
Application number	US-201615271338-A
Country	US
Kind code	B2
Filing date	Sep 21, 2016
Priority date	Sep 21, 2016
Publication date	Aug 24, 2021
Grant date	Aug 24, 2021

Abstract

Mechanisms are provided for implementing a disambiguation engine for disambiguating content. Electronic content is received from a corpus of electronic content, and analyzed to identify an ambiguous portion of content. The ambiguous portion of content is a portion of the electronic content whose meaning is not made explicit in the ambiguous portion of content. A context associated with the ambiguous portion of content is determined and a set of one or more context based ambiguous content interpretation rules associated with the determined context is applied to the ambiguous portion of content to generate an interpretation of the ambiguous portion of content. The ambiguous portion of content is annotated based on the interpretation to generate disambiguated electronic content which is stored for processing as part of a subsequent operation.

First claim

What is claimed is:

1. A method, in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement a disambiguation engine for disambiguating content that implements the method, comprising:
receiving, by the data processing system, electronic content from a corpus of electronic content;
analyzing, by ingestion logic of the data processing system, the electronic content to identify an ambiguous portion of content, wherein the ambiguous portion of content is a portion of the electronic content whose meaning is not made explicit in the ambiguous portion of content;
determining, by the disambiguation engine of the data processing system, a context associated with the ambiguous portion of content at least by analyzing a context portion of content, in the electronic content, associated with the ambiguous portion of content to identify at least one of header information, metadata information, or key term/phrase information associated with the context portion, and mapping the context portion of content to a predefined context having an associated set of one or more context based ambiguous content interpretation rules;
applying, by the disambiguation engine, the set of one or more context based ambiguous content interpretation rules associated with the predetermined context to the ambiguous portion of content to generate an interpretation of the ambiguous portion of content, wherein each context based ambiguous content interpretation rule in the set of one or more context based ambiguous content interpretation rules maps a corresponding text pattern of ambiguous content with an interpretation of the ambiguous content for the predetermined context;
annotating, by the disambiguation engine, the ambiguous portion of content based on the interpretation to generate disambiguated electronic content; and
storing, by the data processing system, the disambiguated electronic content for processing as part of a subsequent operation.

2. The method of claim 1 , further comprising:
performing, by the data processing system, a cognitive decision support operation based on the disambiguated electronic content to generate a cognitive decision support output.

3. The method of claim 2 , wherein:
the electronic content is a patient electronic medical record corresponding to a patient,
the ambiguous portion of content is a notation generated by a medical practitioner,
the cognitive decision support operation is a treatment recommendation operation executed by a cognitive treatment recommendation system of the data processing system, and the cognitive decision support output is a treatment recommendation for treating a medical condition of the patient.

4. The method of claim 1 , wherein analyzing the electronic content to identify the ambiguous portion of content comprises:
applying one or more ambiguous content portion rules or ambiguous content portion string patterns to extracted features of a portion of the electronic content;
determining if the extracted features of the portion of the electronic content satisfy criteria of one of the one or more ambiguous content portion rules or match one of the ambiguous content portion string patterns; and
marking the portion of the electronic content as an ambiguous portion of content in response to the extracted features of the portion of the electronic content satisfying criteria of one of the one or more ambiguous content portion rules or matching one of the ambiguous content portion string patterns.

5. The method of claim 4 , wherein the criteria of the one or more ambiguous content portion rules comprise one or more of the extracted features being associated with more than one concept unique identifiers (CUIs), the extracted features comprising a numerical string without reference to a type of measurement or measurement units, or a numerical string without reference to an object.

6. The method of claim 1 , wherein determining the context associated with the ambiguous portion of content comprises
correlating the electronic content with other different electronic content from another source that indicates the context for the ambiguous portion of content.

7. The method of claim 1 , wherein determining the context associated with the ambiguous portion of content comprises:
correlating the ambiguous portion of content with medical claim information;
correlating at least one medical code in the medical claim information with the ambiguous portion of content; and
identifying the context for the ambiguous portion of content based on the correlated at least one medical code.

8. The method of claim 1 , wherein each context based ambiguous content interpretation rule in the set of one or more context based ambiguous content interpretation rules comprises a corresponding string pattern, one or more interpretation characteristics specifying a meaning of at least a portion of the string pattern, and a corresponding natural language interpretation text string specifying an interpretation of the string pattern, wherein annotating the ambiguous portion of content based on the interpretation to generate disambiguated electronic content comprises annotating the ambiguous portion of content based on at least one of the one or more interpretation characteristics or the natural language interpretation text string.

9. The method of claim 8 , wherein annotating the ambiguous portion of content based on the interpretation to generate disambiguated electronic content comprises replacing the ambiguous portion of content with a disambiguated equivalent natural language text in the electronic content based on a natural language interpretation text of a matching context based ambiguous content interpretation rule in the set of one or more context based ambiguous content interpretation rules.

10. The method of claim 1 , wherein annotating the ambiguous portion of content based on the interpretation to generate disambiguated electronic content comprises storing metadata in association with the electronic content comprising disambiguation information identifying a disambiguated meaning of the ambiguous portion of content.

11. A computer program product comprising a non-transitory computer readable medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to implement a disambiguation engine which operates to:
receive electronic content from a corpus of electronic content;
analyze the electronic content to identify an ambiguous portion of content, wherein the ambiguous portion of content is a portion of the electronic content whose meaning is not made explicit in the ambiguous portion of content;
determine a context associated with the ambiguous portion of content at least by analyzing a context portion of content, in the electronic content, associated with the ambiguous portion of content to identify at least one of header information, metadata information or key term/phrase information associated with the context portion, and mapping the context portion of content to a predefined context having an associated set of one or more context based ambiguous content interpretation rules;
apply the set of one or more context based ambiguous content interpretation rules associated with the predetermined context to the ambiguous portion of content to generate an interpretation of the ambiguous portion of content, wherein each context based ambiguous content interpretation rule in the set of one or more context based ambiguous content interpretation rule

Assignees

• IBM

Inventors

• Allen Corville O
• Bishop Timothy A

Classifications

• G06F40/289 Primary

  Phrasal analysis, e.g. finite state techniques or chunking · CPC title

• G06F16/24575

  using context · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06F40/30

  Semantic analysis · CPC title