IP Library Granted Patent US 11,373,037
Granted Patent B2
US 11,373,037 · App. 16/589,622 · Granted Jun 28, 2022

Inferring relation types between temporal elements and entity elements

Inventors: Scott Carrier (Apex, NC); Brendan Bull (Durham, NC); Dwi Sianto Mansjur (Cary, NC); Paul Lewis Felt (Springville, UT)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
G06F40/205G06F16/322G06F40/169G06N5/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,373,037
App. No.
16/589,622
Granted
Jun 28, 2022
Kind
B2
Abstract

Examples described herein provide a computer-implemented method that includes receiving, by a processing device, the span of text, the span of text comprising a plurality of elements including at least an entity element and a temporal element. The method further includes organizing, by the processing device, the span of text as a natural language processing (NLP) parse tree. The method further includes traversing, by the processing device, the NLP parse tree by concatenating individual nodes of the span of text to generate the relation type between the entity element and the temporal element. The method further includes associating, by the processing device, the entity element, the relation type, and the temporal element together.

Claims (46)

1. A computer-implemented method for inferring a relation type between elements of a span of text, the method comprising:

receiving, by a processing device, the span of text, the span of text comprising a plurality of elements including at least an entity element and a temporal element;

organizing, by the processing device, the span of text as a natural language processing (NLP) parse tree;

traversing, by the processing device, the NLP parse tree, wherein the traversing comprises:

identifying the entity element and the temporal element,

identifying individual nodes of the span of text between the entity element and the temporal element, and

concatenating the individual nodes of the span of text between the entity element and the temporal element to generate the relation type between the entity element and the temporal element, wherein the relation type is based on the individual nodes of the span of text between the entity element and the temporal element; and

associating, by the processing device, the entity element, the relation type, and the temporal element together.

2. The computer-implemented method of claim 1 , further comprising:

annotating an electronic file with the associated entity element, the relation type, and the temporal element.

3. The computer-implemented method of claim 1 , organizing the span of text further comprises identifying a part of speech associated with each of the plurality elements of the span of text.

4. The computer-implemented method of claim 3 , wherein the part of speech is selected from a group consisting of a verb, a noun, and a preposition.

5. The computer-implemented method of claim 1 , wherein the temporal element is a date.

6. The computer-implemented method of claim 1 , wherein the temporal element is a date and a time.

7. The computer-implemented method of claim 1 , wherein the entity element is a medical element.

8. The computer-implemented method of claim 7 , wherein the medical element is a medical procedure.

9. The computer-implemented method of claim 7 , wherein the medical element is a medication.

10. A system comprising:

a memory comprising computer readable instructions; and

a processing device for executing the computer readable instructions, the computer readable instructions controlling the processing device to perform operations for inferring a relation type between elements of a span of text, the operations comprising:

receiving, by the processing device, the span of text, the span of text comprising a plurality of elements including at least an entity element and a temporal element;

organizing, by the processing device, the span of text as a natural language processing (NLP) parse tree;

traversing, by the processing device, the NLP parse tree, wherein the traversing comprises:

identifying the entity element and the temporal element,

identifying individual nodes of the span of text between the entity element and the temporal element, and

concatenating the individual nodes of the span of text between the entity element and the temporal element to generate the relation type between the entity element and the temporal element, wherein the relation type is based on the individual nodes of the span of text between the entity element and the temporal element; and

associating, by the processing device, the entity element, the relation type, and the temporal element together.

11. The system of claim 10 , wherein the operations further comprise:

annotating an electronic file with the associated entity element, the relation type, and the temporal element.

12. The system of claim 10 , wherein organizing the span of text further comprises identifying a part of speech associated with each of the plurality elements of the span of text.

13. The system of claim 12 , wherein the part of speech is selected from a group consisting of a verb, a noun, and a preposition.

14. The system of claim 10 , wherein the temporal element is a date.

15. The system of claim 10 , wherein the temporal element is a date and a time.

16. The system of claim 10 , wherein the entity element is a medical element.

17. The system of claim 16 , wherein the medical element is a medical procedure.

18. The system of claim 16 , wherein the medical element is a medication.

19. 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 perform operations for inferring a relation type between elements of a span of text, the operations comprising:

receiving, by the processing device, the span of text, the span of text comprising a plurality of elements including at least an entity element and a temporal element;

organizing, by the processing device, the span of text as a natural language processing (NLP) parse tree;

traversing, by the processing device, the NLP parse tree, wherein the traversing comprises:

identifying the entity element and the temporal element,

identifying individual nodes of the span of text between the entity element and the temporal element, and

concatenating the individual nodes of the span of text between the entity element and the temporal element to generate the relation type between the entity element and the temporal element, wherein the relation type is based on the individual nodes of the span of text between the entity element and the temporal element; and

associating, by the processing device, the entity element, the relation type, and the temporal element together.

20. The computer program product of claim 19 , wherein the operations further comprise:

annotating an electronic file with the associated entity element, the relation type, and the temporal element.

Assignments (3)
SECURITY INTEREST Recorded Oct 1, 2025
From: MERATIVE US L.P.; MERGE HEALTHCARE INCORPORATED
To: TCG SENIOR FUNDING L.L.C., AS COLLATERAL AGENT
Reel/Frame 072808/0442 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 21, 2022
From: INTERNATIONAL BUSINESS MACHINES CORPORATION
To: MERATIVE US L.P.
Reel/Frame 061496/0752 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 1, 2019
From: CARRIER, SCOTT; BULL, BRENDAN; MANSJUR, DWI SIANTO; FELT, PAUL LEWIS
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 050587/0402 →