IP Library › Granted Patent US 11,651,013
Granted Patent B2
US 11,651,013 · App. 17/142,295 · Granted May 16, 2023

Context-based text searching

Inventors: Indervir Singh Banipal (Austin, TX); Shikhar Kwatra (San Jose, CA); Rodrigo Goulart Silva (Raleigh, NC); Andrew R. Freed (Cary, NC)
Assignee: International Business Machines Corporation
G06F16/3344G06F16/338G06N20/00
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 11,651,013
App. No.
17/142,295
Granted
May 16, 2023
Kind
B2
Abstract

A request is received from a user to search a document for at least one search term. The document is analyzed to determine contextual meanings associated with the at least one search term. An ordered set of contexts of the at least one search term is constructed. An option of disambiguation is then prompted to the user to select a context of the ordered set of contexts. Search results are presented to the user associated with the selected context of the at least one search term.

Claims (34)

1. A method comprising:

receiving a request from a user to search a document for at least one search term;

analyzing the document to determine contextual meanings associated with the at least one search term, where analyzing the document to determine the contextual meanings associated with the at least one search term includes analyzing an ontological structure to determine concepts related to the at least one search term within the ontological structure, wherein the concepts are selected as the contextual meanings;

constructing an ordered set of contexts of the at least one search term;

prompting an option of disambiguation to the user to select a context of the ordered set of contexts; and

presenting search results to the user associated with the selected context of the at least one search term.

2. The method of claim 1 , wherein constructing the ordered set of contexts is based on relevancy to the user based on previous context selections.

3. The method of claim 1 , wherein constructing the ordered set of contexts is based on relevancy with respect to the document.

4. The method of claim 1 , wherein the search results include semantically similar terms related to the selected context of the at least one search term.

5. The method of claim 4 , wherein the semantically similar terms are determined using bidirectional encoder representations from transformers (BERT).

6. The method of claim 1 , wherein constructing the ordered set of contexts is based on relevancy to the user based on user preferences indicated in a set of user training data.

7. A system comprising:

one or more processors; and

one or more computer-readable storage media storing program instructions which, when executed by the one or more processors, are configured to cause the one or more processors to perform a method comprising:

receiving a request from a user to search a document for at least one search term;

analyzing the document to determine contextual meanings associated with the at least one search term, where analyzing the document to determine the contextual meanings associated with the at least one search term includes analyzing an ontological structure to determine concepts related to the at least one search term within the ontological structure, wherein the concepts are selected as the contextual meanings;

constructing an ordered set of contexts of the at least one search term;

prompting an option of disambiguation to the user to select a context of the ordered set of contexts; and

presenting search results to the user associated with the selected context of the at least one search term.

8. The system of claim 7 , wherein constructing the ordered set of contexts is based on relevancy to the user based on previous context selections.

9. The system of claim 7 , wherein constructing the ordered set of contexts is based on relevancy with respect to the document.

10. The system of claim 7 , wherein the search results include semantically similar terms related to the selected context of the at least one search term.

11. The system of claim 10 , wherein the semantically similar terms are determined using bidirectional encoder representations from transformers (BERT).

12. The system of claim 7 , wherein constructing the ordered set of contexts is based on relevancy to the user based on user preferences indicated in a set of user training data.

13. A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising instructions configured to cause one or more processors to perform a method comprising:

receiving a request from a user to search a document for at least one search term;

analyzing the document to determine contextual meanings associated with the at least one search term, where analyzing the document to determine the contextual meanings associated with the at least one search term includes analyzing an ontological structure to determine concepts related to the at least one search term within the ontological structure, wherein the concepts are selected as the contextual meanings;

constructing an ordered set of contexts of the at least one search term;

prompting an option of disambiguation to the user to select a context of the ordered set of contexts; and

presenting search results to the user associated with the selected context of the at least one search term.

14. The computer program product of claim 13 , wherein constructing the ordered set of contexts is based on relevancy to the user based on previous context selections.

15. The computer program product of claim 13 , wherein constructing the ordered set of contexts is based on relevancy with respect to the document.

16. The computer program product of claim 13 , wherein the search results include semantically similar terms related to the selected context of the at least one search term.

17. The computer program product of claim 16 , wherein the semantically similar terms are determined using bidirectional encoder representations from transformers (BERT).

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 6, 2021
From: BANIPAL, INDERVIR SINGH; KWATRA, SHIKHAR; GOULART SILVA, RODRIGO; FREED, ANDREW R.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 054822/0850 →
Continuity (1)
Related Publication 20220215047A1 · Jul 7, 2022