IP Library Granted Patent US 11,429,687
Granted Patent B2
US 11,429,687 · App. 16/598,049 · Granted Aug 30, 2022

Context based URL resource prediction and delivery

Inventors: Mary E. Rudden (Denver, CO); Shikhar Kwatra (Durham, NC); Raghuveer Prasad Nagar (Kota, IN); Reji Jose (Bangalore, IN); Jeremy R. Fox (Georgetown, TX)
Assignee: KYNDRYL, INC.
G06F16/9558G06F16/24575G06F16/9035G06F16/953G06F16/9566G06K9/6267
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 11,429,687
App. No.
16/598,049
Granted
Aug 30, 2022
Kind
B2
Abstract

Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises generating a context-based query through based on a received input; finding a result of the generated query using link prediction algorithm coupled with link prefetching algorithm; and generating a specific link that illustrates and matches the generated context-based query.

Claims (42)

1. A computer-implemented method comprising:

generating a context-based query through based on a received input;

finding a result of the generated query using a link prediction algorithm coupled with a link prefetching algorithm; and

generating a specific link that illustrates and matches the generated context-based query,

wherein the result comprises a compilation of plural resources from plural different source materials in one downloadable format as a downloadable file, and

the link prediction algorithm coupled with link prefetching algorithm comprises linear discriminant analysis classification technique in conjunction with a Random Forest classification technique.

2. The computer-implemented method of claim 1 , wherein generating a query through a program comprises ranking each of the one or more link resources using a rank and retrieve algorithm that considers factors selected from a group consisting of:

user preferences via a user profile, popularity of a link, trending topics, browser history of the user, quality of link, and confidential and privacy settings of the link.

3. The computer-implemented method of claim 1 , wherein finding a result of the generated query comprises matching at least 81% of relevant content of the input.

4. The computer-implemented method of claim 1 , wherein generating a specific link that illustrates and matches the generated query comprises generating a link that specifically directs a user to a specific area of displayable content that satisfies the generated query.

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

selecting one or more links meeting or exceeding at least 81% of a relevant content of the input and presenting the selected one or more links as a downloadable display of multiple links that is collated and presented as a footnote.

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

ranking one or more links meeting or exceeding at least 81% of a relevant content of the received input considering multiple user preferences.

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

modifying a selection and rank of one or more links meeting or exceeding at least 81% of a relevant content of the input using an alternative ranking and retrieving algorithm.

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

compiling multiple portions of different resources that satisfy the generated context-based query into a downloadable file.

9. A computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:

program instructions to generate a context-based query through based on a received input;

program instructions to find a result of the generated query using a link prediction algorithm coupled with a link prefetching algorithm; and

program instructions to generate a specific link that illustrates and matches the generated context-based query,

wherein the link prediction algorithm coupled with link prefetching algorithm comprises a linear discriminant analysis classification technique in conjunction with a Random Forest classification technique.

10. The computer program product of claim 9 , wherein the program instructions to generate a query through a program comprise program instructions to rank each of the one or more link resources using a rank and retrieve algorithm that considers factors selected from a group consisting of:

user preferences via a user profile, popularity of a link, trending topics, browser history of the user, quality of link, and confidential and privacy settings of the link.

11. The computer program product of claim 9 , wherein the program instructions to find a result of the generated query comprise program instructions to match at least 81% of relevant content of the input.

12. The computer program product of claim 9 , wherein the program instructions to generate a specific link that illustrates and match the generated query comprise program instructions to generate a link that specifically directs a user to a specific area of displayable content that satisfies the generated query.

13. The computer program product of claim 9 , one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions further comprise:

program instructions to select one or more links meeting or exceeding at least 81% of a relevant content of the input and present the selected one or more links as a downloadable display of multiple links that is collated and presented as a footnote.

14. A computer system comprising:

one or more computer processors;

one or more computer readable storage media; and

program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising:

program instructions to generate a context-based query through based on a received input;

program instructions to find a result of the generated query using a link prediction algorithm coupled with a link prefetching algorithm; and

program instructions to generate a specific link that illustrates and matches the generated context-based query,

wherein the link prediction algorithm coupled with link prefetching algorithm comprises a linear discriminant analysis classification technique in conjunction with a Random Forest classification technique.

15. The computer system of claim 14 , wherein the program instructions to generate a query through a program comprise program instructions to rank each of the one or more link resources using a rank and retrieve algorithm that considers factors selected from a group consisting of:

user preferences via a user profile, popularity of a link, trending topics, browser history of the user, quality of link, and confidential and privacy settings of the link.

16. The computer system of claim 14 , wherein the program instructions to find a result of the generated query comprise program instructions to match at least 81% of relevant content of the input.

17. The computer system of claim 14 , wherein the program instructions to generate a specific link that illustrates and match the generated query comprise program instructions to generate a link that specifically directs a user to a specific area of displayable content that satisfies the generated query.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 18, 2021
From: INTERNATIONAL BUSINESS MACHINES CORPORATION
To: KYNDRYL, INC.
Reel/Frame 058213/0912 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 10, 2019
From: RUDDEN, MARY E.; KWATRA, SHIKHAR; NAGAR, RAGHUVEER PRASAD; JOSE, REJI; FOX, JEREMY R.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 050676/0574 →