IP Library › Granted Patent US 11,455,325
Granted Patent B2
US 11,455,325 · App. 16/547,526 · Granted Sep 27, 2022

System and method for dialogue based file index

Inventor: Sung Hyuck Lee (Menlo Park, CA)
Assignee: Samsung Electronics, Co., Ltd.
G06F16/3329G06F16/148G06F16/31G06F16/335G06F16/3334G06F16/3335
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 11,455,325
App. No.
16/547,526
Granted
Sep 27, 2022
Kind
B2
Abstract

An intelligent assistant device for conversation-based indexing and searching of a file. The intelligent assistant device having a processor configured to detect a conversation having at least one user. The processor, responsive to detecting the conversation having at least one user configured to mine the conversation for a file associated with the conversation. The processor, responsive to identifying the file further configured to mine the conversation for contextual keywords associated with the file. The processor also configured to index the contextual keywords to the file.

Claims (81)

1. A method for indexing a file with an intelligent assistant device, the method comprising:

detecting, by an input interface in an electronic device, a conversation having at least one user;

responsive to the detecting of the conversation having the at least one user, monitoring, by the electronic device, the conversation for a file associated with the conversation;

responsive to identifying the file associated with the monitored conversation, mining, by the electronic device, the conversation for contextual keywords associated with the file;

determining whether content keywords exist in the file;

responsive to determining that the content keywords exist in the file, indexing, by the electronic device, the file separate from the conversation by marking the file with an index including the contextual keywords mined from the conversation; and

in response to a query, searching for the file based on the index.

2. The method of claim 1 , wherein the mining the conversation comprises:

responsive to an existence of the content keywords, identifying content keywords matching the contextual keywords;

detecting frequencies of the matching content keywords; and

filtering less relevant contextual keywords based on the detected frequencies.

3. The method of claim 2 , further comprising:

detecting an existence of another conversation associated with the file;

responsive to the existence of the other conversation, mining the other conversation for additional contextual keywords associated with the file;

updating the index for the file with the additional contextual keywords mined from the other conversation; and

filtering the less relevant contextual keywords from the index based on whether they appear in the other conversation.

4. The method of claim 1 , wherein the mining of the conversation comprises:

in response to no content keywords existing, detecting frequencies of the contextual keywords; and

filtering less relevant contextual keywords based on the detected frequencies.

5. The method of claim 4 , further comprising:

detecting an existence of content keywords in an update to the file;

responsive to the existence of the content keywords in the update to the file, mining the conversation for additional contextual keywords associated with the file; and

indexing the additional contextual keywords to the file.

6. The method of claim 1 , further comprising:

sending the index to a cloud database, wherein the file is accessible via a third-party application; and

sending content of the file to a local device.

7. The method of claim 1 , wherein the detecting of the conversation comprises detecting speech from the at least one user.

8. The method of claim 1 , wherein the indexing comprises updating the file with metadata based on the contextual keywords mined from the conversation.

9. A computer program product residing on a non-transitory computer-readable storage medium having a plurality of instructions stored thereon, which, when executed by a processor, cause the processor to:

detect, via an input interface, a conversation having at least one user;

responsive to the detecting of the conversation having the at least one user, monitor the conversation for a file associated with the conversation;

responsive to identifying the file associated with the monitored conversation, mine the conversation for contextual keywords associated with the file;

determine whether content keywords exist in the file;

responsive to determining that the content keywords exist in the file, index the file separate from the conversation by marking the file with an index including the contextual keywords mined from the conversation; and

in response to a query, search for the file based on the index.

10. The computer program product of claim 9 , wherein the instructions that when executed cause the processor to mine the conversation comprise instructions that when executed cause the processor to:

responsive to an existence of the content keywords, identify content keywords matching the contextual keywords;

detect frequencies of the matching content keywords; and

filter less relevant contextual keywords based on the detected frequencies.

11. The computer program product of claim 10 , further comprising instructions that when executed cause the processor to:

detect an existence of the other conversation associated with the file;

responsive to the existence of the other conversation, mine the other conversation for additional contextual keywords associated with the file;

update the index for the file with the additional contextual keywords mined from the other conversation; and

filter the less relevant contextual keywords from the index based on whether they appear in the other conversation.

12. The computer program product of claim 9 , wherein the instructions that when executed cause the processor to mine the conversation comprise instructions that when executed cause the processor to:

in response to no content keywords existing, detect frequencies of the contextual keywords; and

filter less relevant contextual keywords based on the detected frequencies.

13. The computer program product of claim 12 , further comprising instructions that when executed cause the processor to:

detect an existence of content keywords in an update to the file;

responsive to the existence of the content keywords in the update to the file, mine the conversation for additional contextual keywords associated with the file; and

index the additional contextual keywords to the file.

14. The computer program product of claim 9 , further comprising instructions that when executed cause the processor to:

send the index to a cloud database, wherein the file is accessible via a third-party application; and

send content of the file to a local device.

15. An intelligent assistant device for conversation-based indexing and searching of a file, the intelligent assistant device comprising:

an interface configured to detect a conversation having at least one user; and

a processor configured to:

responsive to the detecting the conversation having the at least one user, monitor the conversation for a file associated with the conversation;

responsive to identifying the file associated with the monitored conversation, mine the conversation for contextual keywords associated with the file;

determine whether content keywords exist in the file;

responsive to determining that the content keywords exist in the file, index the file separate from the conversation by marking the file with an index including the contextual keywords mined from the conversation; and

in response to a query, search for the file based on the index.

16. The intelligent assistant device of claim 15 , wherein, to mine the conversation, the processor is configured to:

responsive to an existence of the content keywords, identify content keywords matching the contextual keywords;

detect frequencies of the matching content keywords; and

filter less relevant contextual keywords based on the detected frequencies.

17. The intelligent assistant device of claim 16 , wherein the processor is further configured to:

detect an existence of another conversation associated with the file;

responsive to the existence of the other conversation, mine the other conversation for additional contextual keywords associated with the file;

update the index for the file with the additional contextual keywords mined from the other conversation; and

filter the less relevant contextual keywords from the index based on whether they appear in the other conversation.

18. The intelligent assistant device of claim 15 , wherein, to mine the conversation, the processor is configured to:

in response to no content keywords existing, detect frequencies of the contextual keywords; and

filter less relevant contextual keywords based on the detected frequencies.

19. The intelligent assistant device of claim 18 , wherein the processor is further configured to:

detect an existence of content keywords in an update to the file;

responsive to the existence of the content keywords in the update to the file, mine the conversation for additional contextual keywords associated with the file; and

index the additional contextual keywords to the file.

20. The intelligent assistant device of claim 15 , wherein the processor is further configured to:

send the index to a cloud database, wherein the file is accessible via a third-party application; and

send content of the file to a local device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 22, 2019
From: LEE, SUNG HYUCK
To: SAMSUNG ELECTRONICS CO., LTD
Reel/Frame 050150/0021 →
Continuity (2)
Provisional Application 62721440 · Aug 22, 2018
Related Publication 20200065320A1 · Feb 27, 2020