Cognitive auto-fill content recommendation

Patent metadata

Field	Value
Publication number	US-10635748-B2
Application number	US-201715842208-A
Country	US
Kind code	B2
Filing date	Dec 14, 2017
Priority date	Dec 14, 2017
Publication date	Apr 28, 2020
Grant date	Apr 28, 2020

Abstract

Embodiments for cognitively recommending auto-fill content by a processor. Communications generated from one or more applications or devices may be tracked. Auto-fill content extracted from the communications may be recommended to automatically fill into a target application. User reaction to the auto-fill content may be learned to refine user-interaction patterns on the target application or the one or more applications or devices.

First claim

The invention claimed is:

1. A method for cognitively recommending auto-fill content by a processor, comprising:
tracking communications generated from one or more applications or devices;
recommending auto-fill content from the communications to automatically fill into a target application; wherein recommending the auto-fill content further includes extracting the content from a captured screenshot of the communications generated from the one or more applications or devices such that the screenshot captures a virtual image of electronic conversations between users comprising the communications, and automatically filling the auto-fill content into the target application; and
learning user reaction to the auto-fill content to refine user-interaction patterns on the target application or the one or more applications or devices.

2. The method of claim 1 , further including extracting the auto-fill content from the communications based on a plurality of contextual factors.

3. The method of claim 1 , further including:
processing the communications using natural language processing (NLP);
converting an image or video data of the communications to text data; or
converting audio data of the communications to text data.

4. The method of claim 1 , further including synchronizing one or more events of the communications based on chronological order or logical order.

5. The method of claim 1 , further including:
recommending a list of auto-fill content to enable a user to select the auto-fill content from the list of auto-fill content; and
selecting the auto-fill content from a list of auto-fill content.

6. The method of claim 1 , further including initializing a machine learning mechanism using feedback information to learn the user reaction to the auto-fill content and the user-interaction patterns.

7. The method of claim 1 , further including:
merging the communications to generate the auto-fill content for automatically filling the auto-fill content into the target application; or
inferring one or more relationships between values or extrapolating one or more new values based on a cognitive model.

8. A system for cognitively recommending auto-fill content, comprising:
one or more computers with executable instructions that when executed cause the system to:
track communications generated from one or more applications or devices;
recommend auto-fill content from the communications to automatically fill into a target application; wherein recommending the auto-fill content further includes extracting the content from a captured screenshot of the communications generated from the one or more applications or devices such that the screenshot captures a virtual image of electronic conversations between users comprising the communications, and automatically filling the auto-fill content into the target application; and
learn user reaction to the auto-fill content to refine user-interaction patterns on the target application or the one or more applications or devices.

9. The system of claim 8 , wherein the executable instructions further extract the auto-fill content from the communications based on a plurality of contextual factors.

10. The system of claim 8 , wherein the executable instructions further:
process the communications using natural language processing (NLP);
convert an image or video data of the communications to text data; or
convert audio data of the communications to text data.

11. The system of claim 8 , wherein the executable instructions further synchronize one or more events of the communications based on chronological order or logical order.

12. The system of claim 8 , wherein the executable instructions further:
recommend a list of auto-fill content to enable a user to select the auto-fill content from the list of auto-fill content; and
select the auto-fill content from a list of auto-fill content.

13. The system of claim 8 , wherein the executable instructions further initialize a machine learning mechanism using feedback information to learn the user reaction to the auto-fill content and the user-interaction patterns.

14. The system of claim 8 , wherein the executable instructions further:
merge the communications to generate the auto-fill content for automatically filling the auto-fill content into the target application; or
infer one or more relationships between values or extrapolating one or more new values based on a cognitive model.

15. A computer program product for facilitating communications of a user by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that tracks communications generated from one or more applications or devices;
an executable portion that recommends auto-fill content from the communications to automatically fill into a target application; wherein recommending the auto-fill content further includes extracting the content from a captured screenshot of the communications generated from the one or more applications or devices such that the screenshot captures a virtual image of electronic conversations between users comprising the communications, and automatically filling the auto-fill content into the target application; and
an executable portion that learns user reaction to the auto-fill content to refine user-interaction patterns on the target application or the one or more applications or devices.

16. The computer program product of claim 15 , further including an executable portion that:
extracts the auto-fill content from the communications based on a plurality of contextual factors;
merges the communications to generate the auto-fill content for automatically filling the auto-fill content into the target application; or
infers one or more relationships between values or extrapolating one or more new values based on a cognitive model.

17. The computer program product of claim 15 , further including an executable portion that:
processes the communications using natural language processing (NLP);
converts an image or video data of the communications to text data; or
converts audio data of the communications to text data.

18. The computer program product of claim 15 , further including an executable portion that synchronizes one or more events of the communications based on chronological order or logical order.

19. The computer program product of claim 15 , further including an executable portion that:
recommends a list of auto-fill content to enable a user to select the auto-fill content from the list of auto-fill content; and
selects the auto-fill content from a list of auto-fill content.

20. The computer program product of claim 15 , further including an executable portion that initializes a machine learning mechanism using feedback information to learn the user reaction to the auto-fill content and the user-interaction patterns.

Assignees

• IBM

Inventors

• Liu Su
• Calcaterra Jeff
• Zhang Qin Qiong
• Xu Cheng

Classifications

• G06F16/9532 Primary

  Query formulation · CPC title

• G06F40/174 Primary

  Form filling; Merging · CPC title

• G06F40/295

  Named entity recognition · CPC title

• G06F40/274

  Converting codes to words; Guess-ahead of partial word inputs · CPC title

• G06F3/04895

  Guidance during keyboard input operation, e.g. prompting · CPC title