Automatically suggesting a temporal opportunity for and assisting a writer in writing one or more sequel articles via artificial intelligence

• US 10,599,783 B2
• Filed: 12/26/2017
• Issued: 03/24/2020
• Est. Priority Date: 12/26/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Lohia, Pranay, Gurukar, Saket, Gupta, Rishabh, Gupta, Himanshu
• Primary Examiner(s): Colucci, Michael C
• Application Number:
  US15/854,073
• Publication Number:
  US 20190197120A1
• Time in Patent Office: 819 Days
• Field of Search: 704 9, 707613, 707690, 707722, 707724, 707754, 717105, 717141, 382312
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

Methods, systems, and computer program products for automatically suggesting a temporal opportunity for writing one or more sequel articles via artificial intelligence are provided herein. A computer-implemented method includes extracting one or more types of information from a prior written document; automatically determining, based on the extracted information, at least one temporal opportunity for generating a follow-up written document to the prior written document; automatically generating a follow-up written document to the prior written document, the follow-up written document being written in a style that indicates that it is in response to the prior written document, in accordance with the at least one determined temporal opportunity, and based on (i) one or more items of information, related to the extracted information, derived from one or more web sources, and (ii) a writing model attributed to a user.

Claims

1. A computer-implemented method, the method comprising the steps of:

extracting one or more types of information from a prior written document;

automatically determining, based on the extracted information, at least one temporal opportunity for generating a follow-up written document to the prior written document; and

automatically generating a follow-up written document to the prior written document, the follow-up written document being written in a style that indicates that it is in response to the prior written document, in accordance with the at least one determined temporal opportunity, and based on (i) one or more items of information, related to the extracted information, derived from one or more web sources, and (ii) a writing model attributed to a user;

wherein the steps are carried out by at least one computing device.

2. The computer-implemented method of claim 1, wherein the one or more types of information comprise one or more entities mentioned in the prior written document.

3. The computer-implemented method of claim 1, wherein the one or more types of information comprise one or more events mentioned in the prior written document.

4. The computer-implemented method of claim 1, wherein the one or more types of information comprise one or more relationships between (i) one or more entities mentioned in the prior written document and (ii) one or more events mentioned in the prior written document.

5. The computer-implemented method of claim 1, wherein the one or more types of information comprise contextual information pertaining to the prior written document.

6. The computer-implemented method of claim 1, wherein the one or more types of information comprise one or more facts mentioned in the prior written document.

7. The computer-implemented method of claim 1, wherein the one or more types of information comprise one or more information sources used in connection with the prior written document.

8. The computer-implemented method of claim 1, wherein the one or more types of information comprise one or more future predictions mentioned in the prior written document.

9. The computer-implemented method of claim 1, wherein the one or more types of information comprise one or more potential future events mentioned in the prior written document.

10. The computer-implemented method of claim 1, wherein the one or more types of information comprise one or more assumptions on which the prior written document is based.

11. The computer-implemented method of claim 1, wherein said automatically determining at least one temporal opportunity comprises implementing a rule-based system.

12. The computer-implemented method of claim 11, wherein the rule-based system comprises a rule indicating that if the prior written document contains a future prediction, a temporal opportunity for generating a follow-up written document is identified when the future prediction is rendered true or false.

13. The computer-implemented method of claim 11, wherein the rule-based system comprises a rule indicating that if the prior written document contains an assumption on which the prior written document is based, a temporal opportunity for generating a follow-up written document is identified when the assumption changes.

14. The computer-implemented method of claim 11, wherein the rule-based system comprises a rule indicating that if the prior written document mentions an event occurring in a given context with one or more entities, a temporal opportunity for generating a follow-up written document is identified when the event subsequently occurs in the given context with one or more different entities.

15. The computer-implemented method of claim 11, wherein the rule-based system comprises a rule indicating that if the prior written document mentions an event occurring in a given context, a temporal opportunity for generating a follow-up written document is identified when the event subsequently occurs in a different context.

16. The computer-implemented method of claim 1, wherein the generated follow-up written document explicitly refers to the prior written document.

17. The computer-implemented method of claim 1, wherein said automatically generating a follow-up written document comprises automatically generating a follow-up written document having a style that is consistent with the user'"'"'s writing style, based on the writing model attributed to the user.

18. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

extract one or more types of information from a prior written document;

automatically determine, based on the extracted information, at least one temporal opportunity for generating a follow-up written document to the prior written document; and

automatically generate a follow-up written document to the prior written document, the follow-up written document being written in a style that indicates that it is in response to the prior written document, in accordance with the at least one determined temporal opportunity, and based on (i) one or more items of information, related to the extracted information, derived from one or more web sources, and (ii) a writing model attributed to a user.

19. A system comprising:

a memory; and

at least one processor operably coupled to the memory and configured for;

extracting one or more types of information from a prior written document;

automatically determining, based on the extracted information, at least one temporal opportunity for generating a follow-up written document to the prior written document; and

automatically generating a follow-up written document to the prior written document, the follow-up written document being written in a style that indicates that it is in response to the prior written document, in accordance with the at least one determined temporal opportunity, and based on (i) one or more items of information, related to the extracted information, derived from one or more web sources, and (ii) a writing model attributed to a user.

20. A computer-implemented method, the method comprising steps of:

automatically suggesting, based one or more types of information extracted from a prior written document, a temporal opportunity for generating a follow-up written document to the prior written document;

automatically generating, at the suggested temporal opportunity, a follow-up written document to the prior written document based on (i) one or more items of information, related to the extracted information, derived from one or more web sources, and (ii) a writing model attributed to a user;

displaying the generated follow-up written document to the user;

enabling the user to edit the generated follow-up written document;

automatically generating an updated version of the follow-up written document based on editing carried out by the user; and

outputting the updated version of the follow-up written document to the user;

wherein the steps are carried out by at least one computing device.