IP Library › Granted Patent US 11,610,055
Granted Patent B2
US 11,610,055 · App. 17/687,035 · Granted Mar 21, 2023

Systems and methods for analyzing electronic document text

Inventors: Barak Peleg (Givatayim, IL); Dan Padnos (Tel Aviv, IL); Amnon Morag (Tel Aviv, IL); Gilad Lumbroso (Kfar Saba, IL); Yoav Shoham (Tel Aviv, IL); Ori Goshen (Tel Aviv-Jaffa, IL); Barak Lenz (Tel Aviv, IL); Or Dagan (Tel Aviv, IL)
Assignee: AI21 Labs
G06F40/186G06F3/0482G06F40/117G06F40/166G06F40/247G06F40/253G06F40/30
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 11,610,055
App. No.
17/687,035
Filed
Mar 4, 2022
Granted
Mar 21, 2023
Kind
B2
Art Unit
2144
USPC
715/271
Abstract

The presently disclosed embodiments may include a computer readable medium including instructions that when executed by one or more processing devices cause the one or more processing devices to perform a method. The method may include: analyzing an electronic document text; identifying in the electronic document text a first drafted text element to be modified; causing the first drafted text element to be highlighted to a user on a display; generating at least one text output option that conveys a meaning associated with the first drafted text element but includes one or more changes relative to the first drafted text element; and causing the at least one text output option to be shown to the user via the display.

Claims (46)

1. A non-transitory computer readable medium including instructions that when executed by one or more processing devices cause the one or more processing devices to perform a method including:

initiating a writing assistant application in response to input received from a user, the writing assistant application being associated with at least one graphical user interface element shown on a display;

analyzing, using one or more trained models providing a natural language generation function, an electronic document text;

identifying in the electronic document text a first drafted text element to be modified;

causing the first drafted text element to be highlighted to the user on the display;

generating, using the one or more trained models, at least one text output option that conveys a meaning associated with the first drafted text element but includes one or more changes relative to the first drafted text element; and

causing the at least one text output option to be shown to the user via the display.

2. The non-transitory computer readable medium of claim 1 , wherein the analyzing of the electronic document text is initiated in response to input received from the user.

3. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option is not synonymous with the first drafted text element.

4. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option is synonymous with at least a portion of the first drafted text element.

5. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option is generated as a replacement for at least a portion of the first drafted text element.

6. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option is generated to agree with at least one contextual element associated with text in the electronic document text other than the first drafted text element.

7. The non-transitory computer readable medium of claim 1 , wherein analysis of the electronic document text proceeds sentence by sentence.

8. The non-transitory computer readable medium of claim 1 , wherein the first drafted text element includes portions of two or more sentences.

9. The non-transitory computer readable medium of claim 1 , wherein the first drafted text element includes a group of words within a sentence.

10. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option includes at least one complete sentence.

11. The non-transitory computer readable medium of claim 1 , wherein the one or more changes relative to the first drafted text element include a style modification.

12. The non-transitory computer readable medium of claim 1 , wherein the one or more changes relative to the first drafted text element include a modification in grammar.

13. The non-transitory computer readable medium of claim 1 , wherein the one or more changes relative to the first drafted text element include a modification of one or more words included in the first drafted text element.

14. The non-transitory computer readable medium of claim 1 , wherein the method further includes receiving a user selection of the at least one text output option and automatically inserting the user-selected text output option into the document text in place of at least a portion of the first drafted text element.

15. The non-transitory computer readable medium of claim 14 , wherein the user selection of the at least one text output option includes selection of a control element shown on the display in association with the user-selected text output option.

16. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option includes more words than the first drafted text element.

17. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option includes fewer words than the first drafted text element.

18. The non-transitory computer readable medium of claim 1 , wherein no words from the first drafted text element are included in the at least one text output option.

19. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option includes at least one of a change in verb tense, an addition of at least one clause, or a substitution of one or more synonyms relative to the first drafted text element.

20. The non-transitory computer readable medium of claim 1 , wherein the method further includes:

identifying in the electronic document text a second drafted text element to be modified;

causing the second drafted text element to be highlighted to the user on the display;

generating another text output option that conveys a meaning associated with the second drafted text element but includes one or more changes relative to the second drafted text element; and

causing the another text output to be shown to the user via the display.

21. The non-transitory computer readable medium of claim 20 , wherein the second drafted text element occurs in the electronic document text later than the first drafted text element.

22. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option includes two or more text output options, and the method further includes:

receiving a user selection of one of the two or more text output options and automatically inserting the user-selected text output option into the electronic document text in place of the first drafted text element.

23. The non-transitory computer readable medium of claim 1 , wherein the at least one text output option includes two or more text output options, and the method further includes:

receiving a user selection of one of the two or more text output options and automatically generating at least one updated text output option based on the user selection.

24. The non-transitory computer readable medium of claim 23 , wherein the at least one updated text output option is closer to the user selection in at least one of meaning, context, or style than to text output options not selected by the user.

25. The non-transitory computer readable medium of claim 1 , wherein the method further includes: automatically constructing the at least one text output option based on one or more predetermined style parameters.

26. The non-transitory computer readable medium of claim 25 , wherein values for the one or more predetermined style parameters are user selectable.

27. The non-transitory computer readable medium of claim 25 , wherein the one or more predetermined style parameters specify at least one of a level of formality, a level of conciseness, a level of emotion, or a level of politeness.

28. The non-transitory computer readable medium of claim 25 , wherein the one or more predetermined style parameters specify a length to be associated with the at least one text output option.

29. The non-transitory computer readable medium of claim 28 , wherein the length specifies a word count range for the at least one text output option.

30. The non-transitory computer readable medium of claim 1 , wherein the method further includes receiving additional user input and updating the at least one textual output option based on the received additional user input.

31. The non-transitory computer readable medium of claim 1 , wherein the one or more trained models are trained machine learning models.

32. The non-transitory computer readable medium of claim 1 , wherein the writing assistant application is incorporated into word processing software, an email editor, or presentation software.

33. The non-transitory computer readable medium of claim 1 , wherein the at least one graphical user interface element includes at least one of a window, a field, a virtual button, an icon, or a menu item.

34. The non-transitory computer readable medium of claim 1 , wherein the electronic document text includes an email document.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 4, 2022
From: PELEG, BARAK; PADNOS, DAN; MORAG, AMNON; LUMBROSO, GILAD; SHOHAM, YOAV; GOSHEN, ORI; LENZ, BARAK; DAGAN, OR
To: AI21 LABS
Reel/Frame 059174/0887 →
Continuity (6)
Continuation 17592839 · Feb 4, 2022
Continuation PCTUS2020041846 · Jul 13, 2020
Provisional Application 62943493 · Dec 4, 2019
Provisional Application 62882734 · Aug 5, 2019
Provisional Application 62882732 · Aug 5, 2019
Related Publication 20220207236A1 · Jun 30, 2022
Cited By (2)
US 12,346,668 US 12,423,507