IP Library › Granted Patent US 11,321,522
Granted Patent B1
US 11,321,522 · App. 16/055,029 · Granted May 3, 2022

Artificial intelligence communication assistance for composition utilizing communication profiles

Inventors: Oleksiy Shevchenko (West Vancouver, CA); Ayan Mandal (Oakdale, CA); Bradley Jon Hoover (San Francisco, CA); Joel Tetreault (New York, NY); Maksym Lytvyn (West Vancouver, CA); Dmytro Lider (Kyiv, UA)
Assignee: GRAMMARLY, INC.
G06F40/186G06F17/18G06F40/174G06N20/00H04L67/306
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 11,321,522
App. No.
16/055,029
Granted
May 3, 2022
Kind
B1
Abstract

In embodiments of the present invention improved capabilities are described for artificial intelligence communication assistance for aiding in the composition of electronic communications utilizing user communication profiles.

Claims (77)

1. A method of electronic communication assistance, the method comprising:

receiving a partial electronic communication from a first user and directed to a second user at an artificial intelligence assistant computing facility using a first electronic identifier associated with the first user and a second electronic identifier associated with the second user, the partial electronic communication comprising a communication dialog content in a received language;

extracting a communication context from the partial electronic communication;

encoding the partial electronic communication for processing creating an encoded partial electronic communication;

retrieving from a communication profile database a first communication profile for the first user using the first electronic identifier associated with the first user, wherein the first communication profile comprises a first user communication attribute;

retrieving from the communication profile database a second communication profile for the second user using the second electronic identifier associated with the second user, wherein the second communication profile comprises a second user communication attribute;

processing the encoded partial electronic communication with a processor to generate language that is a compositional change in wording of the communication dialog content of the partial electronic communication that optimizes for impact and effectiveness of the language using at least one of the communication context, the first user communication attribute, or the second user communication attribute, wherein the generated language is in the received language; and

generating, in the received language, a changed electronic communication from the partial electronic communication and the compositional change;

wherein:

generation of the language that is a compositional change uses the first user communication attribute; and

the first user communication attribute is a lexical writing feature based at least in part on a percent of characters per communication.

2. The method of claim 1 , further comprising transmitting the changed electronic communication to the first electronic identifier associated with the first user.

3. The method of claim 1 , further comprising transmitting the changed electronic communication to the second electronic identifier associated with the second user.

4. The method of claim 1 , wherein the language that is the compositional change in wording is derived from representations of previous content and context from a plurality of user profiles stored in the communication profile database which are similar to at least one of the first communication profile or the second communication profile.

5. The method of claim 4 , wherein the processor is trained on large-scale data mixed with prior communication and effective communications from the plurality of user profiles.

6. The method of claim 1 , wherein the processor uses at least one of a machine learning model, deep learning model, or other statistical learning algorithm to generate the language that is the compositional change.

7. The method of claim 1 , wherein the processor generates the language that is the compositional change in wording by optimizing the language as determined by the processor using the second user communication attribute.

8. The method of claim 1 , wherein the processor generates the language that is the compositional change in wording by replicating a communication style of the first user as determined by the processor using the first user communication attribute.

9. The method of claim 1 , wherein the partial electronic communication further comprises a communication goal, and the processor generates the language that is the compositional change in wording by optimizing for impact and effectiveness of the language with respect to the communication goal.

10. The method of claim 1 , wherein the processor generates the language that is the compositional change further using a communication template selected from a plurality of communication templates comprising at least one of prepared text or placeholder locations for defining structural elements for user completion.

11. The method of claim 10 , wherein the processor selects the communication template using at least one of a machine learning model, deep learning model, or statistical learning model to find a most effective communication template based at least in part on the communication dialog content.

12. The method of claim 10 , wherein the plurality of communication templates comprise at least one automatically generated template generated by the processor.

13. The method of claim 10 , wherein the processor selects the communication template by using a machine learning model to score the plurality of communication templates based at least in part on the communication dialog content, the communication context, the first user communication attribute, or the second user communication attribute.

14. The method of claim 1 , wherein the lexical writing feature is based at least in part on a sentence length distribution.

15. A method of electronic communication assistance, the method comprising:

receiving a partial electronic communication from a first user and directed to a second user at an artificial intelligence assistant computing facility using a first electronic identifier associated with the first user and a second electronic identifier associated with the second user, the partial electronic communication comprising a communication dialog content in a received language;

retrieving a communication profile, wherein the communication profile comprises a user communication attribute associated with the first user or the second user;

processing the partial electronic communication with a processor to generate language that is a compositional change in wording for the communication dialog content of the partial electronic communication that optimizes for impact and effectiveness of the language using the user communication attribute, wherein the generated language is in the received language; and

generating, in the received language, a changed electronic communication from the partial electronic communication and the compositional change,

wherein the user communication attribute is a lexical writing feature based at least in part on a percent of characters per communication.

16. The method of claim 15 , further comprising transmitting the changed electronic communication to the electronic identifier associated with the first user.

17. The method of claim 15 , wherein the processor uses at least one of a machine learning model, deep learning model, or other statistical learning algorithm for creating the compositional change.

18. The method of claim 15 , wherein the processor generates the language that is the compositional change further using a communication template selected from a plurality of communication templates comprising at least one of prepared text or placeholder locations for defining structural elements for user completion.

19. A system of electronic communication assistance, the system comprising:

a processor;

a memory; and

one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the processor, wherein the one or more programs include instructions for:

receiving a partial electronic communication from a first user and directed to a second user at an artificial intelligence assistant computing facility using a first electronic identifier associated with the first user and a second electronic identifier associated with the second user, the partial electronic communication comprising a communication dialog content in a received language;

retrieving a second user communication attribute associated with the second user;

processing the partial electronic communication with the processor to generate language that is a compositional change in wording for the communication dialog content of the partial electronic communication that optimizes for impact and effectiveness of the language using the second user communication attribute, wherein the generated language is in the received language; and

generating, in the received language, a changed electronic communication from the partial electronic communication and the compositional change;

wherein the second user communication attribute is a lexical writing feature based at least in part on a percent of characters per communication.

20. The system of claim 19 , wherein the language that is the compositional change in wording is derived from representations of previous content and context from a plurality of user profiles stored in a communication profile database associated with the artificial intelligence assistant computing facility.

21. The system of claim 20 , wherein the instructions are structured to train the processor on large-scale data mixed with prior communication and effective communications from the plurality of user profiles.

22. The system of claim 19 , wherein the instructions are structured to use, in part, at least one of a machine learning model, deep learning model, or other statistical learning algorithm to generate the language that is the compositional change.

23. The system of claim 19 , wherein the instructions are structured to generate the language that is the compositional change in wording by optimizing the language as determined by the processor using the second user communication attribute.

24. The system of claim 19 , wherein the instructions are structured to generate the language that is the compositional change in wording by replicating a communication style of the first user as determined by the processor using a first user communication attribute.

25. The system of claim 19 , wherein the language that is the compositional change in wording is derived from representations of previous content and context from a plurality of user profiles stored in a communication profile database associated with the artificial intelligence assistant computing facility.

26. The system of claim 25 , wherein the instructions are structured to train the processor on large-scale data mixed with prior communication and effective communications from the plurality of user profiles.

27. A method of electronic communication assistance, the method comprising:

receiving a partial electronic communication from a first user and directed to a second user at an artificial intelligence assistant computing facility using a first electronic identifier associated with the first user and a second electronic identifier associated with the second user, the partial electronic communication comprising a communication dialog content in a received language;

extracting a communication context from the partial electronic communication; encoding the partial electronic communication for processing creating an encoded partial electronic communication;

retrieving from a communication profile database a first communication profile for the first user using the first electronic identifier associated with the first user, wherein the first communication profile comprises a first user communication attribute;

retrieving from the communication profile database a second communication profile for the second user using the second electronic identifier associated with the second user, wherein the second communication profile comprises a second user communication attribute;

processing the encoded partial electronic communication with a processor to generate language that is a compositional change in wording of the communication dialog content of the partial electronic communication that optimizes for impact and effectiveness of the language using at least one of the communication context, the first user communication attribute, or the second user communication attribute, wherein the generated language is in the received language; and

generating, in the received language, a changed electronic communication from the partial electronic communication and the compositional change;

wherein:

generation of the language that is a compositional change uses the second user communication attribute; and

the second user communication attribute is a lexical writing feature based at least in part on a number of emoticons.

28. The method of claim 27 , further comprising transmitting the changed electronic communication to the first electronic identifier associated with the first user.

29. The method of claim 27 , wherein the language that is the compositional change in wording is derived from representations of previous content and context from a plurality of user profiles stored in the communication profile database which are similar to at least one of the first communication profile or the second communication profile.

30. A method of electronic communication assistance, the method comprising: receiving a partial electronic communication from a first user and directed to a second user at an artificial intelligence assistant computing facility using a first electronic identifier associated with the first user and a second electronic identifier associated with the second user, the partial electronic communication comprising a communication dialog content in a received language;

retrieving a communication profile, wherein the communication profile comprises a user communication attribute associated with the first user or the second user;

processing the partial electronic communication with a processor to generate language that is a compositional change in wording for the communication dialog content of the partial electronic communication that optimizes for impact and effectiveness of the language using the user communication attribute, wherein the generated language is in the received language; and

generating, in the received language, a changed electronic communication from the partial electronic communication and the compositional change;

wherein the user communication attribute is a lexical writing feature based at least in part on a number of emoticons.

31. The method of claim 30 wherein the processor uses at least one of a machine learning model, deep learning model, or other statistical learning algorithm for creating the compositional change.

32. The method of claim 30 , wherein the processor generates the language that is the compositional change further using a communication template selected from a plurality of communication templates comprising at least one of prepared text or placeholder locations for defining structural elements for user completion.

33. A system of electronic communication assistance, the system comprising:

a processor;

a memory; and

one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the processor, wherein the one or more programs include instructions for:

receiving a partial electronic communication from a first user and directed to a second user at an artificial intelligence assistant computing facility using a first electronic identifier associated with the first user and a second electronic identifier associated with the second user, the partial electronic communication comprising a communication dialog content in a received language;

retrieving a second user communication attribute associated with the second user;

processing the partial electronic communication with the processor to generate language that is a compositional change in wording for the communication dialog content of the partial electronic communication that optimizes for impact and effectiveness of the language using the second user communication attribute, wherein the generated language is in the received language; and

generating, in the received language, a changed electronic communication from the partial electronic communication and the compositional change;

wherein the second user communication attribute is a lexical writing feature based at least in part on a number of emoticons.

Assignments (2)
CHANGE OF NAME Recorded Nov 21, 2025
From: GRAMMARLY, INC.
To: SUPERHUMAN PLATFORM INC.
Reel/Frame 073655/0099 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 21, 2019
From: SHEVCHENKO, OLEKSIY; MANDAL, AYAN; HOOVER, BRADLEY JON; TETREAULT, JOEL; LYTVYN, MAKSYM; LIDER, DMYTRO
To: GRAMMARLY, INC.
Reel/Frame 048391/0900 →
Continuity (1)
Provisional Application 62541203 · Aug 4, 2017
Cited By (2)
US 12,204,852 US 12,333,247