Automatic action responses

Patent metadata

Field	Value
Publication number	US-11223584-B2
Application number	US-202017125374-A
Country	US
Kind code	B2
Filing date	Dec 17, 2020
Priority date	Jun 12, 2017
Publication date	Jan 11, 2022
Grant date	Jan 11, 2022

Abstract

Systems and methods are provided that automatically process message input and provide action responses according to the processing results. The automatic action response system may leverage at least one machine-learning algorithm that is trained using a dataset. The provided action responses may comprise of default action responses and/or intelligent action responses that are based at least in part on prior conversational data between a user and a sender. Some intelligent action responses may include text-based replies, which eliminate the need for a user to type a reply on a device screen, thereby saving previous time, conserving device battery life, and preserving the integrity of the device hardware. A portion of a message may be highlighted manually by a user or automatically by the action response system to initiate the automatic action response system. In this way, a more efficient and productive user experience across various devices and applications is achieved.

First claim

What is claimed is:

1. A processor-implemented method of providing action responses, comprising:
detecting at least one portion of a message data received at a computing device;
determining a set of action responses comprising at least an intelligent action response and a default action response, wherein each action response corresponds to the at least one portion of the message data, and wherein the intelligent action response is determined utilizing a database of historical message data;
based on the set of action responses and data from the database containing historical message data, determining to provide, from among the set of action responses, the intelligent action response; and
automatically providing the intelligent action response on the computing device.

2. The processor-implemented method of claim 1 further comprising, based at least in part on a present database of tokens, tokenizing the at least one portion of the message data.

3. The processor-implemented method of claim 2 further comprising highlighting, within a display of the at least one portion of the message data on the computing device, one or more tokens identified by tokenizing the at least one portion of the message data.

4. The processor-implemented method of claim 1 , wherein determining to provide the intelligent action response comprises prioritizing the action responses within the set of action responses, and wherein automatically providing the intelligent action response on the computing device comprises providing a display of the intelligent action response as a prioritized suggestion over the default action response.

5. The processor-implemented method of claim 1 , wherein the intelligent action response is determined utilizing prior conversational history, stored within the database of historical message data, between a user of the computing device and a sender of the message data.

6. The processor-implemented method of claim 1 , wherein determining the set of action responses is based at least in part on a social profile for a user of the computing device.

7. The processor-implemented method of claim 1 , wherein the at least one portion of the message data is text-based.

8. The processor-implemented method of claim 1 , wherein the at least one portion of the message data is speech-based.

9. The processor-implemented method of claim 1 , wherein automatically providing the intelligent action response on the computing device comprises providing the intelligent action response for display with a reply text box.

10. The processor-implemented method of claim 1 , wherein the data from the database containing historical message data indicates action responses previously suggested to a user of the computing device and whether the action responses were accepted by the user.

11. A computer device comprising:
at least one processing unit;
at least one memory storing processor-executable instructions that, when executed by the at least one processing unit, cause the computer device to:
detect at least one portion of a message data received at a computing device;
determine a set of action responses comprising at least an intelligent action response and a default action response, wherein each action response corresponds to the at least one portion of the message data, and wherein the intelligent action response is determined utilizing a database of historical message data;
based on the set of action responses and data from the database containing historical message data, determine to provide, from among the set of action responses, the intelligent action response; and
automatically provide the intelligent action response on the computing device.

12. The computer device of claim 11 , wherein determining to provide the intelligent action response comprises prioritizing the action responses within the set of action responses, and wherein automatically providing the intelligent action response on the computing device comprises providing a display of the intelligent action response as a prioritized suggestion over the default action response.

13. The computer device of claim 11 , wherein the processor-executable instructions that, when executed by the at least one processing unit, cause the computer device further to:
tokenize at least one portion of the message data; and
highlight, within a display of the at least one portion of the message data on the computing device, one or more tokens identified by tokenizing.

14. The computer device of claim 11 , wherein automatically providing the intelligent action response on the computing device comprises providing the intelligent action response for display with a reply text box.

15. The computer device of claim 11 , wherein automatically providing the intelligent action response on the computing device comprises providing the intelligent action response for display as a pop-up element.

16. A computer storage medium storing instructions for executing, on one or more processors of a computer device, a method of providing action responses, the method comprising:
detecting at least one portion of a message data received at a computing device;
determining a set of action responses comprising at least an intelligent action response and a default action response, wherein each action response corresponds to the at least one portion of the message data, and wherein the intelligent action response is determined utilizing a database of historical message data;
based on the set of action responses and data from the database containing historical message data, determining to provide, from among the set of action responses, the intelligent action response; and
automatically providing the intelligent action response on the computing device.

17. The computer storage medium of claim 16 , wherein the intelligent action response is determined utilizing prior conversational history, stored within the database of historical message data, between a user of the computing device and a sender of the message data.

18. The computer storage medium of claim 16 , wherein the data from the database containing historical message data indicates action responses previously suggested to a user of the computing device and whether the action responses were accepted by the user.

19. The computer storage medium of claim 16 , wherein automatically providing the intelligent action response on the computing device comprises one of providing the intelligent action response for display with a reply text box and providing the intelligent action response for display as a pop-up element.

20. The computer storage medium of claim 16 , wherein detecting the at least one portion of a message data comprises detecting a user has highlighted the at least one portion of a message data.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Nguyen Amy Huyen Phuoc
• Lee Chia-Jung
• Zhiboedov Ivan Valeryevich
• Cannons Philipp
• Solimeno Rachel Imogen
• Yoo Dong Hwi
• Wang Yamin
• Shokouhi Milad

Classifications

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G06F16/2365

  Ensuring data consistency and integrity · CPC title

• G06Q10/107

  Computer-aided management of electronic mailing [e-mailing] · CPC title

• G06N20/00 Primary

  Machine learning · CPC title