Identifying tasks in messages

• US 10,534,860 B2
• Filed: 05/16/2018
• Issued: 01/14/2020
• Est. Priority Date: 01/22/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Subramanya, Amarnag, Pellicer, Edgar Gonzalez, Agarwal, Shalini
• Primary Examiner(s): Riley, Marcus T
• Application Number:
  US15/981,055
• Publication Number:
  US 20180267948A1
• Time in Patent Office: 608 Days
• Field of Search: None
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 10/1097 Task assignment
• CPC Class Codes: H04L 51/08 Annexed information, e.g. attachments
• CPC Class Codes: H04M 1/72436 for text messaging, e.g. short messaging services [SMS] or e-mails

Abstract

Methods and apparatus are described herein for identifying tasks in messages. In various implementations, natural language processing may be performed on a received message to generate an annotated message. The annotated message may be analyzed pursuant to a grammar. A portion of the message may be classified as a user task entry based on the analysis of the annotated message.

Claims

1. A computer-implemented method for identifying tasks in messages, comprising:

performing, by a computing system, natural language processing on a received message to generate an annotated message, wherein performance of the natural language processing comprises;

identifying a reference to a task interaction entity in the message,

classifying the task interaction entity as a person, location or organization, and

identifying a task action in the message;

analyzing, by the computing system, the annotated message pursuant to a grammar;

classifying, by the computing system, a portion of the message as a user task entry based on the analysis of the annotated message;

identifying, by the computing system, based on the task interaction entity and task action, as well as the analysis of the annotated message, a user interface associated with resolution of the user task entry; and

causing, by the computing system, the user interface to be automatically launched or opened.

2. The computer-implemented method of claim 1, wherein:

the analyzing comprises analyzing, by the computing system, the annotated message pursuant to a plurality of rule paths of the grammar to generate a plurality of candidate user task entries and associated scores; and

the classifying comprises selecting, by the computing system, the user task entry from the plurality of candidate user task entries based on the associated scores.

3. The computer-implemented method of claim 1, further comprising automatically populating, by the computing system, one or more data points associated with the user interface with information based on the analysis of the annotated message.

4. The computer-implemented method of claim 1, wherein the grammar comprises a context-free grammar.

5. The computer-implemented method of claim 1, wherein the identifying comprises selecting, by the computing system from a plurality of distinct URLs, based on the analysis of the annotated message, a URL associated with a network-based resource that is operable by a user to fulfill the task.

6. The computer-implemented method of claim 1, wherein the received message comprises a voicemail, and the method further includes performing speech recognition on the voicemail.

7. The computer-implemented method of claim 1, wherein the received message comprises an email.

8. The computer-implemented method of claim 1, wherein the received message comprises a text message in a short message service (“

SMS”

) format.

9. A computing system for identifying tasks in messages, including memory and one or more processors operable to execute instructions stored in the memory, comprising instructions to:

perform natural language processing on a received message to generate an annotated message, wherein performance of the natural language processing comprises;

identifying a reference to a task interaction entity in the message,

classifying the task interaction entity as a person, location or organization, and

identifying a task action in the message;

analyze the annotated message pursuant to a grammar;

classify a portion of the message as a user task entry based on the analysis of the annotated message;

identify, based on the task interaction entity and task action, as well as the analysis of the annotated message, a user interface associated is fulfillment of the user task entry; and

cause, by the computing system, the user interface to be automatically launched or opened.

10. The computing system of claim 9, wherein the system further comprises instructions to:

analyze the annotated message pursuant to a plurality of rule paths of the grammar to generate a plurality of candidate user task entries and associated scores; and

select the user task entry from the plurality of candidate user task entries based on the associated scores.

11. The computing system of claim 9, further comprising automatically populating, by the computing system, one or more data points associated with the user interface with information based on the analysis of the annotated message.

12. The computing system of claim 9, wherein the identification of the user interface comprises selecting, from a plurality of distinct URLs, based on the analysis of the annotated message, a URL associated with a network-based resource that is operable by a user to fulfill the task.

13. The system of claim 9, wherein the received message comprises a voicemail, and the system further comprises instructions for performing speech recognition on the voicemail.

14. A computer-implemented method, comprising:

performing, by a computing system, natural language processing on a received message sent to a user to generate an annotated message, wherein the received message was composed by one or more other individuals different than the user;

analyzing, by the computing system, the annotated message pursuant to a plurality of rule paths of a grammar to generate a plurality of candidate user tasks assigned to the user by the one or more individuals and associated scores for each of the plurality of rule paths;

determining that one or more of the associated scores exceeds a particular threshold;

selecting, by the computing system, a task from the plurality of candidate user tasks based on the associated scores responsive to a determination that one or more of the associated scores exceeds the particular threshold;

selecting by the computing system from a plurality of distinct user interfaces associated with a plurality of distinct software applications, based on the analysis of the annotated message, a user interface operable by the user to fulfill the task; and

automatically populating, by the computing system, one or more data entry fields of the selected user interface that are editable by the user with information based on the analysis of the annotated message.

15. The computer-implemented method of claim 14, wherein performance of the natural language processing comprises identifying, by the computing system, a reference to a task interaction entity of the task in the message.

16. The computer-implemented method of claim 15, wherein performance of the natural language processing further comprises classifying, by the computing system, the task interaction entity as a person, location or organization.

17. The computer-implemented method of claim 16, wherein performance of the natural language processing further comprises identifying, by the computing system, a task action of the task.

18. The computer-implemented method of claim 17, wherein selecting the user interface comprises selecting the user interface based on the task interaction entity and task action.

19. The computer-implemented method of claim 14, further comprising automatically launching or opening, by the computing system, the user interface.

20. The computer-implemented method of claim 14, further comprising selecting, by the computing system from a plurality of distinct URLs, based on the analysis of the annotated message, a URL associated with a network-based resource that is operable by the user to fulfill the task.