IP Library Granted Patent US 10,484,319
Granted Patent B1
US 10,484,319 · App. 16/360,903 · Granted Nov 19, 2019

Date and/or time resolution

Inventors: Bryan Christopher Horling (Sunnyvale, CA); Ashutosh Shukla (Mountain View, CA); Antoine Jean Bruguier (Milpitas, CA)
Assignee: GOOGLE LLC
H04L51/08
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 10,484,319
App. No.
16/360,903
Granted
Nov 19, 2019
Kind
B1
Abstract

Methods and apparatus are disclosed for resolving multiple interpretations of an ambiguous temporal term of a resource to a subset of the multiple interpretations. In some implementations, a group of one or more messages is identified, an ambiguous temporal term of the messages determined, additional content of the messages determined, and multiple interpretations of the ambiguous temporal term resolved to a subset based on the additional content.

Claims (50)

1. A system, comprising:

at least one network interface;

memory storing instructions; and

one or more processors executing the instructions stored in the memory to cause the one or more processors to:

receive, via the at least one network interface, a first electronic message generated by a user via a client device;

identify, based on the first electronic message, one or more first message terms of the first electronic message;

receive, via the at least one network interface, a second electronic message generated by the user via the client device, the second electronic message being generated subsequent to the first electronic message;

identify, based on the second electronic message, one or more second message terms of the second electronic message;

determine an ambiguous temporal term of the second terms of the second electronic message, the ambiguous temporal term open to multiple interpretations of dates and/or times;

determine a non-temporal term of the first terms of the first electronic message, the non-temporal term in addition to the ambiguous temporal term;

resolve, based on the non-temporal term, the multiple interpretations, of the ambiguous temporal term, to a subset, wherein in resolving the multiple interpretations to the subset one or more of the processors are to:

determine the subset based on an association of the non-temporal term to the subset; and

responsive to receiving the second electronic message:

transmit, to the client device via the at least one network interface, content that causes the client device to present the resolved subset.

2. The system of claim 1 , wherein one or more of the processors, in executing the instructions, are further to, responsive to receiving the second electronic message:

automatically create an electronic calendar entry that includes the resolved subset.

3. The system of claim 2 , wherein the ambiguous temporal term is a time that fails to identify whether it is for an AM time period or a PM time period, the multiple interpretations include the AM time period and the PM time period, and wherein the resolved subset is one of the AM time period and the PM time period.

4. The system of claim 1 , wherein the association of the non-temporal term to the subset is at least one of: an association to a time zone, an association to a time period, an association to one or more dates, an association to a location, and an association to a language.

5. The system of claim 1 , wherein the non-temporal term is a reference to a location.

6. The system of claim 1 , wherein in resolving the multiple interpretations to the subset based on the non-temporal term one or more of the processors are to provide one or more features associated with the ambiguous temporal term and the non-temporal term as input to a trained machine-learning system and receive, as output from the trained machine-learning system, an indication of the subset.

7. The system of claim 1 , wherein the first message is of a first type and the second message is of a second type that is distinct from the first type.

8. A method implemented by one or more processors, the method comprising:

receiving a first electronic message generated by a user via a client device;

identifying, based on the first electronic message, one or more first message terms of the first electronic message;

receiving a second electronic message generated by the user via the client device, the second electronic message being generated subsequent to the first electronic message;

identifying, based on the second electronic message, one or more second message terms of the second electronic message;

determining an ambiguous temporal term of the second terms of the second electronic message, the ambiguous temporal term open to multiple interpretations of dates and/or times;

determining a non-temporal term of the first terms of the first electronic message, the non-temporal term in addition to the ambiguous temporal term;

resolving, based on the non-temporal term, the multiple interpretations, of the ambiguous temporal term, to a subset, wherein resolving the multiple interpretations to the subset includes:

determining the subset based on an association of the non-temporal term to the subset; and

responsive to receiving the second electronic message:

causing the client device to present the resolved subset.

9. The method of claim 8 , further comprising, responsive to receiving the second electronic message:

automatically creating an electronic calendar entry that includes the resolved subset.

10. The method of claim 9 , wherein the ambiguous temporal term is a time that fails to identify whether it is for an AM time period or a PM time period, the multiple interpretations include the AM time period and the PM time period, and wherein the resolved subset is one of the AM time period and the PM time period.

11. The method of claim 8 , wherein the association of the non-temporal term to the subset is at least one of: an association to a time zone, an association to a time period, an association to one or more dates, an association to a location, and an association to a language.

12. The method of claim 8 , wherein the non-temporal term is a reference to a location.

13. The method of claim 8 , wherein resolving the multiple interpretations to the subset based on the non-temporal term includes providing one or more features associated with the ambiguous temporal term and the non-temporal term as input to a trained machine-learning system and receiving, as output from the trained machine-learning system, an indication of the subset.

14. The method of claim 8 , wherein the first message is of a first type and the second message is of a second type that is distinct from the first type.

15. A non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by a computing device, cause the computing device to perform operations comprising:

receiving a first electronic message generated by a user via a client device;

identifying, based on the first electronic message, one or more first message terms of the first electronic message;

receiving a second electronic message generated by the user via the client device, the second electronic message being generated subsequent to the first electronic message;

identifying, based on the second electronic message, one or more second message terms of the second electronic message;

determining an ambiguous temporal term of the second terms of the second electronic message, the ambiguous temporal term open to multiple interpretations of dates and/or times;

determining a non-temporal term of the first terms of the first electronic message, the non-temporal term in addition to the ambiguous temporal term;

resolving, based on the non-temporal term, the multiple interpretations, of the ambiguous temporal term, to a subset, wherein resolving the multiple interpretations to the subset includes:

determining the subset based on an association of the non-temporal term to the subset; and

responsive to receiving the second electronic message:

causing the client device to present the resolved subset.

Assignments (2)
CHANGE OF NAME Recorded Sep 24, 2019
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 050477/0423 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 27, 2019
From: HORLING, BRYAN CHRISTOPHER; SHUKLA, ASHUTOSH; BRUGUIER, ANTOINE JEAN
To: GOOGLE INC.
Reel/Frame 048719/0476 →
Continuity (1)
Continuation 14316604 · Jun 26, 2014