Messaging account disambiguation

Patent metadata

Field	Value
Publication number	US-10089981-B1
Application number	US-201715454853-A
Country	US
Kind code	B1
Filing date	Mar 9, 2017
Priority date	Mar 9, 2017
Publication date	Oct 2, 2018
Grant date	Oct 2, 2018

Abstract

Methods and systems for performing contact resolution are described herein. When initiating a communications session using a voice activated electronic device, a contact name may be resolved to determine an appropriate contact with which the communications session may be directed to. Contacts from an individual's contact list may be queried to determine a listing of probable contacts associated with the contact name, and contact identifiers associated with the contact may be determined. Using one or more rules for disambiguating between similar contact names, a single contact may be identified, and a communications session with that contact may be initiated.

First claim

What is claimed is:

1. A method, comprising:
receiving, from an electronic device, first audio data representing a first utterance;
receiving a first account identifier associated with the electronic device;
generating first text data representing the first audio data;
determining, using the first text data, that a first intent of the first utterance is for a first communications session to be established with a first recipient electronic device;
determining the first text data includes a first text portion representing a first recipient name;
determining, in a first contact list associated with the first account identifier, a first contact entry that at least substantially matches the first text portion;
determining, in the first contact list, a second contact entry that at least substantially matches the first text portion;
determining first contact information associated with the first contact entry, the first contact information including a first communications identifier and a first additional contact name;
determining second contact information associated with the second contact entry, the second contact information including a second communications identifier and a second additional contact name;
generating second text data representing a request that one of the first additional contact name or the second additional contact name be selected;
generating second audio data representing the second text data; and
causing the electronic device to output audio corresponding to the second audio data.

2. The method of claim 1 , further comprising:
receiving, from the electronic device, third audio data representing a second utterance;
generating third text data representing the third audio data;
determining the third text data includes the first additional contact name; and
causing the first communications session to be established with the first communications identifier.

3. The method of claim 1 , further comprising:
receiving first image data representing a first image associated with the first communications identifier;
receiving second image data representing a second image associated with the second communications identifier; and
causing the first image and the second image to be presented on a display screen associated with the electronic device,
wherein the second text data requests an intended recipient be identified using the first image and the second image.

4. The method of claim 1 , further comprising:
receiving, from the electronic device, third audio data representing a second utterance;
generating third text data representing the third audio data;
determining, using the third text data, that a second intent of the second utterance is for a second communications session be established with a second recipient electronic device;
determining the third text data includes a second text portion representing a second recipient name;
determining, in the first contact list, a third contact entry that at least substantially matches the second text portion;
determining, in the first contact list, a fourth contact entry that at least substantially matches the second text portion;
determining third contact information associated with the third contact entry, the third contact information including a third communications identifier and indicating a first number of communications between a fifth communications identifier associated with the first account identifier and the third communications identifier;
determining fourth contact information associated with the fourth contact entry, the fourth contact information including a fourth communications identifier and indicating a second number of communications between the fifth communications identifier and the fourth communications identifier;
determining a difference between the first number and the second number;
determining that the difference is greater than a threshold value; and
causing the second communications session to be established with the third communications identifier.

5. A method, comprising:
receiving, from a first device, a first request to communicate with an individual having a first name;
determining a first identifier associated with the first request;
determining, in a first contact list associated with the first identifier, a first entry represented by a first contact name;
determining, in the first contact list, a second entry represented by a second contact name;
selecting the first entry based at least in part on the first contact name at least substantially matching the first name;
selecting the second entry based at least in part on the second contact name at least substantially matching the first name;
determining first contact information associated with the first entry, the first contact information including a first additional contact name;
determining second contact information associated with the second entry, the second contact information including a second additional contact name; and
generating first text data requesting a selection of the first additional contact name or the second additional contact name.

6. The method of claim 5 , further comprising:
receiving, from the first device, first audio data representing a first utterance;
generating second text data representing the first audio data;
determining the second text data corresponds to the first request;
generating second audio data representing the second text data; and
causing the first device to output audio corresponding to the second audio data.

7. The method of claim 5 , further comprising:
receiving, from the first device, first audio data representing a first utterance;
generating second text data representing the first audio data;
determining the second text data includes the first additional contact name; and
determining the first entry corresponds to the individual.

8. The method of claim 5 , further comprising:
determining a first confidence score indicating a first likelihood that the first contact name corresponds to the first name;
determining a second confidence score indicating a second likelihood that the second contact name corresponds to the first name;
determining the first confidence score is greater than a predefined confidence score threshold; and
determining the second confidence score is greater than the predefined confidence score threshold.

9. The method of claim 5 , further comprising:
determining, in the first contact list, a third entry represented by a third contact name;
selecting the third entry based at least in part on the third contact name at least substantially matching the first name;
determining third contact information associated with the third entry;
determining the first contact information comprises a first communications identifier;
determining the second contact information comprises a second communications identifier;
determining a third communications identifier is absent from the third contact information; and
determining the third entry is to be ignored.

10. The method of claim 5 , further comprising:
determining, in the first contact list, a third entry represented by a third contact name;
selecting the third entry based at least in part on the third contact name at least substantially matching the first name;
receiving third contact information associated with the third entry;
determining, using the third entry is a duplicate entry of the first entry based, at least in part, on the first contact information and the third contact information both comprising a first communications identifier.

11. The method of claim 5 , further comprising:
determining that the first entry is associated with a first

Assignees

• Amazon Tech Inc

Inventors

• Elangovan Someshwaran
• Nandyal Aparna
• Kancharla Venkatesh
• Rajendran Arun
• Kshirsagar Sumedha Arvind
• Parker Christopher Geiger

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• H04M1/271

  controlled by voice recognition · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title