Alias disambiguation

• US 8,744,995 B1
• Filed: 07/30/2012
• Issued: 06/03/2014
• Est. Priority Date: 07/30/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Hewinson, Philip
• Primary Examiner(s): HICKS, MICHAEL J
• Application Number:
  US13/561,621
• Time in Patent Office: 673 Days
• US Class Current: 707/603
• CPC Class Codes: G06F 16/2379 Updates performed during online database operations; commit processing
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 2250/60 logging of communication history, e.g. outgoing or incoming calls, missed calls, messages or URLs logging of telephone numbers H04M1/56, H04M1/57

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for disambiguation of aliases. A method includes selecting a particular alias, selecting one or more past communications in which the particular alias is used, identifying an item of recipient contact information associated with the selected past communication, identifying a contact record associated with the recipient contact information, and for each contact record, generating or updating a score for the alias, and storing the score in association with the contact record.

Claims

1. A computer-implemented method comprising:

obtaining a communication associated with a user;

selecting a term that occurs in a particular position in a body of the communication;

determining that the term does not match a name of a contact included in contact records of the user;

classifying the term as a candidate alias based at least on determining that the term does not match a name of a contact included in the contact records of the user;

in response to classifying the term as a candidate alias, determining that the term occurs in a subset of past communications of the user, the subset of past communications being collectively associated with a subset of multiple existing contact records associated with an address book of the user;

in response to determining that the term occurs in the subset of past communications of the user, generating, for each of the existing contact records of the subset of multiple existing contact records associated with the address book of the user, an updated contact record indicating (i) the term and (ii) a score that represents an estimated confidence that the term corresponds to the updated contact record, wherein the score is generated based at least on the subset of past communications of the user; and

transmitting, for each of the existing multiple contact records, the updated contact record to a mobile device associated with the user.

2. The method of claim 1, wherein in response to determining that the term occurs in the subset of past communications of the user, generating, for each of the existing contact records of the subset of multiple existing contact records associated with the address book of the user, an updated contact record indicating (i) the term and (ii) a score that represents an estimated confidence that the term corresponds to the updated contact record, comprises:

for each past communication of the subset of past communications, identifying contact information associated with the past communication;

for each identified contact information, determining that an existing contact record of the subset of multiple existing contact records is associated with the identified contact information; and

for each of the existing contact records of the subset of contact records, generating the score indicated by a corresponding updated contact record based on a number of times the existing contact record is determined to be associated with contact information that is identified in the subset of past communications.

3. The method of claim 2, wherein generating the score indicated by the corresponding updated contact record is further based on forms of the past communications of the subset of past communications.

4. The method of claim 2, wherein generating the score indicated by the corresponding updated contact record is further based on a particular position of the term in the past communications of the subset of past communications.

5. The method of claim 1, wherein the updated contact record indicates (i) another term and (ii) another score that represents an estimated confidence that the other term corresponds to the updated contact record.

6. The method of claim 1, comprising:

obtaining another communication associated with the user;

selecting another term that occurs in a particular position in a body of the other communication;

determining that the other term does not match a name of a contact included in contact records of the user;

classifying the other term as another candidate alias based at least on determining that the other term does not match a name of a contact included in the contact records of the user;

in response to classifying the other term as another candidate alias, determining that the other term occurs in another subset of past communications of the user, the other subset of past communications being collectively associated with another subset of multiple existing contact records associated with the address book of the user;

in response to determining that the other term occurs in the other subset of past communications of the user, generating, for each of the existing contact records of the other subset of multiple existing contact records associated with the address book of the user, another updated contact record indicating;

(i) the other term and (ii) another score that represents an estimated confidence that the other term corresponds to the updated contact record, wherein the other score is generated based at least on the other subset of past communications of the user; and

;

(i) the term and (ii) the score that represents the estimated confidence that the term corresponds to the updated contact record wherein the score is generated based at least on the subset of past communications of the user; and

transmitting the other updated contact record to the mobile device associated with the user.

7. The method of claim 1, wherein determining that the term occurs in a subset of past communications of the user comprises:

determining that text corresponding to the term occurs in text corresponding to each of the past communications of the subset of past communications of the user.

8. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

obtaining a communication associated with a user;

selecting a term that occurs in a particular position in a body of the communication;

determining that the term does not match a name of a contact included in contact records of the user;

classifying the term as a candidate alias based at least on determining that the term does not match a name of a contact included in the contact records of the user;

in response to classifying the term as a candidate alias, determining that the term occurs in a subset of past communications of the user, the subset of past communications being collectively associated with a subset of multiple existing contact records associated with an address book of the user;

in response to determining that the term occurs in the subset of past communications of the user, generating, for each of the existing contact records of the subset of multiple existing contact records associated with the address book of the user, an updated contact record indicating (i) the term and (ii) a score that represents an estimated confidence that the term corresponds to the updated contact record, wherein the score is generated based at least on the subset of past communications of the user; and

transmitting, for each of the existing multiple contact records, the updated contact record to a mobile device associated with the user.

9. The system of claim 8, wherein in response to determining that the term occurs in the subset of past communications of the user, generating, for each of the existing contact records of the subset of multiple existing contact records associated with the address book of the user, an updated contact record indicating (i) the term and (ii) a score that represents an estimated confidence that the term corresponds to the updated contact record, comprises:

for each past communication of the subset of past communications, identifying contact information associated with the past communication;

for each identified contact information, determining that an existing contact record of the subset of multiple existing contact records is associated with the identified contact information; and

for each of the existing contact records of the subset of contact records, generating the score indicated by a corresponding updated contact record based on a number of times the existing contact record is determined to be associated with contact information that is identified in the subset of past communications.

10. The system of claim 9, wherein generating the score indicated by the corresponding updated contact record is further based on forms of the past communications of the subset of past communications.

11. The system of claim 9, wherein generating the score indicated by the corresponding updated contact record is further based on a particular position of the term in the past communications of the subset of past communications.

12. The system of claim 8, wherein the updated contact record indicates (i) another term and (ii) another score that represents an estimated confidence that the other term corresponds to the updated contact record.

13. The system of claim 8, the instructions comprising:

obtaining another communication associated with the user;

selecting another term that occurs in a particular position in a body of the other communication;

determining that the other term does not match a name of a contact included in contact records of the user;

classifying the other term as another candidate alias based at least on determining that the other term does not match a name of a contact included in the contact records of the user;

in response to classifying the other term as another candidate alias, determining that the other term occurs in another subset of past communications of the user, the other subset of past communications being collectively associated with another subset of multiple existing contact records associated with the address book of the user;

in response to determining that the other term occurs in the other subset of past communications of the user, generating, for each of the existing contact records of the other subset of multiple existing contact records associated with the address book of the user, another updated contact record indicating;

(i) the other term and (ii) another score that represents an estimated confidence that the other term corresponds to the updated contact record, wherein the other score is generated based at least on the other subset of past communications of the user; and

;

(i) the term and (ii) the score that represents the estimated confidence that the term corresponds to the updated contact record wherein the score is generated based at least on the subset of past communications of the user; and

transmitting the other updated contact record to the mobile device associated with the user.

14. The system of claim 8, wherein determining that the term occurs in a subset of past communications of the user comprises:

determining that text corresponding to the term occurs in text corresponding to each of the past communications of the subset of past communications of the user.

15. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

obtaining a communication associated with a user;

selecting a term that occurs in a particular position in a body of the communication;

determining that the term does not match a name of a contact included in contact records of the user;

classifying the term as a candidate alias based at least on determining that the term does not match a name of a contact included in the contact records of the user;

in response to classifying the term as a candidate alias, determining that the term occurs in a subset of past communications of the user, the subset of past communications being collectively associated with a subset of multiple existing contact records associated with an address book of the user;

in response to determining that the term occurs in the subset of past communications of the user, generating, for each of the existing contact records of the subset of multiple existing contact records associated with the address book of the user, an updated contact record indicating (i) the term and (ii) a score that represents an estimated confidence that the term corresponds to the updated contact record, wherein the score is generated based at least on the subset of past communications of the user; and

transmitting, for each of the existing multiple contact records, the updated contact record to a mobile device associated with the user.

16. The medium of claim 15, wherein in response to determining that the term occurs in the subset of past communications of the user, generating, for each of the existing contact records of the subset of multiple existing contact records associated with the address book of the user, an updated contact record indicating (i) the term and (ii) a score that represents an estimated confidence that the term corresponds to the updated contact record, comprises:

for each past communication of the subset of past communications, identifying contact information associated with the past communication;

for each identified contact information, determining that an existing contact record of the subset of multiple existing contact records is associated with the identified contact information; and

for each of the existing contact records of the subset of contact records, generating the score indicated by a corresponding updated contact record based on a number of times the existing contact record is determined to be associated with contact information that is identified in the subset of past communications.

17. The medium of claim 16, wherein generating the score indicated by the corresponding updated contact record is further based on forms of the past communications of the subset of past communications.

18. The medium of claim 16, wherein generating the score indicated by the corresponding updated contact record is further based on a particular position of the term in the past communications of the subset of past communications.

19. The medium of claim 15, wherein the updated contact record indicates (i) another term and (ii) another score that represents an estimated confidence that the other term corresponds to the updated contact record.

20. The medium of claim 15, the instructions comprising:

obtaining another communication associated with the user;

selecting another term that occurs in a particular position in a body of the other communication;

determining that the other term does not match a name of a contact included in contact records of the user;

classifying the other term as another candidate alias based at least on determining that the other term does not match a name of a contact included in the contact records of the user;

in response to classifying the other term as another candidate alias, determining that the other term occurs in another subset of past communications of the user, the other subset of past communications being collectively associated with another subset of multiple existing contact records associated with the address book of the user;

in response to determining that the other term occurs in the other subset of past communications of the user, generating, for each of the existing contact records of the other subset of multiple existing contact records associated with the address book of the user, another updated contact record indicating;

(i) the other term and (ii) another score that represents an estimated confidence that the other term corresponds to the updated contact record, wherein the other score is generated based at least on the other subset of past communications of the user; and

;

(i) the term and (ii) the score that represents the estimated confidence that the term corresponds to the updated contact record wherein the score is generated based at least on the subset of past communications of the user; and

transmitting the other updated contact record to the mobile device associated with the user.

21. The medium of claim 15, wherein determining that the term occurs in a subset of past communications of the user comprises:

determining that text corresponding to the term occurs in text corresponding to each of the past communications of the subset of past communications of the user.