Predictive messaging service for active voice calls

• US 9,210,110 B2
• Filed: 08/28/2012
• Issued: 12/08/2015
• Est. Priority Date: 08/28/2012
• Status: Expired due to Fees

• Current Assignee: AT&T Mobility II LLC (AT&T, Inc.)
• Original Assignee: AT&T Mobility II LLC (AT&T, Inc.)
• Inventors: Maria, Arturo
• Primary Examiner(s): Miah, Liton
• Application Number:
  US13/596,412
• Publication Number:
  US 20140066025A1
• Time in Patent Office: 1,197 Days
• Field of Search: 455/414.4
• US Class Current: 1/1
• CPC Class Codes: H04L 51/066 Format adaptation, e.g. format conversion or compression
• CPC Class Codes: H04L 51/58 Message adaptation for wireless communication

Abstract

Concepts and technologies disclosed herein are for a predictive messaging service for active voice calls. A method for predictive messaging may include receiving, at a predictive messaging system, incoming audio associated with an active voice call, converting the audio into text, analyzing the text to predict a message that a user participating in the active voice call is expected to send, creating the message, and sending the message to a network element for delivery to a destination.

Claims

1. A method comprising:

receiving, at a predictive messaging system comprising a processor, incoming audio associated with a voice conversation that occurs during an active voice call between a first user and a second user;

converting, by the predictive messaging system, the incoming audio associated with the voice conversation into text;

analyzing, by the predictive messaging system, the text to predict a message that the first user participating in the active voice call is expected to send as a result of information exchanged during the voice conversation, wherein analyzing the text comprises

comparing the text to a rule, the rule defining a pattern of data and a destination associated with the pattern of data, the pattern of data comprising a plurality of keywords, and

determining whether at least a portion of the text matches at least a portion of the pattern of data;

in response to determining that the at least a portion of the text matches the at least a portion of the pattern of data, creating, by the predictive messaging system, the message, the message associated with at least a portion of the plurality of keywords of the at least a portion of the pattern of data; and

sending, by the predictive messaging system, the message to a network element for delivery to the destination defined by the rule, wherein the destination defined by the rule is not associated with the first user and the second user.

2. The method of claim 1, wherein sending the message to the network element comprises sending the message to:

a short message service center;

an email server;

an instant messaging server;

or

a social networking server.

3. The method of claim 1, further comprising:

identifying a lack of inflection associated with a word of the incoming audio, wherein the text comprises the word; and

ignoring, when creating the message, a keyword of the plurality of keywords determined to match the word based on the lack of inflection associated with the word.

4. The method of claim 1, further comprising storing the text.

5. The method of claim 4, further comprising discarding, after the text is stored, the text in response to determining that the at least a portion of the text does not match the at least a portion of the pattern of data.

6. The method of claim 1, wherein the pattern of data is contained within a user profile associated with the first user.

7. The method of claim 1, wherein the rule further defines an instruction to obtain address information of the first user participating in the active voice call and to include the address information in the message.

8. The method of claim 1, wherein the pattern of data comprises a modification that incorporates user behavior identified by an analysis of a previous communication associated with the first user.

9. The method of claim 1, wherein sending the message to the network element comprises:

sending the message during the active voice call;

or

sending the message after the active voice call.

10. A predictive messaging system comprising:

a processor; and

a memory that stores computer-executable instructions that, when executed by the processor, cause the processor to perform operations comprising

receiving incoming audio associated with a voice conversation that occurs during an active voice call between a first user and a second user,

converting the incoming audio associated with the voice conversation into text,

analyzing the text to predict a message that the first user participating in the active voice call is expected to send as a result of information exchanged during the voice conversation, wherein analyzing the text comprises

comparing the text to a rule, the rule defining a pattern of data and a destination associated with the pattern of data, the pattern of data comprising a plurality of keywords, and

determining whether at least a portion of the text matches at least a portion of the pattern of data,

in response to determining that the at least a portion of the text matches the at least a portion of the pattern of data, creating the message, the message associated with at least a portion of the plurality of keywords of the at least a portion of the pattern of data, and

sending the message to a network element for delivery to the destination defined by the rule, wherein the destination defined by the rule is not associated with the first user and the second user.

11. The predictive messaging system of claim 10, wherein the operations further comprise:

identifying a lack of inflection associated with a word of the incoming audio, wherein the text comprises the word; and

ignoring, when creating the message, a keyword of the plurality of keywords determined to match the word based on the lack of inflection associated with the word.

12. The predictive messaging system of claim 10, wherein the operations further comprise:

storing the text; and

discarding, after storing the text, the text in response to determining that the at least a portion of the text does not match the at least a portion of the pattern of data.

13. The predictive messaging system of claim 10, wherein the pattern of data is contained within a user profile associated with the first user.

14. The predictive messaging system of claim 10, wherein the rule further defines an instruction to obtain address information of the first user participating in the active voice call and to include the address information in the message.

15. The predictive messaging system of claim 10, wherein the pattern of data comprises a modification that incorporates user behavior identified by an analysis of a previous communication associated with the first user.

16. The predictive messaging system of claim 10, wherein sending the message to the network element comprises:

sending the message during the active voice call;

or

sending the message after the active voice call.

17. A computer-readable storage medium that stores computer-executable instructions that, when executed by a processor, cause the processor to perform operations comprising:

receiving incoming audio associated with a voice conversation that occurs during an active voice call between a first user and a second user;

converting the incoming audio associated with the voice conversation into text;

analyzing the text to predict a message that the first user participating in the active voice call is expected to send as a result of information exchanged during the voice conversation, wherein analyzing the text comprises

comparing the text to a rule, the rule defining a pattern of data and a destination associated with the pattern of data, the pattern of data comprising a plurality of keywords, and

determining whether at least a portion of the text matches at least a portion of the pattern of data;

in response to determining that the at least a portion of the text matches the at least a portion of the pattern of data, creating the message, the message associated with at least a portion of the plurality of keywords of the at least a portion of the pattern of data; and

sending the message to a network element for delivery to the destination defined by the rule, wherein the destination defined by the rule is not associated with the first user and the second user.

18. The computer-readable storage medium of claim 17, wherein the operations further comprise:

identifying a lack of inflection associated with a word of the incoming audio, wherein the text comprises the word; and

ignoring, when creating the message, a keyword of the plurality of keywords determined to match the word based on the lack of inflection associated with the word.

19. The computer-readable storage medium of claim 17, wherein the operations further comprise:

storing the text; and

discarding, after storing the text, the text in response to determining that the at least a portion of the text does not match the at least a portion of the pattern of data.

20. The computer-readable storage medium of claim 17, wherein the pattern of data is contained within a user profile.