Predictive messaging service for active voice calls
First Claim
Patent Images
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 comprisescomparing 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, anddetermining 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.
1 Assignment
0 Petitions
Accused Products
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.
28 Citations
20 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
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. - View Dependent Claims (11, 12, 13, 14, 15, 16)
-
-
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. - View Dependent Claims (18, 19, 20)
-
Specification