| CPC H04M 3/42204 (2013.01) [G10L 15/1815 (2013.01); G10L 15/22 (2013.01); G10L 15/30 (2013.01); H04L 65/1046 (2013.01); H04L 65/1069 (2013.01); H04L 65/1096 (2013.01); H04M 3/42365 (2013.01); H04M 3/4365 (2013.01); G10L 2015/088 (2013.01); H04M 2201/40 (2013.01)] | 20 Claims |

|
1. A system for providing a call session in a communication environment between a first communication device associated with a caller user and having first device coordinates in the communication environment and a second communication device associated with a recipient user and having second device coordinates in the communication environment, the system comprising an automated call controller, the automated call controller adapted for being coupled to the first communication device via a first communication link and to the second communication device via a second communication link; wherein
in a forward direction from the first communication device to the second communication device, the automated call controller is configured for:
coupling said first communication device to the automated call controller via the first communication link;
receiving a call initiation audio signal from the first communication device via the first communication link, said call initiation audio signal being indicative of at least one call initiation phrase uttered by the caller user, said call initiation phrase being indicative of the caller user intention to establish said call session and intended for playing back on the second communication device to the recipient user, said call initiation phrase including at least one personality characteristic of the recipient user;
analyzing said call initiation audio signal in order to determine said at least one call initiation phrase, the analyzing of said call initiation audio signal including:
extracting said call initiation phrase uttered by the caller user from said call initiation audio signal;
converting said call initiation phrase to a text form;
performing syntactic analysis of the text form of said call initiation phrase, in order to decompose said call initiation phrase into corresponding phrase elements;
performing semantic interpretation of said phrase elements required for determining said at least one personality characteristic of the recipient user; and
determining said at least one personality characteristic of the recipient user;
finding said second device coordinates of the second communication device in the communication environment by using said at least one personality characteristic of the recipient user;
coupling said second communication device to the automated call controller via the second communication link by using said second device coordinates;
transmitting said call initiation audio signal to said second communication device via said second communication link;
in a backward direction from the second communication device to the first communication device, the automated call controller is configured for:
receiving a recipient user reaction signal from the second communication device via the second communication link provided by the recipient user in response to said call initiation audio signal, said recipient user reaction signal including a recipient response audio signal, said recipient response audio signal is indicative of a recipient user response phrase uttered by the recipient user, said recipient user response phrase being indicative of the recipient user intention to accept the call session or to reject the call session and being intended for playing back on the first communication device to the caller user;
analyzing the recipient response audio signal to determine indication of the recipient user intention to accept the call session or to reject the call session, the analyzing of the recipient response audio signal includes:
extracting said recipient user response phrase uttered by the recipient user from said recipient response audio signal;
converting said recipient user response phrase to a text form;
performing syntactic analysis of the recipient user response phrase, in order to decompose said at least one recipient user response phrase into corresponding phrase elements;
performing semantic interpretation of said phrase elements required for determining the recipient user intention;
determining the recipient user intention either to accept or to reject the call session from the semantically interpreted phrase elements; and
if the recipient user intention is determined as the recipient acceptance intention of the call session, establishing a full-duplex call session between the first and the second communication devices; and exchanging audio signals between the first and second communication devices during said established call session, said audio signals being generated during a voice communication of the caller user and the recipient user.
|