System, method and computer program product for extracting user profiles and habits based on speech recognition and calling history for telephone system advertising

1. A client device configured to receive at least one targeted message from a server in communication with the client device, the client device comprising:

a voice recognition unit configured to convert at least one term in voice data into text data;

a data transmission unit configured to transmit communication data to a server, wherein the communication data includes the text data generated by the voice recognition unit;

a message reception unit configured to:

receive a targeted message from the server, wherein the targeted message is selected by the server from a server database comprising a plurality of messages, in accordance with user profile information that is generated by the server based on the communication data; and

an output unit configured to provide the targeted message, received by the message reception unit, to a user of the client device.

2. The client device according to claim 1 , wherein the voice recognition unit is configured to convert the at least one term in voice data using a hidden Markov model.

3. The client device according to claim 1 , wherein the communication data further includes at least one of a call destination number, a call initiation number, a date of a call, and a time of a call.

4. The client device according to claim 1 , wherein the communication data further includes geographic information corresponding to a location of the client device.

5. The client device according to claim 1 , wherein the communication data further includes geographic information, and wherein the targeted message is selected based at least in part on the geographic information.

6. The client device according to claim 1 , wherein the targeted message includes at least one of sound, text, and image data.

7. The client device according to claim 1 , wherein the targeted message comprises an advertisement.

8. A method of receiving at least one targeted message, the method comprising:

converting at least one term in voice data into text data;

transmitting communication data to a server, wherein the communication data includes the text data; and

receiving a targeted message from the server, wherein the targeted message is selected by the server from a server database comprising a plurality of messages, in accordance with user profile information that is generated by the server based on the communication data.

9. The method according to claim 8 , wherein converting at least one term in voice data into text data includes using at least one hidden Markov model to recognize the at least one term in the voice data.

10. The method according to claim 8 , wherein the communication data further includes at least one of a call destination number, a call initiation number, a date of a call, and a time of a call.

11. The method according to claim 8 , wherein the communication data further includes geographic information corresponding to a location of the client device.

12. The method according to claim 8 , wherein the communication data further includes geographic information, and wherein the targeted message is selected based at least in part on the geographic information.

13. The method according to claim 8 , wherein the targeted message includes at least one of sound, text, and image data.

14. The method according to claim 8 , wherein the targeted message comprises an advertisement.

15. A non-transitory computer-readable medium having instructions stored therein that in response to execution by a client device, cause the client device to perform operations comprising:

converting at least one term in voice data into text data;

transmitting communication data to a server, wherein the communication data includes the text data; and

receiving a targeted message from the server, wherein the targeted message is selected by the server from a server database comprising a plurality of messages, in accordance with user profile information that is generated by the server based on the transmitted communication data.

16. The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise recognizing the at least one term in the voice data by using at least one hidden Markov model.

17. The non-transitory computer-readable medium of claim 15 , wherein the communication data further includes at least one of a call destination number, a call initiation number, a date of a call, and a time of a call.

18. The non-transitory computer-readable medium of claim 15 , wherein the communication data further includes geographic information corresponding to a location of the client device.

19. The non-transitory computer-readable medium of claim 15 , wherein the communication data further includes geographic information, and wherein the targeted message is selected based at least in part on the geographic information.

20. The non-transitory computer-readable medium of claim 15 , wherein the targeted message comprises an advertisement.