Call distribution techniques

1. A method comprising:

intercepting an incoming call placed by a caller to a receiver, wherein the incoming call comprises incoming call data;

if a portion of the incoming call data matches a pre-established list of approved callers, forwarding the incoming call to the receiver;

determining if the portion of the incoming call data matches a pre-established list of disapproved callers;

answering the incoming call while playing a ringback tone to the caller for a preset time period;

analyzing incoming call audio during the preset time period to determine if the caller is a human or a machine;

if the caller is determined to be a human and the portion of incoming call data matches the pre-established list of disapproved callers, terminating the call;

if the caller is determined to be a human and the portion of incoming data does not match the pre-established list of disapproved callers, forwarding the incoming call to the receiver; and

if the caller is determined to be a machine, forwarding the incoming call to a honeypot server, wherein the honeypot server stores the incoming call data for later access by the receiver.

2. The method as in claim 1 , further comprising using incoming call data to provide information obtained from the Internet about the caller to the receiver.

3. The method as in claim 2 , wherein using incoming call data to provide information obtained from the Internet about the caller to the receiver uses call forwarding.

4. The method as in claim 1 , wherein analyzing the incoming call audio during the preset time period further comprises calculating an average amplitude of the amount of noise produced during a segment of the incoming call audio and determining if the segment of the incoming call audio is speech to be further analyzed or background noise to be filtered.

5. The method as in claim 4 , wherein analyzing the incoming call audio during the preset time period comprises calculating the distance and regularity of audio spikes produced during a segment of the incoming call audio.

6. The method as in claim 5 , wherein if the audio spikes are closely correlated around each other determining that the caller is likely a machine and if the audio spikes are not closely correlated around each other determining that the caller is likely a human.

7. The method as in claim 1 , wherein analyzing the incoming call audio during the preset time period comprises analyzing segments of silence within the incoming call audio.

8. The method as in claim 7 , wherein analyzing the incoming call audio during the preset time period further comprises applying a smoothing function that masks small segments of silence.

9. The method as in claim 8 , wherein if the segments of silence are extended determining that the caller is likely a human and if the segments of silence are not extended determining that the caller is likely a machine.

10. The method as in claim 1 , wherein analyzing the incoming call audio during the preset time period comprises analyzing segments of incoming call audio that are a preset percentage greater than the average amplitude of the incoming call audio.

11. The method as in claim 10 , wherein if the segments of audio are a preset percentage greater than the average amplitude of the incoming call audio determining that the caller is a likely a machine and if the segments of incoming call audio are not a preset percentage greater than the average amplitude of the incoming call audio determining that the caller is likely a human.

12. The method as in claim 10 , wherein if noise within segments of incoming call audio significantly deviates determining that the caller is a likely a human and if the segments of incoming call audio do not significantly deviate determining that the caller is likely a machine.

13. The method as in claim 12 wherein the calculation of whether noise within segments of incoming call audio significantly deviates uses a smoothing function.

14. The method as in claim 13 wherein the calculation of whether noise within segments of incoming call audio significantly deviates further comprises calculating a probability where highly confident areas of scoring account for 25% and averaging all probabilities account for 75%.

15. The method as in claim 14 , further comprising calculating a confidence score from 0 to 100, wherein the caller is determined to be a machine if the confidence score is greater than 50 and the caller is determined is determined to be a human if the confidence score is 50 or less.

16. A method comprising:

a) intercepting an incoming call placed by a caller to a receiver, wherein the incoming call comprises incoming call data;

b) answering the incoming call while playing a ringback tone for a preset time period to the caller;

c) analyzing the incoming call audio during the preset time period to determine if the caller is a human or a machine, comprising the following steps:

1) calculating the average amplitude for the amount of noise produced during a segment of the incoming call audio;

2) calculating the distance and regularity of audio spikes produced during a segment of the incoming call audio;

3) analyzing segments of silence within the incoming call audio; and

4) analyzing segments of the incoming call audio that are a preset percentage greater than the average amplitude of the incoming call audio;

5) determining that the incoming call audio may be from a human if there is a high level of repetitive noise; and

6) determining that the incoming call audio may be from a machine if there is significant audio determined to be robotic, if there is significant audio that is not background noise and if there are many consistent spikes in the incoming call audio;

d) if the caller is determined to be a human and the portion of incoming data does not match a pre-established list of disapproved callers, forwarding the incoming call to the receiver; and

e) if the caller is determined to be a machine, forwarding the call to a honeypot server.

17. The method of claim 16 further comprising:

if a portion of the incoming call data matches a pre-established list of approved callers, forwarding the incoming call to the receiver.

18. The method of claim 17 further comprising accessing additional information about the caller beyond the incoming call data and presenting that additional information to the receiver prior to forwarding the incoming call to the receiver.

19. A method comprising:

a) intercepting an incoming call placed by a caller to a receiver, wherein the incoming call comprises incoming call data;

b) answering the incoming call while playing a ringback tone for a preset time period to the caller;

c) analyzing the incoming call audio during the preset time period to determine if the caller is a human or a machine, comprising the following steps:

1) calculating the average amplitude for the amount of noise produced during a segment of the incoming call audio;

2) calculating the distance and regularity of audio spikes produced during a segment of the incoming call audio;

3) analyzing segments of silence within the incoming call audio;

4) analyzing segments of the incoming call audio that are a preset percentage greater than the average amplitude of the incoming call audio; and

5) smoothing the analysis to screen and exclude segments that likely result from poor audio;

d) if the caller is determined to be a human and the portion of incoming data does not match a pre-established list of disapproved callers, forwarding the incoming call to the receiver via a session initiation protocol if there is sufficient network strength based on data throughput and via plain old telephone service if there is insufficient network strength based on data throughput;

e) if the caller is determined to be a human and the portion of incoming data matches a pre-established list of disapproved callers, terminating the call; and

f) if the caller is determined to be a machine, forwarding the call to a honeypot server;

wherein the forwarding the incoming call to the receiver is accomplished.

20. The method as in claim 19 , wherein the session initiation protocol uses a Voice over Internet Protocol.