System and method for identifying unwanted communications using communication fingerprinting

1. A method, in a communication environment including a data processing system comprising a processor and a memory, for identifying communicators as wanted or unwanted based on messages from such communicators, the method comprising:

receiving, by the data processing system, an inbound communication from a communicator;

extracting, by the data processing system, features from the inbound communication;

comparing, by the data processing system, the extracted features to fingerprints stored in a database accessible to the data processing system, the fingerprints including data representative of content features from communications associated with wanted and unwanted communicators;

determining, by the data processing system, a likely identity of the communicator based on at least one match of the extracted features to the fingerprints; and

providing, by the data processing system, the likely identity to a device of a recipient of the inbound communication.

2. The method of claim 1 wherein the inbound communication includes an audio message.

3. The method of claim 2 further comprising transcribing, by the data processing system, the audio message into text.

4. The method of claim 1 wherein the fingerprints comprise content features associated with messages from unwanted or wanted communicators.

5. The method of claim 4 wherein the content features are selected from the group consisting of: phone number, message duration, call frequency, time of call, call recipients, keywords, phrases, speech tone, and speech frequency range.

6. The method of claim 1 further comprising:

determining a degree of overlap between a given one of the fingerprints and the extracted features; and

calculating a score based on the determined degree of overlap.

7. The method of claim 1 further comprising recording the inbound communication by electronically deploying a call answering artificial intelligence computer program that conducts conversations with communicators.

8. A system for identifying communicators as wanted or unwanted based on messages from such communicators, the system comprising:

a processor; and

a memory having executable instructions stored thereon that when executed by the processor cause the processor to:

receive an inbound communication from a communicator;

extract features from the inbound communication;

compare the extracted features to fingerprints stored in a database accessible to the data processing system, the fingerprints including data representative of content features from communications associated with wanted and unwanted communicators;

determine a likely identity of the communicator based on at least one match of the extracted features to the fingerprints; and

provide the likely identity to a device of a recipient of the inbound communication.

9. The system of claim 8 wherein the inbound communication includes an audio message.

10. The system of claim 9 wherein the processor is further configured to transcribe the audio message into text.

11. The system of claim 8 wherein the fingerprints comprise content features associated with messages from unwanted or wanted communicators.

12. The system of claim 11 wherein the content features are selected from the group consisting of: phone number, message duration, call frequency, time of call, call recipients, keywords, phrases, speech tone, and speech frequency range.

13. The system of claim 8 wherein the processor is further configured to:

determine a degree of overlap between a given one of the fingerprints and the extracted features; and

calculate a score based on the determined degree of overlap.

14. The system of claim 8 wherein the processor is further configured to record the inbound communication by electronically deploying a call answering artificial intelligence computer program that conducts conversations with communicators.

15. A method, in a communication environment including a data processing system comprising a processor and a memory, for identifying communicators as wanted or unwanted based on messages from such communicators, the method comprising:

recording, by the data processing system, communications from a plurality of communicators;

determining, by the data processing system, desirability of the plurality of communicators as either wanted or unwanted;

generating, by the data processing system, fingerprints including data representative of message content from the recording of the communications;

storing the fingerprints with corresponding ones of the determined desirability to a database; and

determining, by the data processing system, a desirability of an unknown communicator based on a match of message content from an inbound communication from the unknown communicator to at least one of the fingerprints.

16. The method of claim 15 further comprising:

generating transcripts of the communications from the plurality of communicators; and

converting the transcripts to fingerprints.

17. The method of claim 15 wherein the inbound communication includes a voice message.

18. The method of claim 17 further comprising transcribing, by the data processing system, the voice message into text.

19. The method of claim 15 wherein the fingerprints comprise features of the message content.

20. The method of claim 19 wherein the features are selected from the group consisting of: phone number, message duration, call frequency, time of call, call recipients, keywords, phrases, speech tone, and speech frequency range.