IP Library Granted Patent US 10,182,148
Granted Patent B2
US 10,182,148 · App. 15/319,117 · Granted Jan 15, 2019

Method and system for filtering undesirable incoming telephone calls

Inventor: Maxime Winkler (Martigny, CH)
Assignee: KATIA SA
H04M3/436G06N99/005H04L63/0861H04L63/10H04M3/4211H04M3/42059H04M3/42102H04M2201/41
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,182,148
App. No.
15/319,117
Granted
Jan 15, 2019
Kind
B2
Abstract

Method of filtering undesirable incoming telephone calls, in which a decision to block a call or to transmit it is based both on the caller's number and on analysis of the caller's voice.

Claims (48)

1. A process for filtering, by use of a filtering system, unwanted incoming telephone calls from a calling party terminal device to a called party terminal device through a telephone network, the filtering system comprising a module connected between the called party terminal device and the telephone network, the method comprising:

determining, on said module or on a server of the filtering system that is connected to said module via the telephone network or a connection, a calling party number of a received call from the calling party terminal device and destined to the called party terminal device;

attributing, on said module or on said server, a confidence score to the calling party number;

based on a first confidence score attributed to the calling party number, transmitting, by using said module, the call to the called party terminal device,

based on a second confidence score attributed to the calling party number, rejecting, by using said module, the call,

based on a third confidence score attributed to the calling party number, asking, by using said module or said server, a calling party employing the calling party terminal device to speak on the calling party terminal device; wherein the third confidence score is different of the second confidence score;

when, based on the third confidence score, the calling party is asked to speak, analyzing, on said module or on said server, the voice of the calling party without transmitting said voice to the called party terminal device; and

based on the analysis of the voice of the calling party, transmitting, by using said module, the call to the called party terminal device, or blocking, by using said module, the call without transmitting the call to the called party.

2. The process as claimed in claim 1 , further comprising, on said module or on said server, an analysis of the face of the calling party.

3. The process as claimed in claim 1 , wherein the analyzing of the voice of the calling party continues after the call has been transmitted to the called party, wherein the call is blocked or blockable when the continued analysis shows that the call is unwanted.

4. The process as claimed in claim 1 , further comprising, on said module or on said server, deciding to call back the calling party in order to check the calling party number and asking the calling party to speak.

5. The process as claimed in claim 3 , comprising a step in the course of which the called party signals an unwanted call, this indication then being used in the decision to reject future calls from the calling party to other called parties, or to ask this calling party to speak.

6. The process as claimed in claim 3 , comprising a step of semantic analysis, on said module or on said server, of the conversation, wherein the decision to transmit a call or the decision to block a call is dependent on this semantic analysis.

7. The process as claimed in claim 6 , the decision to transmit a call or the decision to block a call on the basis of the semantic analysis being dependent on each called party.

8. The process as claimed in claim 3 , comprising a step of analysis of the background noise, of the echoes, of the music and/or of the sound signals transmitted by the calling party, the decision to transmit a call or the decision to block a call being dependent on this analysis.

9. The process as claimed in claim 3 , comprising a step of modeling, on said module or on said server, of the authorized calling parties, along with a step of modeling of the unauthorized calling parties.

10. The process as claimed in claim 3 , in which said decision to transmit the call, to reject the call, or to ask the calling party to speak is based on a machine learning method.

11. The process as claimed in claim 1 , in which said filtering system performs a plausibility analysis for the calling party number and takes this plausibility analysis into account in its decision either to transmit the call, or to reject the call, or to ask the calling party to speak.

12. A process for filtering, by use of a filtering system, an unwanted incoming telephone calls from a calling party terminal device to a called party terminal device through a telephone network, the filtering system comprising a module connected between the called party terminal device and the telephone network, the method comprising:

determining, on said module or on a server of the filtering system that is connected to said module via the telephone network or a connection, a calling party number of a received call from the calling party terminal device and destined to the called party terminal device;

attributing, on said module or on said server, a confidence score to the calling party number;

based on a first confidence score, transmitting, by using said module, the call to the called party terminal device;

based on a second confidence score, rejecting, by said module, the call;

based on a third confidence score, asking, by using said module or said server, a calling party employing the calling party terminal device to speak on the calling party terminal device;

when, based on a third confidence score, the calling party is asked to speak, analyzing, on said module or on said server, the voice of the calling party; and

based on the analysis of the voice of the calling party, transmitting, by using said module, the call to the called party terminal device, or blocking, by using said module, the call without transmitting the call to the called party,

wherein said confidence score attributed to the calling party: is dependent on the called party, is based on said voice analysis, or depends on a history of calls made by said calling party being identifying with said voice analysis.

13. A process for filtering, by use of a filtering system, an unwanted incoming telephone calls from a calling party terminal device to a called party terminal device through a telephone network, the filtering system comprising a module connected between the called party terminal device and the telephone network; the method comprising:

determining, on said module or on a server of the filtering system that is connected to said module via the telephone network or a connection, a calling party number of a received call from the calling party terminal device and destined to the called party terminal device;

attributing, on said module or on said server, a confidence score to the calling party number;

based on a first confidence score, transmitting, by using said module, the call to the called party terminal device,

based on a second confidence score, rejecting, by using said module, the call;

based on a third confidence score, asking, by using said module or server, a calling party employing the calling party terminal device to speak on the calling party terminal device;

when, based on a third confidence score, the calling party is asked to speak, analyzing, on said module or on said server, the voice of the calling party; and

based on the analysis of the voice of the calling party, transmitting, by using said module, the call to the called party terminal device, or blocking, by using said module, the call without transmitting the call to the called party,

wherein the process further comprises making, on said module or on said server, a decision to reject the call or to ask the calling party to speak based on the confidence score, and

wherein said decision to reject the call or to ask the calling party to speak being dependent on:

a history of calls made with said calling party number to other called parties; or

data of a profile of the calling party in a directory, on the web and/or in a social network, said profile being checked by using said module or said server.

14. A process for filtering, by use of a filtering system, an unwanted incoming telephone calls from a calling party terminal device to a called party terminal device through a telephone network, the filtering system comprising a module connected between the called party terminal device and the telephone network; the method comprising:

determining, on said module or on a server of the filtering system that is connected to said module via the telephone network or a connection, a calling party number of a received call from the calling party terminal device and destined to the called party terminal device;

attributing, on said module or on said server, a confidence score to the calling party number;

based on a first confidence score, transmitting, by using said module, the call to the called party terminal device;

based on a second confidence score, rejecting, by using said module, the call;

based on a third confidence score, asking, by using said module or server, a calling party employing the calling party terminal device to speak on the calling party terminal device;

when, based on a third confidence score, the calling party is asked to speak, analyzing, on said module or on said server, the voice of the calling party;

based on the analysis of the voice of the calling party, transmitting, by using said module, the call to the called party terminal device, or blocking, by using said module, the call without transmitting the call to the called party; and

authenticating said calling party by said voice analysis and checking if said authentication corresponds to the calling party number.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 28, 2017
From: WINKLER, MAXIME
To: KATIA SA
Reel/Frame 042849/0896 →
Priority Claims (1)
CH 925/14 · Jun 18, 2014 · national
Continuity (1)
Related Publication 20170134574A1 · May 11, 2017