Protecting user data during audio interactions

Abstract

A method for protecting user data during an audio interaction includes various operations performed by a processing system including at least one processor. In one example, the operations include detecting an audio signal that is part of an interaction between a user and another party, converting the audio signal into a string of text, detecting that the interaction is likely to put sensitive data of the user at risk, based on a comparison of the string of text to a library of interactions that are known to put sensitive data at risk, and sending an alert to notify the user that the interaction is likely to put the sensitive data of the user at risk, wherein the alert is sent to prevent the user from providing the sensitive data to the another party, and wherein the method is performed contemporaneously with an occurrence of the interaction.

What is claimed is: 
     
         1 . A method comprising:
 detecting, by a processing system including at least one processor, an audio signal that is part of an in-person interaction between a user and another party, wherein the in-person interaction is unsolicited by the user;   converting, by the processing system, the audio signal into a string of text;   detecting, by the processing system, that the in-person interaction is likely to put sensitive data of the user at risk, based on a comparison of the string of text to a library of known interactions that are known to put sensitive data at risk; and   sending, by the processing system in response to the detecting that the in-person interaction is likely to put the sensitive data of the user at risk, an alert to notify the user that the in-person interaction is likely to put the sensitive data of the user at risk, wherein the alert is timed to be sent before the user provides the sensitive data to the another party, and wherein the alert comprises at least one of: a suggestion to conference via a telephone call another individual who is known to the user whose sensitive data is likely to be put at risk before continuing the in-person interaction or a suggestion to move the in-person interaction to another location,   wherein the method is performed contemporaneously with an occurrence of the in-person interaction.   
     
     
         2 . The method of  claim 1 , where the processing system listens continuously for audio signals including the audio signal. 
     
     
         3 . The method of  claim 1 , wherein the detecting that the in-person interaction is likely to put the sensitive data of the user at risk comprises:
 matching, by the processing system, a word in the string of text to a keyword that is associated with an interaction in the library of known interactions.   
     
     
         4 . The method of  claim 1 , wherein the detecting that the in-person interaction is likely to put the sensitive data of the user at risk comprises:
 matching, by the processing system, a pattern of the interaction between the user and the another party to a pattern of an interaction in the library of known interactions.   
     
     
         5 . The method of  claim 1 , wherein the detecting is further based on a characteristic of the in-person interaction that occurs outside of the audio signal, and wherein the characteristic comprises a characteristic that is known to be associated with interactions that are known to put sensitive data at risk. 
     
     
         6 . The method of  claim 5 , wherein the characteristic is a name of the another party. 
     
     
         7 . The method of  claim 5 , wherein the characteristic is an identification of the another party. 
     
     
         8 . The method of  claim 5 , wherein the characteristic is a time of day of the in-person interaction. 
     
     
         9 . The method of  claim 1 , further comprising:
 placing, by the processing system, the telephone call to the another individual prior to the sending.   
     
     
         10 . The method of  claim 1 , further comprising:
 issuing, by the processing system, a challenge to the another party, wherein the challenge is designed to verify an identity of the another party, and wherein the challenge comprises comparing information provided by the another party to information retrieved by the processing system from the Internet.   
     
     
         11 . The method of  claim 1 , further comprising:
 requesting, by the processing system, a permission from the user to conduct the in-person interaction on behalf of the user; and   placing, by the processing system, the telephone call directly to the another individual in response to receiving the permission from the user to conduct the in-person interaction on behalf of the user.   
     
     
         12 . The method of  claim 1 , wherein the alert comprises at least one of: a visible alert, an audible alert, or a tactile alert. 
     
     
         13 . The method of  claim 1 , wherein the processing system is part of a mobile phone of the user. 
     
     
         14 . The method of  claim 1 , further comprising:
 informing, by the processing system, the user during the in-person interaction to remind quiet until the telephone call is placed with the another individual.   
     
     
         15 . The method of  claim 1 , wherein the another individual is a family member or a caregiver of the user whose sensitive data is likely to be put at risk. 
     
     
         16 . A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising:
 detecting an audio signal that is part of an in-person interaction between a user and another party, wherein the in-person interaction is unsolicited by the user;   converting the audio signal into a string of text;   detecting that the in-person interaction is likely to put sensitive data of the user at risk, based on a comparison of the string of text to a library of known interactions that are known to put sensitive data at risk; and   sending, in response to the detecting that the in-person interaction is likely to put the sensitive data of the user at risk, an alert to notify the user that the in-person interaction is likely to put the sensitive data of the user at risk, wherein the alert is timed to be sent before the user provides the sensitive data to the another party, and wherein the alert comprises at least one of: a suggestion to conference via a telephone call another individual who is known to the user whose sensitive data is likely to be put at risk before continuing the in-person interaction or a suggestion to move the in-person interaction to another location,   wherein the method is performed contemporaneously with an occurrence of the in-person interaction.   
     
     
         17 . The non-transitory computer-readable medium of  claim 16 , wherein the detecting that the in-person interaction is likely to put the sensitive data of the user at risk comprises:
 matching a word in the string of text to a keyword that is associated with an interaction in the library of known interactions.   
     
     
         18 . The non-transitory computer-readable medium of  claim 16 , wherein the detecting that the in-person interaction is likely to put the sensitive data of the user at risk comprises:
 matching a pattern of the interaction between the user and the another party to a pattern of an interaction in the library of known interactions.   
     
     
         19 . The non-transitory computer-readable medium of  claim 16 , wherein the detecting is further based on a characteristic of the in-person interaction that occurs outside of the audio signal, and wherein the characteristic comprises a characteristic that is known to be associated with interactions that are known to put sensitive data at risk. 
     
     
         20 . A device comprising:
 a processing system including at least one processor; and   a non-transitory computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
 detecting an audio signal that is part of an in-person interaction between a user and another party, wherein the in-person interaction is unsolicited by the user; 
 converting the audio signal into a string of text; 
 detecting that the in-person interaction is likely to put sensitive data of the user at risk, based on a comparison of the string of text to a library of known interactions that are known to put sensitive data at risk; and 
 sending, in response to the detecting that the in-person interaction is likely to put the sensitive data of the user at risk, an alert to notify the user that the in-person interaction is likely to put the sensitive data of the user at risk, wherein the alert is timed to be sent before the user provides the sensitive data to the another party, and wherein the alert comprises at least one of: a suggestion to conference via a telephone call another individual who is known to the user whose sensitive data is likely to be put at risk before continuing the in-person interaction or a suggestion to move the in-person interaction to another location, 
 wherein the method is performed contemporaneously with an occurrence of the in-person interaction.