Input/output privacy tool

Patent metadata

Field	Value
Publication number	US-2024211572-A1
Application number	US-202418599700-A
Country	US
Kind code	A1
Filing date	Mar 8, 2024
Priority date	Sep 15, 2017
Publication date	Jun 27, 2024
Grant date	—

Abstract

Various examples described herein are directed to systems and methods for managing an interface between a user and a user computing device. The user computing device may determine that an audio sensor in communication with the user computing device indicates a first command in a user voice of the user, where the first command instructs the user computing device to perform a first task. The user computing device may determine that the audio sensor also indicates a first ambient voice different than the user voice and match the first ambient voice to a first known voice. The user computing device may determine that a second computing device associated with the first known voice is within a threshold distance of the user computing device and select a first privacy level for the first task based at least in part on the first known voice.

First claim

What is claimed is:

1 . A user computing device programmed to interface with a user, the user computing device comprising at least one processor unit programmed to perform operations comprising:
determining that an audio sensor in communication with the at least one processor indicates a first human voice, the first human voice being of the user; determining that the audio sensor indicates a second human voice, the second human voice being different than the first human voice; determining that the second human voice does not match any voice in a set of known human voices; determining that the second human voice has been detected more than a threshold number of times; responsive to determining that the second human voice has been detected more than the threshold number of times, prompting the user to provide a privacy level for the second human voice; determining that the audio sensor indicates a first command in the first human voice and indicates the second human voice, the first command instructing the user computing device to perform a first task; and executing the first task at the privacy level for the second human voice.

2 . The user computing device of claim 1 , the operations further comprising:
determining that the audio sensor indicates a third human voice different than the first human voice and the second human voice; determining that the third human voice does not match any voice in the set of known human voices; and incrementing a record indicating a number of times that the third human voice is detected.

3 . The user computing device of claim 1 , further comprising, adding the second human voice to the set of known human voices.

4 . The user computing device of claim 1 , the determining that the second human voice has been detected more than the threshold number of times comprising determining that stored data describing ambient human voices that were not matched to one of the set of known human voices describes the second human voice more than the threshold number of times.

5 . The user computing device of claim 1 , the determining that the second human voice has been detected more than the threshold number of times comprising determining that the second human voice has been detected more than the threshold number of times in a first time period.

6 . The user computing device of claim 1 , the operations further comprising, before prompting the user to provide the privacy level for the second human voice, causing an audio output device of the user computing device to play a sample of the second human voice to the user.

7 . The user computing device of claim 1 , the operations further comprising:
sending an indication of the second human voice to a remote computing system; receiving, from the remote computing system, identity data describing the second human voice; and before prompting the user to provide the privacy level for the second human voice, providing the identity data describing the second human voice to the user.

8 . The user computing device of claim 1 , the operations further comprising:
determining that the audio sensor indicates a third human voice different than the first human voice; determining that the audio sensor indicates a second command in the first human voice, wherein the second command instructs the user computing device to perform a second task; determining that a second computing device associated with the third human voice is within a threshold distance of the user computing device; after determining that the second computing device associated with the third human voice is within the threshold distance of the user computing device, selecting a privacy level for the second task based at least in part on the second human voice; and executing the second task at the privacy level for the second task.

9 . The user computing device of claim 8 , the operations further comprising:
determining that the audio sensor indicates a third command in the first human voice, wherein the third command instructs the user computing device to perform a third task; determining that the audio sensor indicates the third human voice; determining that the second computing device is not detected within the threshold distance of the user computing device; and after determining that the second computing device is not detected within the threshold distance of the user computing device, executing the third task at a privacy level for the third task that is less private than the privacy level for the second task.

10 . The user computing device of claim 1 , the operations further comprising:
determining that a personal audio device is connected to the user computing device; and before executing the first task at the privacy level for the second human voice, modifying the privacy level for the second human voice based at least in part on the determining that the personal audio device is connected to the user computing device.

11 . A computer-implemented method for interfacing a user computing device with a user, the computer-implemented method comprising:
determining, by the user computing device, that an audio sensor of the user computing device indicates a first human voice, the first human voice being of the user; determining, by the user computing device, that the audio sensor indicates a second human voice, the second human voice being different than the first human voice; determining, by the user computing device, that the second human voice does not match any voice in a set of known human voices; determining, by the user computing device, that the second human voice has been detected more than a threshold number of times; responsive to determining that the second human voice has been detected more than the threshold number of times, prompting the user, by the user computing device, to provide a privacy level for the second human voice; determining, by the user computing device, that the audio sensor indicates a first command in the first human voice and indicates the second human voice, the first command instructing the user computing device to perform a first task; and executing, by the user computing device, the first task at the privacy level for the second human voice.

12 . The computer-implemented method of claim 11 , further comprising:
determining, by the user computing device, that the audio sensor indicates a third human voice different than the first human voice and the second human voice; determining, by the user computing device, that the third human voice does not match any voice in the set of known human voices; and incrementing, by the user computing device, a record indicating a number of times that the third human voice is detected.

13 . The computer-implemented method of claim 11 , further comprising, adding, by the user computing device, the second human voice to the set of known human voices.

14 . The computer-implemented method of claim 11 , the determining that the second human voice has been detected more than the threshold number of times comprising determining that stored data describing ambient human voices that were not matched to one of the set of known human voices describes the second human voice more than the threshold number of times.

15 . The computer-implemented method of claim 11 , the determining that the second human voice has been detected more than the threshold number of times comprising determining that the second human voice has been detected more than the threshold number of times in a first time period.

16 . The computer-implemented method of claim 11 , further

Assignees

• Wells Fargo Bank Na

Inventors

• Nichols Tambra
• Rench Teresa Lynn
• Hartsell Jonathan Austin
• Brenner John C
• Williams Christopher James

Classifications

• H04W12/63

  Location-dependent; Proximity-dependent · CPC title

• H04W12/30

  Security of mobile devices; Security of mobile applications · CPC title

• G10L17/00

  Speaker identification or verification techniques · CPC title

• H04W12/08

  Access security · CPC title

• G10L17/06

  Decision making techniques; Pattern matching strategies · CPC title