Sensitive data control

Patent metadata

Field	Value
Publication number	US-2024029739-A1
Application number	US-202318376147-A
Country	US
Kind code	A1
Filing date	Oct 3, 2023
Priority date	Mar 30, 2020
Publication date	Jan 25, 2024
Grant date	—

Abstract

A system is provided for determining privacy controls for output including sensitive data. A user may subscribe to receive an output in the future based on the occurrence of an event. The system may determine when the event is occurred triggering the output, and determine that the output includes outputting sensitive data. The system may determine output data that does not include the sensitive data, send the output data to a device, and may request the user to provide an authentication input to receive the sensitive data.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
receiving message data corresponding to a message to be output by at least one device associated with a user profile, the message data comprising a first portion of natural language message content and a second portion of natural language message content, wherein the first portion does not include the second portion; performing text-to-speech processing using the first portion of natural language message content to determine output audio data representing synthesized speech of the first portion; determining to output the second portion separately from the first portion; causing presentation of audio corresponding to the output audio data; and sending, to a destination associated with the user profile, the second portion of natural language content.

2 . The computer-implemented method of claim 1 , further comprising:
receiving input data corresponding to a user indication, wherein determining to output the second portion separately from the first portion is based on the user indication.

3 . The computer-implemented method of claim 2 , further comprising:
receiving audio data corresponding to an utterance including the user indication; and performing speech processing using the audio data to determine the input data.

4 . The computer-implemented method of claim 2 , further comprising:
detecting a first input to a graphical user interface; and based at least in part on the first input, determining the input data.

5 . The computer-implemented method of claim 1 , further comprising:
determining stored data associated with the user profile; and determining that the stored data corresponds to a characteristic of the second portion, wherein determining to output the second portion separately from the first portion is based on the stored data corresponding to the characteristic of the second portion.

6 . The computer-implemented method of claim 1 , wherein the destination corresponds to an email address associated with the user profile.

7 . The computer-implemented method of claim 1 , wherein the destination corresponds to a display screen of a device associated with the user profile.

8 . The computer-implemented method of claim 1 , wherein:
presentation of the audio is performed by a first device; and the destination corresponds to a second device different from the first device.

9 . The computer-implemented method of claim 1 , wherein the destination corresponds to a wearable device associated with the user profile.

10 . The computer-implemented method of claim 1 , further comprising:
processing the second portion of natural language message content to determine the second portion of natural language message content comprises sensitive information, wherein determining to output the second portion separately from the first portion is based on the second portion of natural language message content comprising sensitive information.

11 . A system comprising:
at least one processor; and at least one memory including instructions that, when executed by the at least one processor, cause the system to:
receive message data corresponding to a message to be output by at least one device associated with a user profile, the message data comprising a first portion of natural language message content and a second portion of natural language message content, wherein the first portion does not include the second portion;
perform text-to-speech processing using the first portion of natural language message content to determine output audio data representing synthesized speech of the first portion;
determine to output the second portion separately from the first portion;
cause presentation of audio corresponding to the output audio data; and
send, to a destination associated with the user profile, the second portion of natural language content.

12 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, cause the system to:
receive input data corresponding to a user indication, wherein the instructions that cause the system to determine to output the second portion separately from the first portion are based on the user indication.

13 . The system of claim 12 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, cause the system to:
receive audio data corresponding to an utterance including the user indication; and perform speech processing using the audio data to determine the input data.

14 . The system of claim 12 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, cause the system to:
detect a first input to a graphical user interface; and based at least in part on the first input, determine the input data.

15 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, cause the system to:
determine stored data associated with the user profile; and determine that the stored data corresponds to a characteristic of the second portion, wherein the instructions that cause the system to determine to output the second portion separately from the first portion re based on the stored data corresponding to the characteristic of the second portion.

16 . The system of claim 11 , wherein the destination corresponds to an email address associated with the user profile.

17 . The system of claim 11 , wherein the destination corresponds to a display screen of a device associated with the user profile.

18 . The system of claim 11 , wherein:
presentation of the audio is performed by a first device; and the destination corresponds to a second device different from the first device.

19 . The system of claim 11 , wherein the destination corresponds to a wearable device associated with the user profile.

20 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, cause the system to:
process the second portion of natural language message content to determine the second portion of natural language message content comprises sensitive information, wherein the instructions that cause the system to determine to output the second portion separately from the first portion are based on the second portion of natural language message content comprising sensitive information.

Assignees

• Amazon Tech Inc

Inventors

• Nadig Vinaya
• Kanoria Shipra Agarwal
• Kassis Elad Refael
• Babuji Ambika
• Dani Neelesh Deo
• Mutagi Rohan

Classifications

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G06F21/6245 Primary

  Protecting personal data, e.g. for financial or medical purposes · CPC title

• H04L67/306

  User profiles · CPC title

• G06F9/542

  Event management; Broadcasting; Multicasting; Notifications · CPC title