Sensitive data control

Patent metadata

Field	Value
Publication number	US-11862170-B2
Application number	US-202217951657-A
Country	US
Kind code	B2
Filing date	Sep 23, 2022
Priority date	Mar 30, 2020
Publication date	Jan 2, 2024
Grant date	Jan 2, 2024

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 a first recipient device associated with a user profile, the message data comprising first output data corresponding to message content and an indication of a first sender of the message;
determining that the first sender corresponds to stored data associated with the user profile;
based at least in part on the stored data, determining second output data corresponding to the message, wherein the second output data excludes a portion of the first output data, and wherein the second output data requests an input for user authentication processing;
causing the second output data to be presented using the first recipient device;
after causing the second output data to be presented, receiving authentication data from the first recipient device, the authentication data being based on an authentication action performed via the first recipient device;
determining that the authentication data satisfies a first privacy control; and
based at least in part on the authentication data satisfying the first privacy control, causing the portion of the first output data to be presented using the first recipient device.

2. The computer-implemented method of claim 1 , further comprising:
prior to receiving the message data:
receiving first input data corresponding to a first user input associated with the user profile,
determining, from the first input data, that the first user input requests a first notification be output when a first event occurs,
generating first trigger data representing the first notification is to be output when the first event occurs, and
storing the first trigger data as the stored data; and

after storing the first trigger data:
receiving event data corresponding to the message,
determining the event data corresponds to the first event represented by the first trigger data, and
determining, using the first trigger data, that the first notification is to be output by the first recipient device.

3. The computer-implemented method of claim 1 , further comprising:
processing, using semantic analysis, the first output data to determine that the portion includes a representation of sensitive data.

4. The computer-implemented method of claim 1 , further comprising:
determining stored user recognition data associated with the user profile; and
determining, using the stored user recognition data, that the authentication data satisfies the first privacy control.

5. The computer-implemented method of claim 1 , further comprising:
processing the first output data to determine that the portion includes information of a first data type corresponding to sensitive data.

6. The computer-implemented method of claim 5 , wherein the first data type corresponds to medical information.

7. The computer-implemented method of claim 5 , wherein the first data type corresponds to personal identification information.

8. The computer-implemented method of claim 1 , further comprising:
determining that the portion of the first output data corresponds to a first representation of sensitive data; and
using natural language generation, determining the second output data to include at least a second representation of the sensitive data in a non-sensitive manner.

9. The computer-implemented method of claim 1 , further comprising:
determining a second recipient device associated with the user profile;
determining, using the user profile, that the second recipient device is designated as a personal device; and
based at least in part on the second recipient device being designated as the personal device, causing the first output data to be presented using the second recipient device without previously presenting the second output data using the second recipient device.

10. The computer-implemented method of claim 9 , wherein causing presentation of the first output data using the second recipient device occurs after receiving the authentication data from the first recipient device.

11. A system comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive notification data corresponding to an input notification to be output by a first recipient device associated with a user profile, the notification data comprising first output data corresponding to notification content;
determine that the notification content corresponds to a first data type corresponding to sensitive data;
based at least in part on the notification content corresponding to the first data type, determine second output data corresponding to the input notification, wherein the second output data excludes a portion of the first output data, and wherein the second output data requests an input for user authentication processing;
cause the second output data to be presented using the first recipient device;
after causing the second output data to be presented, receive authentication data from the first recipient device, the authentication data being based on an authentication action performed via the first recipient device;
determine that the authentication data satisfies a first privacy control; and
based at least in part on the authentication data satisfying the first privacy control, cause the portion of the first output data to be presented using the first recipient device.

12. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
prior to receipt of the notification data:
receive first input data corresponding to a first user input associated with the user profile,
determine, from the first input data, that the first user input requests a first notification be output when a first event occurs,
generate first trigger data representing the first notification is to be output when the first event occurs, and
store the first trigger data; and

after storage of the first trigger data:
receive event data corresponding to the input notification,
determine the event data corresponds to the first event represented by the first trigger data, and
determining, using the first trigger data, that the input notification is to be output by the first recipient device.

13. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
process, using semantic analysis, the first output data to determine that the portion includes a representation of sensitive data.

14. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine stored user recognition data associated with the user profile; and
determine, using the stored user recognition data, that the authentication data satisfies the first privacy control.

15. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
process the notification data to determine an indication of a first source of the notification data; and
determine that the first source corresponds to stored data associated with the user profile,
wherein determination of the second output data is based at least in part on the stored data.

16. The system of claim 11 , wherein the first data type corresponds to medical

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

• G06F9/542

  Event management; Broadcasting; Multicasting; Notifications · CPC title

• G06F21/6245 Primary

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

• G10L13/00

  Speech synthesis; Text to speech systems · CPC title

• G10L15/1815

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