IP Library › Granted Patent US 12,099,629
Granted Patent B2
US 12,099,629 · App. 17/676,141 · Granted Sep 24, 2024

Assigning confidence to data de-identification

Inventors: Omer Dror (Sunnyvale, CA); Ofir Farchy (Modiin, IL)
Assignee: LYNX MD LTD
G06F21/6245G06F21/6209G06F21/6254G06F21/6272G16H10/60G16H40/20G16H40/63G16H40/67
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 12,099,629
App. No.
17/676,141
Granted
Sep 24, 2024
Kind
B2
Abstract

Systems, methods and non-transitory computer readable media for assigning confidence to data de-identification are provided. A data collection may be accessed to generate a de-identified copy of the data collection. A confidence level that the generated de-identified copy does not include identified information may be determined. In response to a first value of the confidence level, providing particular information based on the de-identified copy of the data collection to a first entity and to a second entity. In response to a second value of the confidence level, providing the particular information to the first entity and forgoing providing the particular information to the second entity.

Claims (55)

1. A non-transitory computer readable medium storing a software program comprising data and computer implementable instructions for carrying out a method for assigning confidence to data de-identification, the method comprising:

accessing a data collection to generate a de-identified copy of the data collection;

determining a confidence level that the generated de-identified copy does not include identified information;

in response to a first value of the confidence level, providing particular information based on the de-identified copy of the data collection to a first entity and to a second entity; and

in response to a second value of the confidence level, providing the particular information to the first entity and forgoing providing the particular information to the second entity.

2. The non-transitory computer readable medium of claim 1 , wherein the method further comprises analyzing the generated de-identified copy to determine the confidence level.

3. The non-transitory computer readable medium of claim 1 , wherein the method further comprises analyzing the data collection to determine the confidence level.

4. The non-transitory computer readable medium of claim 1 , wherein the method further comprises analyzing the data collection and the generated de-identified copy to determine the confidence level.

5. The non-transitory computer readable medium of claim 1 , wherein the method further comprises:

for each level of residual identified information of a plurality of levels of residual identified information, determining a likelihood that the de-identified copy of the data collection includes the level of residual identified information; and

determining the confidence level that the generated de-identified copy does not include identified information based on the plurality of determined likelihoods.

6. The non-transitory computer readable medium of claim 1 , wherein the method further comprises:

for each particular type of identified information of a plurality of types of identified information, determining a likelihood that the de-identified copy of the data collection includes identified information of the particular type of identified information; and

determining the confidence level that the generated de-identified copy does not include identified information based on the plurality of determined likelihoods.

7. The non-transitory computer readable medium of claim 1 , wherein the method further comprises:

for each pair of a particular type of residual identified information and a level of residual identified information of a plurality of pairs, determining a likelihood that the de-identified copy of the data collection includes the level of residual identified information of the particular type of residual identified information; and

determining the confidence level that the generated de-identified copy does not include identified information based on the plurality of determined likelihoods.

8. The non-transitory computer readable medium of claim 1 , wherein the method further comprises:

analyzing the data collection to determine a level of identified information in the data collection; and

determining the confidence level that the generated de-identified copy does not include identified information based on the determined level of identified information in the data collection.

9. The non-transitory computer readable medium of claim 1 , wherein the data collection includes at least a first image and a second image, the de-identified copy of the data collection includes the second image and does not include the first image, and the method further comprises:

analyzing the first image to determine a visual characteristic;

analyzing the second image to determine a likelihood that the second image includes the visual characteristic; and

determining the confidence level that the generated de-identified copy does not include identified information based on the determined likelihood.

10. The non-transitory computer readable medium of claim 9 , wherein the visual characteristic is associated with a face of an individual.

11. The non-transitory computer readable medium of claim 9 , wherein the method further comprises:

calculating a convolution of at least part of the first image to obtain a result value of the calculated convolution; and

determining the visual characteristic based on the result value.

12. The non-transitory computer readable medium of claim 9 , wherein the method further comprises:

calculating a convolution of at least part of the second image to obtain a result value of the calculated convolution; and

determining the likelihood that the second image includes the visual characteristic based on the result value.

13. The non-transitory computer readable medium of claim 1 , wherein the method further comprises, in response to the second value of the confidence level, providing second particular information based on the de-identified copy of the data collection to the second entity, the second particular information differs from the particular information.

14. The non-transitory computer readable medium of claim 1 , wherein the particular information is the de-identified copy of the data collection.

15. The non-transitory computer readable medium of claim 1 , wherein the particular information includes a statistical measure of the de-identified copy of the data collection.

16. The non-transitory computer readable medium of claim 1 , wherein the method further comprises, after providing the particular information:

in response to the first value of the confidence level, providing specific information based on the de-identified copy of the data collection to the first entity and to the second entity, the specific information differs from the particular information; and

in response to the second value of the confidence level, providing the specific information to the second entity and forgoing providing the specific information to the first entity.

17. The non-transitory computer readable medium of claim 1 , wherein the method further comprises, in response to the second value of the confidence level:

initiating an action to generate a second de-identified copy of the data collection, the second de-identified copy differs from the de-identified copy; and

providing specific information based on the second de-identified copy of the data collection to the second entity.

18. The non-transitory computer readable medium of claim 17 , wherein the action to generate the second de-identified copy of the data collection comprises:

presenting to a user at least part of the de-identified copy of the data collection;

receiving from the user a response to the presentation; and

generating the second de-identified copy of the data collection based on the received response.

19. A system for assigning confidence to data de-identification, the system comprising:

at least one processing unit configured to:

accessing a data collection to generate a de-identified copy of the data collection;

determining a confidence level that the generated de-identified copy does not include identified information;

in response to a first value of the confidence level, providing particular information based on the de-identified copy of the data collection to a first entity and to a second entity; and

in response to a second value of the confidence level, providing the particular information to the first entity and forgoing providing the particular information to the second entity.

20. A method for assigning confidence to data de-identification, the method comprising:

accessing a data collection to generate a de-identified copy of the data collection;

determining a confidence level that the generated de-identified copy does not include identified information;

in response to a first value of the confidence level, providing particular information based on the de-identified copy of the data collection to a first entity and to a second entity; and

in response to a second value of the confidence level, providing the particular information to the first entity and forgoing providing the particular information to the second entity.

Assignments (2)
SECURITY INTEREST Recorded Nov 11, 2022
From: LYNX MD LTD.
To: SILICON VALLEY BANK
Reel/Frame 061730/0103 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 18, 2022
From: DROR, OMER; FARCHY, OFIR
To: LYNX MD LTD
Reel/Frame 059305/0991 →
Continuity (4)
Provisional Application 63151751 · Feb 21, 2021
Provisional Application 63151745 · Feb 21, 2021
Provisional Application 63151748 · Feb 21, 2021
Related Publication 20220179994A1 · Jun 9, 2022