Granted Patent B2

US 12,455,984 · App. 18/305,148 · Granted Oct 28, 2025

Inventors: Grant Howard George Middleton (Toronto, CA); Brian Joseph Rasquinha (Ontario, CA)

Assignee: Privacy Analytics Inc.

G06F21/6254

Abstract

Claims (98)

1. A computer-implemented method comprising:

automatically, using a trained machine-learning model, detecting attributes in unstructured data;

determining an amount of undetected attributes and detected attributes in the unstructured data;

simulating additional attributes for the unstructured data according to the amount of undetected attributes, wherein the sampling comprises, for each undetected attribute:

sampling a population distribution for a sampled value, wherein the population distribution is an externally supplied reference distribution;

computing a sampling frequency according to the sampled value; and

assigning the sampling frequency as an additional attribute;

analyzing a risk of disclosure in the unstructured data using the detected attributes and the simulated additional attributes, wherein the analyzing comprises:

assigning a first information value to each detected attribute according to samples received from a first statistical distribution used to simulate the additional attributes;

assigning a second information value to each simulated additional attribute according to samples retrieved from a second statistical distribution, wherein the second statistical distribution is generated based on attributes that change with respect to time;

aggregating the first information value for each detected attribute and the second information value for each simulated additional attribute into an aggregated value;

determining an anonymity value using the first information value, the second information value, the aggregated value, and a size of a population associated with the unstructured data; and

determining the risk of disclosure in the unstructured data using the determined anonymity value;

modifying the detected attributes according to the analyzed risk of disclosure; and

replacing the detected attributes with the modified detected attributes in the unstructured data.

2. The computer-implemented method of claim 1 , wherein the unstructured data comprise medical records, emails, presentations, textbooks, brochures, websites, documents, audio recordings, images, and videos.

3. The computer-implemented method of claim 1 , further comprising:

generating a machine-learning model that is configured to detect the attributes in the unstructured data, wherein generating the machine-learning model comprises:

training the machine-learning model to detect the attributes in a first subset of the unstructured data;

determining a number of undetected attributes in the training of the machine-learning model; and

retraining the machine-learning model to detect the attributes in the first subset of the unstructured data based on data indicative of the undetected attributes.

4. The computer-implemented method of claim 3 , further comprising:

determining the number of the undetected attributes in the first subset satisfies a threshold limit;

in response to determining the number of the undetected attributes satisfies the threshold limit, deploying the trained machine-learning model; and

detecting, by the trained machine-learning model, the attributes in a second subset of the unstructured data by providing the second subset as input to the trained machine-learning model, wherein the second subset of the unstructured data is different from the first subset of the unstructured data.

5. The computer-implemented method of claim 4 , wherein detecting the attributes in the second subset of the unstructured data by providing the second subset as input to the trained machine-learning model further comprises:

for each detected attribute:

generating, by the trained machine-learning model, an identifier in the second subset of the unstructured data that represents (i) an identified location of the detected attribute and (ii) an indication of a detected attribute;

generating, by the trained machine-learning model, a confidence level associated with the identifier that indicates how likely a corresponding detected attribute represents an actual attribute according to criteria;

comparing the confidence level to a threshold level; and

in response to determining the confidence level satisfies the threshold level, labeling a portion of the unstructured data with the identifier at the identified location of the corresponding detected attribute.

6. The computer-implemented method of claim 1 , wherein automatically detecting the attributes in the unstructured data further comprises:

receiving data specifying criteria associated with attributes to be detected in the unstructured data; and

receiving data specifying criteria associated with attributes not to be detected in the unstructured data.

7. The computer-implemented method of claim 6 , wherein the criteria comprise a name, a date of birth, a personal identifier, an age, a location, a medical diagnosis, a relevant date, personal characteristics, and an address.

8. The computer-implemented method of claim 6 , wherein determining the amount of undetected attributes and detected attributes in the unstructured data further comprises:

determining a number of identifiers associated with the detected attributes labeled in the unstructured data; and

determining a number of undetected attributes in the unstructured data, wherein determining the number of undetected attributes comprises:

determining a difference between (i) the number of identifiers associated with the detected attributes to (ii) a known number of detected attributes in the unstructured data, wherein the known number of detected attributes is supplied by an external party; and

in response to determining the difference between (i) the number of identifiers associated with the detected attributes to (ii) the known number of detected attributes in the unstructured data, simulating the additional attributes according to the difference.

9. The computer-implemented method of claim 1 , wherein simulating the additional attributes for the unstructured data according to the amount of undetected attributes comprises simulating the additional attributes for the unstructured data using a random seed, a counting method, and an averaging method.

10. The computer-implemented method of claim 1 , wherein simulating the additional attributes for the unstructured data according to the amount of undetected attributes comprises simulating the additional attributes for the unstructured data according to the amount of the undetected attributes the trained machine-learning model missed during processing of the unstructured data.

11. The computer-implemented method of claim 1 , wherein modifying the detected attributes in the unstructured data according to the analyzed risk of disclosure further comprises:

determining a transformation approach for transforming the detected attributes in the unstructured data based on the analyzed risk of disclosure; and

transforming the detected attributes in the unstructured data according to the determined transformation approach, wherein the transformations comprise at least one of resynthesis, masking, generalizing, injecting noise, and imputing simulated values.

12. The computer-implemented method of claim 11 , wherein replacing the detected attributes with the modified detected attributes in the unstructured data further comprises:

generating structured data that represents the detected attributes from the unstructured data using identifiers associated with the detected attributes in the unstructured data; and

applying the transformed attributes from the structured data to locations of the identifiers in the unstructured data, wherein applying the transformed attributes replace the detected attributes from the unstructured data.

13. The computer-implemented method of claim 1 , further comprising providing, to an external party, the unstructured data that comprises the modified detected attributes and the undetected attributes.

14. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

automatically, using a trained machine-learning model, detecting attributes in unstructured data;

determining an amount of undetected attributes and detected attributes in the unstructured data;

simulating additional attributes for the unstructured data according to the amount of undetected attributes, wherein the sampling comprises, for each undetected attribute:

sampling a population distribution for a sampled value, wherein the population distribution is an externally supplied reference distribution;

computing a sampling frequency according to the sampled value; and

assigning the sampling frequency as an additional attribute;

analyzing a risk of disclosure in the unstructured data using the detected attributes and the simulated additional attributes, wherein the analyzing comprises:

assigning a first information value to each detected attribute according to samples received from a first statistical distribution used to simulate the additional attributes;

assigning a second information value to each simulated additional attribute according to samples retrieved from a second statistical distribution, wherein the second statistical distribution is generated based on attributes that change with respect to time;

aggregating, for each detected attribute and simulated additional attribute, the first information value and the second information value into an aggregated value;

determining an anonymity value using the first information value, the second information value, the aggregated information value, and a size of a population associated with the unstructured data; and

determining the risk of disclosure in the unstructured data using the determined anonymity value;

modifying the detected attributes according to the analyzed risk of disclosure; and

replacing the detected attributes with the modified detected attributes in the unstructured data.

15. The system of claim 14 , wherein the unstructured data comprise medical records, emails, presentations, textbooks, brochures, websites, documents, audio recordings, images, and videos.

16. The system of claim 14 , further comprising:

generating a machine-learning model that is configured to detect the attributes in the unstructured data, wherein generating the machine-learning model comprises:

training the machine-learning model to detect the attributes in a first subset of the unstructured data;

determining a number of undetected attributes in the training of the machine-learning model; and

retraining the machine-learning model to detect the attributes in the first subset of the unstructured data based on data indicative of the undetected attributes.

17. The system of claim 16 , further comprising:

determining the number of the undetected attributes in the first subset satisfies a threshold limit;

in response to determining the number of the undetected attributes satisfies the threshold limit, deploying the trained machine-learning model; and

detecting, by the trained machine-learning model, the attributes in a second subset of the unstructured data by providing the second subset as input to the trained machine-learning model, wherein the second subset of the unstructured data is different from the first subset of the unstructured data.

18. The system of claim 17 , wherein detecting the attributes in the second subset of the unstructured data by providing the second subset as input to the trained machine-learning model further comprises:

for each detected attribute:

generating, by the trained machine-learning model, an identifier in the second subset of the unstructured data that represents (i) an identified location of the detected attribute and (ii) an indication of a detected attribute;

generating, by the trained machine-learning model, a confidence level associated with the identifier that indicates how likely a corresponding detected attribute represents an actual attribute according to criteria;

comparing the confidence level to a threshold level; and

in response to determining the confidence level satisfies the threshold level, labeling a portion of the unstructured data with the identifier at the identified location of the corresponding detected attribute.

19. The system of claim 14 , wherein automatically detecting the attributes in the unstructured data further comprises:

receiving data specifying criteria associated with attributes to be detected in the unstructured data; and

receiving data specifying criteria associated with attributes not to be detected in the unstructured data.

20. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

automatically, using a trained machine-learning model, detecting attributes in unstructured data;

determining an amount of undetected attributes and detected attributes in the unstructured data;

simulating additional attributes for the unstructured data according to the amount of undetected attributes, wherein the sampling comprises, for each undetected attribute:

sampling a population distribution for a sampled value, wherein the population distribution is an externally supplied reference distribution;

computing a sampling frequency according to the sampled value; and

assigning the sampling frequency as an additional attribute;

analyzing a risk of disclosure in the unstructured data using the detected attributes and the simulated additional attributes, wherein the analyzing comprises:

assigning a first information value to each detected attribute according to samples received from a first statistical distribution used to simulate the additional attributes;

assigning a second information value to each simulated additional attribute according to samples retrieved from a second statistical distribution, wherein the second statistical distribution is generated based on attributes that change with respect to time;

aggregating, for each detected attribute and simulated additional attribute, the first information value and the second information value into an aggregated value;

determining an anonymity value using the first information value, the second information value, the aggregated information value, and a size of a population associated with the unstructured data; and

determining the risk of disclosure in the unstructured data using the determined anonymity value;

modifying the detected attributes according to the analyzed risk of disclosure; and replacing the detected attributes with the modified detected attributes in the unstructured data.

Assignments (7)

Continuity (2)

References Cited (21)