# US 9,965,650 B1 · Computer system of computer servers and dedicated computer clients specially programmed to generate synthetic non-reversible electronic data records based on real-time electronic querying and methods of use thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 9,965,650 B1
- Document ID: US9965650B1
- Status: Granted
- Kind: B1
- Application number: 15/592,779
- Filed: 2017-05-11
- Granted: 2018-05-08
- Earliest claimed: 2016-05-11
- Assignees: MDClone Ltd.
- Applicants: MDClone Ltd.
- Inventors: Luz Erez
- Web page: https://patentgrep.com/patent/US9965650B1

## CPC

- G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification}
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/04847: Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
- G06F 16/24564: {Applying rules; Deductive queries}
- G06F 16/248: Presentation of query results
- G06F 16/335: Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536)
- G06F 16/9038: Presentation of query results
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G06F 21/602: {Providing cryptographic facilities or services}
- H04L 9/0618: {Block ciphers, i.e. encrypting groups of characters of a plain text message using fixed encryption transformation}
- H04L 2209/42: Anonymization, e.g. involving pseudonyms
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In some embodiments, the present invention provides for an exemplary computer system which includes at least: a graphical user interface client; a dedicated application server; the dedicated application server is configured to connect to the graphical user interface client and an electronic source with electronic data records; where the electronic data records include real identification identifiers of real individuals; where the graphical user interface client is configured to generate at a graphical user interface that is configured to receive user authenticating credential information and to conduct a real-time electronic negotiation querying session between the user and the dedicated application server to generate a plurality of non-reversible synthetic electronic data records of a plurality of synthetic individuals, by utilizing at least one statistical technique so that the plurality of non-reversible synthetic electronic data records cannot be used to identify any real individual in the plurality of electronic data records.

## Claims

### Claim 1

A computer system, comprising:
at least one graphical user interface client;
at least one dedicated application server;
wherein the at least one dedicated application server comprises:
a non-transitory memory storing instructions and
at least one server processor;
wherein, when executing the instructions by the at least one server processor, the at least one dedicated application server is configured to operationally connect to the at least one graphical user interface client and at least one electronic source with a plurality of electronic data records;
wherein the plurality of electronic data records comprises at least 10,000 data records;
wherein the plurality of electronic data records comprises real identification identifiers of real individuals;
wherein the at least one graphical user interface client is configured to utilize at least one processor of a computing device of a user to:
generate at least first graphical user interface that comprises:
i) at least one first programmable software object which is configured to receive user authenticating credential information;
wherein the at least one dedicated application server is configured to assign an anonymity level to the user based on user authenticating credential information;
ii) a plurality of second programmable software objects which are configured to conduct at least one real-time electronic negotiation querying session between the user and the at least one dedicated application server;
wherein the at least one real-time electronic negotiation querying session is configured to:
1) receive, from the user, via the plurality of second programmable software objects, at least the following:
a) at least one of:
a plurality of personal event data parameters of at least one personal event and at least one demographic identifier, and
b) a plurality of reference event data parameters of at least one reference event,
wherein the plurality of reference event data parameters of the at least one reference event comprise a plurality of time-related property data parameters for at least one time-related property of the at least one reference event;
2) allow, the user, via the plurality of second programmable software objects, to iteratively adjust the plurality of personal event data parameters of the at least one personal event and at least one of the at least one demographic identifier and the plurality of reference event data parameters of the at least one reference event so that, based on the anonymity level of the user, there is a matched subset of a minimal number of real individuals associated with the plurality of electronic data records of the at least one electronic source matching the at least one personal event and the at least one reference event;
3) display, in real-time, an indication of how many real individuals are in the matched subset;
4) generate, with each adjustment iteration, a plurality of non-reversible synthetic electronic data records of a plurality of synthetic individuals, by utilizing at least one statistical technique to perform at least one of:
self-recalculation of discrete values of the plurality of electronic data records of the matched subset and
self-transformation of categorical values of the plurality of electronic data records of the matched subset;
5) electronically output, for the user, the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals to at least one electronic destination associated with the user; and
6) generate at least one comparison report, analyzing all pairs of variables between the plurality of electronic data records of the matched subset and the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals; and
wherein the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals are records that protect privacy of the real individuals associated with the plurality of electronic data records of the matched subset while avoiding generalization of the plurality of electronic data records of the matched subset that would occur when the plurality of electronic data records of the matched subset would be anonymized, based on the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals:
a) being statistically representative of the matched subset,
b) having at least one synthetic identification identifier corresponding to at least one real identification identifier of a real individual from the matched subset, and
c) being unsuitable to be utilized to identify any real individual from the matched sub set.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein the at least one dedicated application server is configured to assign the anonymity level to the user based on an entity affiliation of the user.

### Claim 3 (depends on 1)

The computer system of claim 1, wherein the at least one statistical technique is a conditional probability methodology.

### Claim 4 (depends on 1)

The computer system of claim 1, wherein the at least one comparison report is generated based on Pearson's correlation for each pairs of variables between the plurality of electronic data records of the matched subset and the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals.

### Claim 5 (depends on 1)

The computer system of claim 1, wherein the plurality of electronic data records are a plurality of electronic medical records.

### Claim 6 (depends on 5)

The computer system of claim 5, wherein the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals are HIPAA self-compliant.

### Claim 7 (depends on 6)

The computer system of claim 6, wherein the at least one synthetic identification identifier is de-identification identifier which is required, based on HIPAA, to be removed from the plurality of electronic data records of the matched subset prior to being outputted to the at least one electronic destination associated with the user.

### Claim 8

A computer-implemented method, comprising:
causing to install at least one graphical user interface client on a computing device of a user;
wherein the at least one graphical user interface client is configured to operationally connect to at least one dedicated application server;
wherein the at least one dedicated application server comprises:
a non-transitory memory storing instructions and
at least one server processor;
wherein, when executing the instructions by the at least one server processor, the at least one dedicated application server is configured to operationally connect to the at least one graphical user interface client and at least one electronic source with a plurality of electronic data records;
wherein the plurality of electronic data records comprises at least 10,000 data records;
wherein the plurality of electronic data records comprises real identification identifiers of real individuals;
wherein the at least one graphical user interface client is configured to utilize at least one processor of the computing device of the user to:
generate at least first graphical user interface that comprises:
i) at least one first programmable software object which is configured to receive user authenticating credential information;
wherein the at least one dedicated application server is configured to assign an anonymity level to the user based on user authenticating credential information;
ii) a plurality of second programmable software objects which are configured to conduct at least one real-time electronic negotiation querying session between the user and the at least one dedicated application server;
wherein the at least one real-time electronic negotiation querying session is configured to:
1) receive, from the user, via the plurality of second programmable software objects, at least the following:
a) at least one of:
a plurality of personal event data parameters of at least one personal event and
at least one demographic identifier, and
b) a plurality of reference event data parameters of at least one reference event,
wherein the plurality of reference event data parameters of the at least one reference event comprise a plurality of time-related property data parameters for at least one time-related property of the at least one reference event;
2) allow, the user, via the plurality of second programmable software objects, to iteratively adjust the plurality of personal event data parameters of the at least one personal event and at least one of the at least one demographic identifier and the plurality of reference event data parameters of the at least one reference event so that, based on the anonymity level of the user, there is a matched subset of a minimal number of real individuals associated with the plurality of electronic data records of the at least one electronic source matching the at least one personal event and the at least one reference event;
3) display, in real-time, an indication of how many real individuals are in the matched subset;
4) generate, with each adjustment iteration, a plurality of non-reversible synthetic electronic data records of a plurality of synthetic individuals, by utilizing at least one statistical technique to perform at least one of:
self-recalculation of discrete values of the plurality of electronic data records of the matched subset and
self-transformation of categorical values of the plurality of electronic data records of the matched subset;
5) electronically output, for the user, the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals to at least one electronic destination associated with the user; and
6) generate at least one comparison report, analyzing all pairs of variables between the plurality of electronic data records of the matched subset and the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals; and
wherein the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals are records that protect privacy of the real individuals associated with the plurality of electronic data records of the matched subset while avoiding generalization of the plurality of electronic data records of the matched subset that would occur when the plurality of electronic data records of the matched subset would be anonymized, based on the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals:
a) being statistically representative of the matched subset,
b) having at least one synthetic identification identifier corresponding to at least one real identification identifier of a real individual from the matched subset, and
c) being unsuitable to be utilized to identify any real individual from the matched subset.

### Claim 9 (depends on 8)

The method of claim 8, wherein the at least one dedicated application server is configured to assign the anonymity level to the user based on an entity affiliation of the user.

### Claim 10 (depends on 8)

The method of claim 8, wherein the at least one statistical technique is a conditional probability methodology.

### Claim 11 (depends on 8)

The method of claim 8, wherein the at least one comparison report is generated based on Pearson's correlation for each pairs of variables between the plurality of electronic data records of the matched subset and the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals.

### Claim 12 (depends on 8)

The method of claim 8, wherein the plurality of electronic data records are a plurality of electronic medical records.

### Claim 13 (depends on 12)

The method of claim 12, wherein the plurality of non-reversible synthetic electronic data records of the plurality of synthetic individuals are HIPAA self-compliant.

### Claim 14 (depends on 13)

The method of claim 13, wherein the at least one synthetic identification identifier is de-identification identifier which is required, based on HIPAA, to be removed from the plurality of electronic data records of the matched subset prior to being outputted to the at least one electronic destination associated with the user.