Methods and systems of biometric identification in telemedicine using remote sensing

Patent metadata

Field	Value
Publication number	US-11037679-B1
Application number	US-202016939408-A
Country	US
Kind code	B1
Filing date	Jul 27, 2020
Priority date	Jul 27, 2020
Publication date	Jun 15, 2021
Grant date	Jun 15, 2021

Abstract

In an aspect, a system for biometric identification in telemedicine using remote sensing, the system includes a computing device configured to initiate a communication interface between the computing device and a client device operated by a human subject, wherein the communication interface includes an audiovisual streaming protocol, receive, from at least a remote sensor at the human subject, a plurality of current physiological data, generate at least a biometric identification signature of the human subject, wherein generating further includes receiving subject signature training data, including a plurality of category descriptors and correlated physiological data entries, training a biometric signature model as a function of the subject signature training data and a machine-learning process, generating the biometric identification signature as a function of the biometric signature model, determining a degree of similarity between the plurality of current physiological data and the at least a biometric signature, and calculate an identity quantifier as a function of the degree of similarity.

First claim

What is claimed is:

1. A system for biometric identification in telemedicine using remote sensing, the system comprising:
a computing device at a first location, the computing device configured to:
initiate a communication interface between the computing device and a client device associated with a human subject and at a second location, wherein the communication interface includes an audiovisual streaming protocol;
receive, from at least a remote sensor at the human subject, a plurality of current physiological data associated with the human subject;
generate at least a biometric identification signature of the human subject, wherein generating further comprises:
receiving a subject signature training data, wherein the subject signature training data correlates a plurality of category descriptors and physiological data entries;
training a biometric signature model as a function of a machine-learning process, wherein the machine-learning process is trained as a function of the subject signature training data; and
generating the biometric identification signature as a function of the biometric signature model;

determine a degree of similarity between the plurality of current physiological data and the at least a biometric signature, wherein the degree of similarity measures a probability as a function an error function;
calculate an identity quantifier as a function of the degree of similarity; and
provide the plurality of physiological data to a user of the computing device using the communication interface.

2. The system of claim 1 , wherein the plurality of current physiological data further comprises heart rate data.

3. The system of claim 1 , wherein the plurality of current physiological data further comprises motion detector data.

4. The system of claim 1 , wherein the plurality of current physiological data further comprises image data.

5. The system of claim 1 , wherein the plurality of current physiological data further comprises audio data.

6. The system of claim 1 , wherein the computing device is further configured to generate the at least a biometric identification signature by:
receiving a plurality of physiological data corresponding to a plurality of users;
performing a feature learning algorithm on the plurality of physiological data;
identifying, as a function of the feature learning algorithm, at least a highly divergent data category; and
generating the at least a biometric identification signature as a function of the at least a highly divergent data category.

7. The system of claim 1 , wherein the computing device is further configured to determine the degree of similarity by:
generating an error function of the plurality of current physiological data and the at least a biometric signature; and
determining the degree of similarity as a function of the generating.

8. The system of claim 1 , wherein the computing device is further configured to determine the degree of similarity by:
generating a distance metric between the plurality of physiological data and the at least a biometric signature; and
determining the degree of similarity as a function of the distance metric.

9. The system of claim 1 , wherein the computing device is configured to authenticate a physiological sample set as a function of the identity quantifier.

10. The system of claim 9 , wherein the physiological sample set includes the plurality of physiological data.

11. A method of biometric identification in telemedicine using remote sensing, the method comprising:
initiating, by a computing device at a first location, a communication interface between the computing device and a client device associated with a human subject and at a second location, wherein the communication interface includes an audiovisual streaming protocol;
receiving, by the computing device and from at least a remote sensor at the human subject, a plurality of current physiological data;
generate, by the computing device, at least a biometric identification signature of the human subject, wherein generating further comprises:
receiving a subject signature training data, wherein the subject signature training data correlates a plurality of category descriptors and physiological data entries;
training a biometric signature model as a function of a machine-learning process, wherein the machine-learning process is trained as a function of the subject signature training data; and
generating the biometric identification signature as a function of the biometric signature module;

determining, by the computing device, a degree of similarity between the plurality of current physiological data and the at least a biometric, wherein the degree of similarity measures a probability as a function an error function;
calculating, by the computing device, an identity quantifier as a function of the degree of similarity; and
providing the plurality of physiological data to a user of the computing device using the communication interface.

12. The method of claim 11 , wherein the plurality of current physiological data further comprises heart rate data.

13. The method of claim 11 , wherein the plurality of current physiological data further comprises motion detector data.

14. The method of claim 11 , wherein the plurality of current physiological data further comprises image data.

15. The method of claim 11 , wherein the plurality of current physiological data further comprises audio data.

16. The method of claim 11 , wherein generating the at least a biometric identification signature further comprises:
receiving a plurality of physiological data corresponding to a plurality of users;
performing a feature learning algorithm on the plurality of physiological data;
identifying, as a function of the feature learning algorithm, at least a highly divergent data category; and
generating the at least a biometric identification signature as a function of the at least a highly divergent data category.

17. The method of claim 11 , wherein determining the degree of similarity further comprises:
generating an error function of the plurality of current physiological data and the at least a biometric signature; and
determining the degree of similarity as a function of the generating.

18. The method of claim 11 , wherein determining the degree of similarity further comprises:
generating a distance metric between the plurality of physiological data and the at least a biometric signature; and
determining the degree of similarity as a function of the distance metric.

19. The method of claim 11 further comprising authenticating a physiological sample set as a function of the identity quantifier.

20. The method of claim 19 , wherein the physiological sample set includes the plurality of physiological data.

Assignees

• Kpn Innovations Llc

Inventors

• Neumann Kenneth

Classifications

• G06V10/763

  Non-hierarchical techniques, e.g. based on statistics of modelling distributions · CPC title

• G06V40/70

  Multimodal biometrics, e.g. combining information from different biometric modalities · CPC title

• G06F18/23213

  with fixed number of clusters, e.g. K-means clustering · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title