Patent Issued for Authentication based on motion and biometric data (USPTO 11822633): United Services Automobile Association

2023 DEC 07 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Billman, Bradley Jay (Celina, TX, US), Desai, Snehal (Richardson, TX, US), Flachsbart, Matthew (Grapevine, TX, US), filed on October 21, 2020, was published online on November 21, 2023.

The assignee for this patent, patent number 11822633, is United Services Automobile Association (San Antonio, Texas, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Organizations and individuals that operate and/or manage computing systems may implement various security measures to prevent unauthorized individuals, devices, and processes from accessing secured data stored on the systems, gaining control of processes executing on the systems, introducing new (e.g., malicious) processes to the systems, and/or gaining unauthorized access for other purposes. Traditionally, a user may provide one or more credentials to gain access to a system. Such credentials may include a username, password, and/or personal identification number (PIN). By comparing the supplied credentials with previously established credentials for the user, a determination may be made whether to permit or deny the requested access. In some instances, tokens such as cryptographic keys may be employed to authenticate an individual and/or verify that an individual or process is authorized to access a system. Cryptographic keys may also be employed to secure communications over a network.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “Implementations of the present disclosure are generally directed to authentication of individuals using biometric and/or biologically determined information. More specifically, implementations are directed to determining a motion (e.g., tremor) signature for an individual based on measured motion(s) in at least a portion of the individual’s body, and employing the motion signature to authenticate the individual for secure access to a device, stored data, an application, and/or for other purposes.

“In general, innovative aspects of the subject matter described in this specification can be embodied in methods that include operations of: receiving motion data collected by one or more motion sensors of a user device, the motion data describing motions of at least one body part of a user of the user device; determining a tremor signature for the user based on an analysis of the motion data; receiving biometric data collected by one or more biometric sensors, the biometric data describing at least one physiological characteristic of the user other than the tremor signature; determining an authentication result for the user based on a comparison of the tremor signature and the biometric data to a model that at least describes a baseline tremor signature and baseline biometric data for the user; and based on the authentication result indicating a successful authentication of the user, providing access to secure information through the user device.

“Implementations can optionally include one or more of the following features: the operations further include receiving location data collected by one or more location sensors, the location data describing a current location of the user; the model further describes at least one baseline location for the user; determining the authentication result is further based on a comparison of the location data to the model that describes the at least one baseline location for the user; the tremor signature is determined periodically based on the motion data that is periodically collected by the one or more motion sensors; the biometric data is collected periodically by the one or more biometric sensors; the authentication result is determined periodically based on the comparison of the periodically determined tremor signature and the periodically collected biometric data; the model is developed using a machine learning algorithm; the operations further include employing the tremor signature and the biometric data to update the model, based on the authentication result indicating a successful authentication of the user; the operations further include performing a credential-based authentication of the user, based on the authentication result indicating an unsuccessful authentication of the user; the operations further include employing the tremor signature and the biometric data to update the model, based on a successful credential-based authentication of the user; at least one translational motion of the at least one body part of the user; at least one rotational motion of the at least one body part of the user; the biometric data describes one or more of a fingerprint of the user, an image of at least a portion of a face of the user, a retinal scan of the user, a heartbeat of the user, a cardiac electrical signature of the user, and a bio-electrical impedance of the user; the secure information includes one or more of a secure feature of the user device, a secure feature of an application executing on the user device, data stored in a secure location on the user device, and data stored in a secure location on a remote computing device; determining the authentication result for the user further includes combining the tremor signature and the biometric data to determine a combined authentication signature for the user, comparing the combined authentication signature to a baseline authentication signature for the user to determine the authentication result; determining the authentication result is included in a periodically iterated authentication of the user, such that access for the user is disabled in response to detecting a change in the authentication result; determining the authentication result further includes classifying the tremor signature and the biometric data into one or more parameter matrices, performing at least one statistical operations on the one or more parameter matrices, computing one or more properties of a resulting statistical data matrix to obtain an authentication signature profile, and comparing the authentication signature profile to a baseline authentication signature profile for the user to determine the authentication result; determining the authentication result further includes employing a plurality of potential models of combined tremor signature and biometric data for contextual authentication, the plurality of potential models being applicable to different circumstances of the user; the operations further include creating a new potential model in response to one or more failures to authenticate the user with self-similar data sets using at least one of the plurality of potential models; the operations further include in response to determining that the biometric data for an authentication request does not match any of the plurality of potential models and is close to two or more of the potential models, posing a contextual question to the user to select one of the two or more potential models; the contextual question is posed during a learning mode associated with a newly created potential model; and/or the contextual question is varied semantically among instances when the context question is posed to users.

“Other implementations of any of the above aspects include corresponding systems, apparatus, and computer programs that are configured to perform the actions of the methods, encoded on computer storage devices. The present disclosure also provides a computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations in accordance with implementations of the methods provided herein. The present disclosure further provides a system for implementing the methods provided herein. The system includes one or more processors, and a computer-readable storage medium coupled to the one or more processors having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations in accordance with implementations of the methods provided herein.

“Implementations of the present disclosure provide one or more of the following technical advantages and technical improvements over previously available solutions. By authenticating an individual using a motion signature that is determined based on detected motion(s) (e.g., tremor) in the individual’s body, implementations provide an authentication technique that is unobtrusive and easy from the perspective of the individual being authenticated, with minimal effort performed by the individual. This provides a more positive user experience compared to traditional techniques in which the individual may be asked to remember and enter a username, password, personal identification number (PIN), answers to knowledge-based questions (e.g., what is your mother’s maiden name?), and/or other credential(s). Moreover, implementations provide an authentication technique that is more secure and less vulnerable to spoofing compared to traditional authentication methods. Traditional user credentials (e.g., password, PIN, etc.) may be guessed or stolen, but a motion signature based on measured motions of the individual’s body would be much more difficult to spoof Implementations further inhibit spoofing by correlating known and ongoing real-time biometric (e.g., bio-signal) analysis from the user and device(s) operated by, or in proximity to, the user. For example, a user may be wearing a heart rate monitor, as a standalone sensor, fitness tracking device, wearable computer, or other suitable user device.”

The claims supplied by the inventors are:

“1. A system, comprising: at least one processor; and a memory communicatively coupled to the at least one processor, the memory storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising: receiving motion data collected by one or more motion sensors of a user device disposed on at least one body part of a user, wherein the motion data is representative of one or more motions of the at least one body part detected via one or more additional motions of the user device during a first period of time; determining a tremor signature for the user based on an analysis of the motion data; receiving biometric data collected by one or more biometric sensors during the first period of time, the biometric data describing at least one physiological characteristic of the user other than the tremor signature; receiving location data associated with the user device while the user device is detecting the one or more additional motions during the first period of time; determining an authentication result for the user based on the tremor signature, the biometric data, and the location data, and a user model associated with the user, wherein the user model is determined by applying a machine learning algorithm to a baseline tremor signature, a baseline biometric data, and baseline location data acquired over a second period of time different from the first period of time, and wherein the user model comprises an expected tremor signature, expected biometric data, and expected location data during the first period of time, wherein a successful authentication corresponds to a threshold amount of similarity between: a first collection of the tremor signature, the biometric data, and the location data; and a second collection of the expected tremor signature, the expected biometric data, and the expected location data; in response to the authentication result indicating an unsuccessful authentication: sending, by the at least one processor, a request to the user device for a credential-based authentication of the user, wherein the request is configured to cause the user device to receive an input for the credential-based authentication; receiving the input from the user device; and authenticating the user based on the input; and in response to the authentication result indicating a successful authentication: updating the user model based on the tremor signature, the biometric data, and the location data.

“2. The system of claim 1, the operations comprising: in response to authenticating the user based on the input: sending a second request to the user device, wherein the second request is configured to cause the user device to receive a second input representative of a state of the user; and receiving the second input from the user device.

“3. The system of claim 2, the operations comprising generating a second baseline tremor signature based on the tremor signature and a second baseline biometric data based on the biometric data.

“4. The system of claim 3, wherein the second baseline tremor signature and the second baseline biometric data are associated with the state of the user.

“5. The system of claim 1, the operations comprising generating additional biometric data based on an analysis of motion data, wherein the additional biometric data comprises a waveform associated with a heartbeat of the user.

“6. The system of claim 1, the operations comprising removing a component of the motion data based on the analysis of the motion data, wherein the component corresponds to a periodic motion of the at least one body part of the user.

“7. The system of claim 6, wherein the component of the motion data corresponds to a periodic component.

“8. The system of claim 1, wherein the input comprises a username, a personal identification number, a password, or any combination thereof.

“9. The system of claim 1, wherein the biometric data comprises audio data associated with a recording from the user device.

“10. A computer-implemented method performed by at least one processor, the method comprising: receiving, by the at least one processor, motion data collected by one or more motion sensors of a user device disposed on at least one body part of a user, wherein the motion data is representative of one or more motions of the at least one body part detected via one or more additional motions of the user device during a first period of time; determining, by the at least one processor, a tremor signature for the user based on an analysis of the motion data; receiving, by the at least one processor, biometric data collected by one or more biometric sensors during the first period of time, the biometric data describing at least one physiological characteristic of the user other than the tremor signature; receiving location data associated with the user device while the user device is detecting the one or more additional motions during the first period of time; determining, by the at least one processor, an authentication result for the user based on the tremor signature, the biometric data, and the location data, and a user model associated with the user, wherein the user model is determined by applying a machine learning algorithm to a baseline tremor signature, a baseline biometric data, and baseline location data acquired over a second period of time different from the first period of time, and wherein the user model comprises an expected tremor signature, expected biometric data, and expected location data during the first period of time, wherein a successful authentication corresponds to a threshold amount of similarity between: a first collection of the tremor signature, the biometric data, and the location data; and a second collection of the expected tremor signature, the expected biometric data, and the expected location data; in response to the authentication result indicating an unsuccessful authentication: sending, by the at least one processor, a request to the user device for an input-based authentication of the user, wherein the request is configured to cause the user device to receive an input for the input-based authentication; receiving, by the at least one processor, the input from the user device; and authenticating, by the at least one processor, the user based on the input; and in response to authenticating the user based on the input: updating, by the at least one processor, the user model based on the tremor signature, the biometric data, and the location data.

“11. The method of claim 10, wherein the input is representative of a state of the user, and wherein the state of the user comprises a posture of the user, a health condition of the user, a motion context associated with the user, or any combination thereof.

“12. The method of claim 10, wherein the request is configured to cause the user device to display a question.

“13. The method of claim 10, comprising: in response to authenticating the user based on the input: sending, by the at least one processor, a second request to the user device, wherein the second request is configured to cause the user device to receive a second input representative of a state of the user; receiving, by the at least one processor, the second input from the user device; and updating, by the at least one processor, the user model based on the second input.

“14. The method of claim 10, comprising: receiving, by the at least one processor, the location data collected by one or more location sensors.

“15. The method of claim 14, wherein the location data comprises one or more wireless network signals.

“16. The method of claim 10, comprising receiving, by the at least one processor, video data corresponding to the motion data.

“17. The method of claim 16, comprising generating, by the at least one processor, additional biometric data based on an analysis of the video data, wherein the additional biometric data comprises a waveform associated with a heartbeat of the user.”

There are additional claims. Please visit full patent to read further.

For more information, see this patent: Billman, Bradley Jay. Authentication based on motion and biometric data. U.S. Patent Number 11822633, filed October 21, 2020, and published online on November 21, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11822633)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)