# US 11,907,342 B2 · Selection of authentication function according to environment of user device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,907,342 B2 - Document ID: US11907342B2 - Status: Granted - Kind: B2 - Application number: 16/949,945 - Filed: 2020-11-20 - Published: 2022-05-26 - Granted: 2024-02-20 - Earliest claimed: 2020-11-20 - Assignees: QUALCOMM Incorporated - Applicants: QUALCOMM Incorporated - Inventors: Russell Gruhlke; Naga Chandan Babu Gudivada; Vishnu Vardhan Kasilya Sudarsan; Sumeet Kumar Sahu; Ravishankar Sivalingam - Web page: https://patentgrep.com/patent/US11907342B2 ## CPC - G06F 21/31: User authentication - H04L 63/08: {for authentication of entities (cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32)} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract In some aspects, a user device may detect an authentication event associated with unlocking the user device. The user device may determine, based at least in part on sensor data from a sensor of the user device, an environmental context of the user device. The user device may select, from a plurality of authentication functions of the user device, an authentication function based at least in part on the environmental context of the user device. The user device may activate an authentication component that is associated with the authentication function to authenticate a user in association with unlocking the user device. Numerous other aspects are provided. ## Claims ### Claim 1 A method, comprising: detecting an authentication event associated with unlocking a user device; determining, based at least in part on sensor data from a sensor of the user device, an environmental context of the user device; selecting, from a plurality of authentication functions of the user device, a facial recognition authentication function based at least in part on the environmental context of the user device, wherein the environmental context indicates one or more of: whether the user device is still or in motion, an amount of ambient light surrounding the user device, an orientation of the user device, or a position of a finger relative to a fingerprint sensor; and activating an authentication component that is associated with the facial recognition authentication function to authenticate a user in association with unlocking the user device. ### Claim 2 (depends on 1) The method of claim 1, wherein detecting the authentication event comprises at least one of: detecting an interaction with an input component of the user device, detecting, via motion data from an accelerometer of the user device, a motion of the user device associated with the authentication event, or detecting, via image data of a vision sensor of the user device, that the user is interacting with the user device. ### Claim 3 (depends on 1) The method of claim 1, wherein the sensor data is associated with a low-power sensor of the user device that facilitates an always-on context detection capability when a user interface of the user device is in a locked state. ### Claim 4 (depends on 3) The method of claim 3, wherein the low-power sensor comprises at least one of: a vision sensor of the user device, an accelerometer of the user device, or a gyroscope of the user device. ### Claim 5 (depends on 1) The method of claim 1, wherein the authentication component is a separate component of the user device from the sensor. ### Claim 6 (depends on 1) The method of claim 1, wherein the sensor data comprises image data, wherein determining the environmental context comprises: detecting, according to an object detection technique, the finger depicted in an image associated with the image data, and determining the position of the finger relative to the fingerprint sensor, and wherein selecting the facial recognition authentication function comprises: determining whether the position of the finger is within a threshold distance of the fingerprint sensor, and selecting the facial recognition authentication function based at least in part on determining whether the position of the finger is within the threshold distance of the fingerprint sensor. ### Claim 7 (depends on 1) The method of claim 1, wherein the sensor comprises a low-power vision sensor, and wherein the authentication component comprises a camera. ### Claim 8 (depends on 1) The method of claim 1, wherein the environmental context is determined further based at least in part on a machine learning model that is trained based at least in part on historical sensor data associated with corresponding historical usage of one or more of the plurality of authentication functions. ### Claim 9 (depends on 1) The method of claim 1, further comprising: determining, based at least in part on the environmental context, that a default authentication function is to be bypassed; and preventing activation of a default authentication component that is associated with the default authentication function. ### Claim 10 (depends on 1) The method of claim 1, wherein the authentication component is a primary authentication component, and wherein the method further comprises: deactivating, based at least in part on a failure, the primary authentication component; determining a secondary authentication function; and activating a secondary authentication component associated with the secondary authentication function to authenticate the user. ### Claim 11 A user device, comprising: one or more memories; and one or more processors, communicatively coupled to the one or more memories, configured to: detect an authentication event associated with unlocking the user device; determine, based at least in part on sensor data, an environmental context of the user device; determine whether to select, from a plurality of authentication functions of the user device, a facial recognition authentication function based at least in part on the environmental context of the user device, wherein the environmental context indicates one or more of: whether the user device is still or in motion, an amount of ambient light surrounding the user device, an orientation of the user device, or a position of a finger relative to a fingerprint sensor; and activate, based on a determination of whether to select the facial recognition authentication function, an authentication component to authenticate a user in association with unlocking the user device. ### Claim 12 (depends on 11) The user device of claim 11, wherein the one or more processors, when detecting the authentication event, are configured to at least one of: detect an interaction with an input component of the user device, detect, via motion data from an accelerometer of the user device, a motion of the user device associated with the authentication event, or detect, via image data of a vision sensor of the user device, that the user is interacting with the user device. ### Claim 13 (depends on 11) The user of claim 11, wherein the sensor data is associated with a low-power sensor of the user device that facilitates an always-on context detection capability when a user interface of the user device is in a locked state. ### Claim 14 (depends on 11) The user device of claim 11, wherein the sensor data comprises image data, wherein, when determining the environmental context, the one or more processors are configured to: detect, according to an object detection technique the finger depicted in an image associated with the image data, and determine the position of the finger relative to the fingerprint sensor, and wherein, when determining whether to select the authentication function, the one or more processors are configured to: determine whether to select the facial recognition authentication function based at least in part on the position of the finger relative to the fingerprint sensor. ### Claim 15 (depends on 11) The user device of claim 11, wherein the environmental context is determined further based at least in part on a machine learning model that is trained based at least in part on historical sensor data associated with corresponding historical usage of one or more of the plurality of authentication functions. ### Claim 16 (depends on 11) The user device of claim 11, wherein the one or more processors are further configured to: prior to selecting the authentication function, determining, based at least in part on the environmental context, that a default authentication function is to be bypassed; and preventing activation of a default authentication component that is associated with the default authentication function. ### Claim 17 (depends on 11) The user device of claim 11, wherein the facial recognition authentication function is a primary authentication function or a secondary authentication function, wherein the authentication component is a primary authentication component, and wherein the one or more processors are further configured to: detect a failure associated with the primary authentication function authenticating the user; deactivate, based at least in part on the failure, the primary authentication component; determine, based at least in part on the environmental context, the secondary authentication function; and activate a secondary authentication component associated with the secondary authentication function to authenticate the user. ### Claim 18 (depends on 11) The user device of claim 11, wherein the environmental context indicates the orientation of the user device, and wherein the orientation of the user device is a horizontal orientation or a vertical orientation. ### Claim 19 (depends on 11) The user device of claim 11, wherein the environmental context indicates the orientation of the user device, and wherein, when determining whether to select the facial recognition authentication function, the one or processors are configured to: determine, based on the orientation of the user device, whether the user is within a field of view of a camera used to obtain an image of the user for performing the facial recognition authentication function. ### Claim 20 (depends on 11) The user device of claim 11, wherein the environmental context indicates that the user device is in motion, wherein, when determining whether to select the facial recognition authentication function, the one or processors are configured to: determine to select the facial recognition authentication function based on the user device not being in motion. ### Claim 21 (depends on 11) The user device of claim 11, wherein, when determining whether to select the facial recognition authentication function, the one or processors are configured to: determine whether to select the facial recognition authentication function based on the environmental context and based on preference information indicated by the user. ### Claim 22 A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: one or more instructions that, when executed by one or more processors of a user device, cause the user device to: detect an authentication event associated with unlocking the user device; determine, based at least in part on sensor data, an environmental context of the user device; select, from a plurality of authentication functions of the user device, a facial recognition authentication function based at least in part on the environmental context of the user device, wherein the environmental context indicates one or more of: whether the user device is still or in motion, an amount of ambient light surrounding the user device, an orientation of the user device, or a position of a finger relative to a fingerprint sensor; and activate an authentication component based on selecting the facial recognition authentication function. ### Claim 23 (depends on 22) The non-transitory computer-readable medium of claim 22, wherein the sensor data is associated with a low-power sensor of the user device that facilitates an always-on context detection capability when a user interface of the user device is in a locked state. ### Claim 24 (depends on 23) The non-transitory computer-readable medium of claim 23, wherein the low-power sensor comprises at least one of: a vision sensor of the user device, an accelerometer of the user device, or a gyroscope of the user device. ### Claim 25 (depends on 22) The non-transitory computer-readable medium of claim 22, wherein the sensor data comprises image data, and wherein the environmental context is based on the finger being depicted in an image associated with the image data. ### Claim 26 An apparatus, comprising: means for detecting an authentication event associated with unlocking a user device that includes the apparatus; means for determining, based at least in part on sensor data, an environmental context of the user device; means for selecting, from a plurality of authentication functions of the user device, a facial recognition authentication function based at least in part on the environmental context of the user device; and means for activating an authentication component that is associated with the facial recognition authentication function to authenticate a user in association with unlocking the user device. ### Claim 27 (depends on 26) The apparatus of claim 26, wherein the sensor data is associated with a low-power sensor of the user device that facilitates an always-on context detection capability when a user interface of the user device is in a locked state. ### Claim 28 (depends on 27) The apparatus of claim 27, wherein the low-power sensor comprises at least one of: a vision sensor of the user device, an accelerometer of the user device, or a gyroscope of the user device. ### Claim 29 (depends on 26) The apparatus of claim 26, wherein the environmental context is determined further based at least in part on a machine learning model that is trained based at least in part on historical sensor data associated with corresponding historical usage of one or more of the plurality of authentication functions. ### Claim 30 (depends on 26) The apparatus of claim 26, wherein the facial recognition authentication function is a primary authentication function or a secondary authentication function, wherein the authentication component is a primary authentication component or a secondary authentication component, and wherein the apparatus further comprises: means for detecting a failure associated with the primary authentication function authenticating the user; means for deactivating, based at least in part on the failure, the primary authentication component; means for determining, based at least in part on the environmental context, a secondary authentication function; and means for activating a secondary authentication component associated with the secondary authentication function to authenticate the user.