# US 12,002,364 B1 · Facial recognition technology for improving driver safety > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,002,364 B1 - Document ID: US12002364B1 - Status: Granted - Kind: B1 - Application number: 18/130,756 - Filed: 2023-04-04 - Granted: 2024-06-04 - Earliest claimed: 2019-10-02 - Assignees: Samsara Inc. - Applicants: Samsara Inc. - Inventors: Evaline Shin-Tin Tsai; Alan Guihong Liu; Ijeoma Emeagwali; Ishaan Kansal; Saleh ElHattab; Bodecker John DellaMaria; Eliott Ray Chapuis; Jason Noah Laska; Jennifer Kao; Sean Kyungmok Bae; Sylvie Lee; Brian Tuan - Web page: https://patentgrep.com/patent/US12002364B1 ## CPC - G08G 1/20: {Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles} - B60R 11/04: Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06T 7/74: {involving reference images or patches} - G06V 20/59: inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions - G06V 40/16: Human faces, e.g. facial parts, sketches or expressions - G06V 40/173: {face re-identification, e.g. recognising unknown faces across different face tracks} - G07C 5/02: Registering or indicating driving, working, idle, or waiting time only (apparatus forming part of taximeters G07B13/00) - G08G 1/017: identifying vehicles (G08G1/015, G08G1/054 take precedence) - B60R 2300/8006: for monitoring and displaying scenes of vehicle interior, e.g. for monitoring passengers or cargo - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/30201: Face - G06T 2207/30268: Vehicle interior - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE ## Abstract Methods for performing operations for improving driver safety across a fleet of vehicles are disclosed. A plurality of safety events pertaining to a driving of a fleet of vehicles by a plurality of drivers are detected. A subset of the events is identified. The subset corresponds to one or more safety events of the plurality of safety events involving one or more vehicles of the fleet of vehicles to which drivers have not been assigned. A user interface is generated for presentation on a client device, the user interface including an interactive user interface element for accessing the subset of the events. One or more user interface elements are provided for accepting or rejecting recommendations for assignments of one of the plurality of drivers to each of the vehicles. The recommendations are generated based on an application of a machine-learned model to images of faces captured. ## Claims ### Claim 1 A system comprising: one or more computer processors; one or more computer memories; a set of instructions stored in the one or more computer memories, the set of instructions configuring the one or more computer processors to perform operations, the operations comprising: identifying a set of safety events, the set of the safety events corresponding to one or more vehicles of a set of vehicles to which one or more drivers of a set of drivers has been automatically assigned based on facial recognition; detecting a plurality of safety events pertaining to the set of vehicles; generating a user interface for presentation on a client device, the user interface including an interactive user interface element for accessing the set of the safety events; and providing one or more interactive user interface elements in the user interface for manually correcting one or more of the automatic assignments of the one or more drivers to one or more vehicles. ### Claim 2 (depends on 1) The system of claim 1, the operations further comprising displaying, in the user interface, one or more images of one or more faces captured inside the one or more vehicles when one or more of the plurality of safety events occurred. ### Claim 3 (depends on 2) The system of claim 2, wherein the one or more images of the faces are selected from a set of the one or more images of the one or more faces based on one or more quality metrics associated with the one or more images or a proximity of one or more times of one or more capturings of the one or more images to one or more times at which one or more of the plurality of safety events occurred. ### Claim 4 (depends on 1) The system of claim 1, further comprising sorting the plurality of safety events based on one or more severity levels associated with each of the plurality of safety events and, based on the accessing of the plurality of safety events, generating a list of the plurality of safety events for displaying on the client device in order of one or more severity levels. ### Claim 5 (depends on 1) The system of claim 1, further comprising updating a training of a machine-learned model based on accepting or rejecting of recommendations, the updating of the training including adding an image of a face to or removing an image of a face from a set of a plurality of images of faces associated with the set of drivers. ### Claim 6 (depends on 1) The system of claim 1, further comprising, based on accepting of a recommendation, providing user interface elements in the user interface for viewing a set of additional safety events, the set of additional safety events associated with the set of drivers. ### Claim 7 (depends on 6) The system of claim 6, further comprising sorting the set of additional safety events based on one or more levels of severity associated with each of the set of the additional safety events and providing one or more interactive user interface elements in the user interface for accepting or rejecting a corrective action for a driver of the one or more drivers, the corrective action including providing a notification to the driver to complete an online learning module pertaining to the set of the additional safety events. ### Claim 8 A method comprising: identifying a set of safety events, the set of the safety events corresponding to one or more vehicles of a set of vehicles to which one or more drivers of a set of drivers has been automatically assigned based on facial recognition; detecting a plurality of safety events pertaining to the set of vehicles; generating a user interface for presentation on a client device, the user interface including an interactive user interface element for accessing the set of the safety events; and providing one or more interactive user interface elements in the user interface for manually correcting one or more of the automatic assignments of the one or more drivers to one or more vehicles. ### Claim 9 (depends on 8) The method of claim 8, the operations further comprising displaying, in the user interface, one or more images of one or more faces captured inside the one or more vehicles when one or more of the plurality of safety events occurred. ### Claim 10 (depends on 9) The method of claim 9, wherein the one or more images of the faces are selected from a set of the one or more images of the one or more faces based on one or more quality metrics associated with the one or more images or a proximity of one or more times of one or more capturings of the one or more images to one or more times at which one or more of the plurality of safety events occurred. ### Claim 11 (depends on 8) The method of claim 8, further comprising sorting the plurality of safety events based on one or more severity levels associated with each of the plurality of safety events and, based on the accessing of the plurality of safety events, generating a list of the plurality of safety events for displaying on the client device in order of one or more severity levels. ### Claim 12 (depends on 8) The method of claim 8, further comprising updating a training of a machine-learned model based on accepting or rejecting of recommendations, the updating of the training including adding an image of a face to or removing an image of a face from a set of a plurality of images of faces associated with the set of drivers. ### Claim 13 (depends on 8) The method of claim 8, further comprising, based on accepting of a recommendation, providing user interface elements in the user interface for viewing a set of additional safety events, the set of additional safety events associated with the set of drivers. ### Claim 14 (depends on 13) The method of claim 13, further comprising sorting the set of additional safety events based on one or more levels of severity associated with each of the set of the additional safety events and providing one or more interactive user interface elements in the user interface for accepting or rejecting a corrective action for a driver of the one or more drivers, the corrective action including providing a notification to the driver to complete an online learning module pertaining to the set of the additional safety events. ### Claim 15 A non-transitory computer-readable storage medium storing a set of instructions that, when executed by one or more computer processors, causes the one or more computer processors to perform operations, the operations comprising: identifying a set of safety events, the set of the safety events corresponding to one or more vehicles of a set of vehicles to which one or more drivers of a set of drivers has been automatically assigned based on facial recognition; detecting a plurality of safety events pertaining to the set of vehicles; generating a user interface for presentation on a client device, the user interface including an interactive user interface element for accessing the set of the safety events; and providing one or more interactive user interface elements in the user interface for manually correcting one or more of the automatic assignments of the one or more drivers to one or more vehicles. ### Claim 16 (depends on 15) The non-transitory computer-readable storage medium of claim 15, the operations further comprising displaying, in the user interface, one or more images of one or more faces captured inside the one or more vehicles when one or more of the plurality of safety events occurred. ### Claim 17 (depends on 16) The non-transitory computer-readable storage medium of claim 16, wherein the one or more images of the faces are selected from a set of the one or more images of the one or more faces based on one or more quality metrics associated with the one or more images or a proximity of one or more times of one or more capturings of the one or more images to one or more times at which one or more of the plurality of safety events occurred. ### Claim 18 (depends on 15) The non-transitory computer-readable storage medium of claim 15, further comprising sorting the plurality of safety events based on one or more severity levels associated with each of the plurality of safety events and, based on the accessing of the plurality of safety events, generating a list of the plurality of safety events for displaying on the client device in order of one or more severity levels. ### Claim 19 (depends on 15) The non-transitory computer-readable storage medium of claim 15, further comprising updating a training of a machine-learned model based on accepting or rejecting of recommendations, the updating of the training including adding an image of a face to or removing an image of a face from a set of a plurality of images of faces associated with the set of drivers. ### Claim 20 (depends on 15) The non-transitory computer-readable storage medium of claim 15, further comprising, based on accepting of a recommendation, providing user interface elements in the user interface for viewing a set of additional safety events, the set of additional safety events associated with the set of drivers.