Trip based characterization using micro prediction determinations
AssigneeLytx, Inc.
InventorJesse Daniels
Life of this patent
Estimating the term…
Abstract
A system for characterizing driver behavior includes an interface and a processor. The interface is configured to receive a set of vehicle data, wherein the set of vehicle data comprises embedded image vectors that characterize vehicle data over a short time scale. The processor is configured to determine, using a long time scale model, a long time scale label based at least in part on the embedded image vectors.
Claims21
A system for characterizing driver behavior, comprising:
- an interface configured to:
- receive short time scale vehicle data associated with a vehicle with a mounted vehicle event recorder, wherein the short time scale vehicle data comprises an embedded image vector that characterizes vehicle data over a short time period, wherein a short time scale model executing on the event recorder generates the embedded image vector using image data associated with the short time period;
- and
- a processor configured to:
- determine, using a long time scale model, a long time scale label associated with the embedded image vector;
- and
- assign the long time scale label to the embedded image vector, wherein the long time scale model is trained using a set of existing long time scale labeled embedded image vectors.
A method for characterizing driver behavior, comprising:
- receiving short time scale vehicle data associated with a vehicle with a mounted vehicle event recorder, wherein the short time scale vehicle data comprises an embedded image vector that characterizes vehicle data over a short time period, wherein a short time scale model executing on the event recorder generates the embedded image vector using image data associated with the short time period;
- determining, using a long time scale model executing on a processor, a long time scale label associated with the embedded image vector;
- and
- assigning the long time scale label to the embedded image vector, wherein the long time scale model is trained using a set of existing long time scale labeled embedded image vectors.
A computer program product for characterizing driver behavior, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
- receiving a short time scale vehicle data associated with a vehicle with a mounted vehicle event recorder, wherein the short time scale vehicle data comprises an embedded image vector that characterizes vehicle data over a short time period wherein a short time scale model executing on the event recorder generates the embedded image vector using image data associated with the short time period;
- determining, using a long time scale model executing on a processor, a long time scale label associated with the embedded image vector;
- and
- assigning the long time scale label to the embedded image vector, vector, wherein the long time scale model is trained using a set of existing long time scale labeled embedded image vectors.
Dependencies are inferred from the claim text.