Systems and methods for automatic detection of gig-economy activitysystems and methods for automatic detection of gig-economy activity

Abstract

Systems and methods relating to improving the experience of gig-economy workers are disclosed, with particular reference to gig-economy work involving vehicle use. Such systems and methods include automatically monitoring and evaluating activities such as driving during performance of gigs, as well as providing recommendations based thereupon. Gig-related activities may be automatically detected based upon data provided by a mobile device associated with the gig-economy worker, thereby automatically generating a record of such activities for the worker. Telematics data indicative of movement of a vehicle may be collected and analyzed to detect gig-economy activities. During or after performance of gig-economy work, data automatically collected may be used to generate and present recommendations or education points to the gig-economy worker.

What is claimed is: 
     
         1 . A computer-implemented method for automatically classifying driving activity by a gig-economy worker, the method comprising:
 obtaining, by one or more processors, telematics data associated with operation of one or more vehicles by the gig-economy worker, wherein the telematics data comprises at least speed and location data for a plurality of trip segments corresponding to respective times and road segments of the plurality of trip segments;   generating, by a classifier executed by the one or more processors, a likelihood score for each of the plurality of trip segments based upon the telematics data associated with such trip segment, wherein the likelihood score indicates a probability or probability range of the respective trip segment being a gig-related trip segment associated with gig driving activities by the gig-economy worker;   classifying, by the classifier executed by the one or more processors, each of the plurality of trip segments as being a gig-related trip segment or a non-gig-related trip segment based upon the respective likelihood score; and   identifying, by the one or more processors, one or more gig-related trips comprising a plurality of gig-related trip segments.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein obtaining the telematics data comprises controlling a plurality of sensors disposed within the one or more vehicles to record periodic measurements of the telematics data. 
     
     
         3 . The computer-implemented method of  claim 1 , further comprising:
 obtaining, by the one or more processors, environmental data regarding an operating environment of the respective vehicle for each of the plurality of trip segments,   wherein the likelihood score for each of the plurality of trip segments is determined based upon the telematics data and the environmental data associated with such trip segment.   
     
     
         4 . The computer-implemented method of  claim 1 , wherein the likelihood score for each of the plurality of trip segments is based at least in part upon comparison of the telematics data associated with the respective trip segment with a baseline profile of non-gig-related driving by the gig-economy worker. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein generating the likelihood score for each of the plurality of trip segments comprises processing the telematics data associated with the respective trip segment using a machine learning model previously trained on additional telematics data associated with a plurality of additional trip segments including both gig-related driving and non-gig-related driving by the gig-economy worker. 
     
     
         6 . The computer-implemented method of  claim 5 , where in the machine learning model has been previously validated using log data from a gig-economy platform indicating a definitive classification of at least some of the additional trip segments. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein identifying the one or more gig-related trips comprises identifying a current trip is gig-related. 
     
     
         8 . The computer-implemented method of  claim 1 , wherein identifying the one or more gig-related trips comprises identifying one or more sets of multiple gig-related trip segments separated by one or more sets of non-gig-related trip segments. 
     
     
         9 . The computer-implemented method of  claim 1 , further comprising:
 determining, by the one or more processors, an aspect of an insurance policy for the gig-economy worker based upon the telematics data associated with the gig-related trip segments of the one or more gig-related trips, wherein the aspect of the insurance policy associated with the gig-economy worker includes at least one of type of insurance, an insurance premium, a deductible, an insured limit, or a condition.   
     
     
         10 . A system for automatically classifying driving activity by a gig-economy worker, comprising:
 one or more processors; and   a non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by the one or more processors, cause the system to:
 obtain telematics data associated with operation of one or more vehicles by the gig-economy worker, wherein the telematics data comprises at least speed and location data for a plurality of trip segments corresponding to respective times and road segments of the plurality of trip segments; 
 generate a likelihood score for each of the plurality of trip segments based upon the telematics data associated with such trip segment, wherein the likelihood score indicates a probability or probability range of the respective trip segment being a gig-related trip segment associated with gig driving activities by the gig-economy worker; 
 classify each of the plurality of trip segments as being a gig-related trip segment or a non-gig-related trip segment based upon the respective likelihood score; and 
 identify one or more gig-related trips comprising a plurality of gig-related trip segments. 
   
     
     
         11 . The system of  claim 10 , wherein the computer-readable instructions that cause the system to obtain the telematics data cause the system to control a plurality of sensors disposed within the one or more vehicles to record periodic measurements of the telematics data. 
     
     
         12 . The system of  claim 10 , wherein the likelihood score for each of the plurality of trip segments is based at least in part upon comparison of the telematics data associated with the respective trip segment with a baseline profile of non-gig-related driving by the gig-economy worker. 
     
     
         13 . The system of  claim 10 , wherein the computer-readable instructions that cause the system to generate the likelihood score for each of the plurality of trip segments cause the system to process the telematics data associated with the respective trip segment using a machine learning model previously trained on additional telematics data associated with a plurality of additional trip segments including both gig-related driving and non-gig-related driving by the gig-economy worker. 
     
     
         14 . The system of  claim 10 , wherein the computer-readable instructions, when executed by the one or more processors, further cause the system to:
 determine an aspect of an insurance policy for the gig-economy worker based upon the telematics data associated with the gig-related trip segments of the one or more gig-related trips, wherein the aspect of the insurance policy associated with the gig-economy worker includes at least one of type of insurance, an insurance premium, a deductible, an insured limit, or a condition.   
     
     
         15 . A tangible, non-transitory computer-readable medium storing computer-readable instructions that, when executed by one or more processors of a system, cause the system to:
 obtain telematics data associated with operation of one or more vehicles by the gig-economy worker, wherein the telematics data comprises at least speed and location data for a plurality of trip segments corresponding to respective times and road segments of the plurality of trip segments;   generate a likelihood score for each of the plurality of trip segments based upon the telematics data associated with such trip segment, wherein the likelihood score indicates a probability or probability range of the respective trip segment being a gig-related trip segment associated with gig driving activities by the gig-economy worker;   classify each of the plurality of trip segments as being a gig-related trip segment or a non-gig-related trip segment based upon the respective likelihood score; and   identify one or more gig-related trips comprising a plurality of gig-related trip segments.   
     
     
         16 . The tangible, non-transitory computer-readable medium of  claim 15 , wherein the computer-readable instructions that cause the system to obtain the telematics data cause the system to control a plurality of sensors disposed within the one or more vehicles to record periodic measurements of the telematics data. 
     
     
         17 . The tangible, non-transitory computer-readable medium of  claim 15 , wherein:
 the computer-readable instructions, when executed by the one or more processors, further cause the system to obtain environmental data regarding an operating environment of the respective vehicle for each of the plurality of trip segments; and   the likelihood score for each of the plurality of trip segments is determined based upon the telematics data and the environmental data associated with such trip segment.   
     
     
         18 . The tangible, non-transitory computer-readable medium of  claim 15 , wherein the likelihood score for each of the plurality of trip segments is based at least in part upon comparison of the telematics data associated with the respective trip segment with a baseline profile of non-gig-related driving by the gig-economy worker. 
     
     
         19 . The tangible, non-transitory computer-readable medium of  claim 15 , wherein the computer-readable instructions that cause the system to generate the likelihood score for each of the plurality of trip segments cause the system to process the telematics data associated with the respective trip segment using a machine learning model previously trained on additional telematics data associated with a plurality of additional trip segments including both gig-related driving and non-gig-related driving by the gig-economy worker. 
     
     
         20 . The tangible, non-transitory computer-readable medium of  claim 15 , wherein the computer-readable instructions, when executed by the one or more processors, further cause the system to:
 determine an aspect of an insurance policy for the gig-economy worker based upon the telematics data associated with the gig-related trip segments of the one or more gig-related trips, wherein the aspect of the insurance policy associated with the gig-economy worker includes at least one of type of insurance, an insurance premium, a deductible, an insured limit, or a condition.