Patent Issued for Systems and methods for automatic detection of gig-economy activity (USPTO 11663675): State Farm Mutual Automobile Insurance Company

2023 JUN 21 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States) has been issued patent number 11663675, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Abella, Elijah (Chandler, AZ, US), Beachy, Dar (Hopedale, IL, US), Bryant, Emily (Mesa, AZ, US), DiBenedetto, Michael (Mesa, AZ, US), Estes, Hannah (Queen Creek, AZ, US), Fields, Brian M. (Normal, IL, US), Rodriguez, James P. (Avondale, AZ, US), Schwartz, Audrey (Mesa, AZ, US), Sellers, Kristin (Gilbert, AZ, US), Sherwood, Diana (Scottsdale, AZ, US), Tucker, Ben (Bloomington, IL, US), Zarkoob, Anna (Tempe, AZ, US), Zhang, Hanpei (Mesa, AZ, US).

This patent was filed on February 8, 2021 and was published online on May 30, 2023.

From the background information supplied by the inventors, news correspondents obtained the following quote: “Gig-economy work has grown significantly in recent years due to the coordination power of mobile computing networks. Millions of gig-economy workers provide a broad array of gig-economy services, such as on-demand transportation services (e.g., ridesharing or transportation network company (“TNC”) services), distributed goods delivery services, project-based home and office assistance services, and other services on an ad hoc or transactional basis.

“The rapid increase in both supply and demand for such services has drawn in many new service providers, but information resources are lacking. The differences between traditional work and gig-economy work have left gaps in areas such as risk assessment and gig optimization. This results in an increased record-keeping burden on individual gig-economy workers to attempt to track their own activities. Additionally, by the distributed nature of gig-economy work, the supply of gig-economy is the result of many unrelated individual decisions, making it difficult for individual gig-economy workers to determine whether it is worthwhile to offer their services at any given time.

“Certain costs with significant impacts on gig-economy work profitability are also unobservable by even the most sophisticated gig-economy workers. For example, on-demand transportation services are typically in high demand at times and places where risk levels of vehicle accidents are elevated (e.g., during inclement weather, in crowded business districts, and late at night on weekends). However, risk levels associated with on-demand transportation gigs may not be directly observable. Thus, gig-economy workers are left without much-needed information relating to costs of providing gig services relative to the revenue that may be obtained from offering such services. Thus, inefficient use of gig-economy worker effort results from a lack of relevant data. Conventional techniques may have other drawbacks as well.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “The present embodiments relate to, inter alia, detecting, monitoring, and optimizing gig-economy work based upon data associated with a plurality of gig-economy workers and relating to a plurality of gigs performed by such gig-economy workers. Additional, fewer, or alternative features described herein below may be included in some aspects.

“In one aspect, a computer-implemented method for monitoring and evaluating gig-economy work (e.g., commercial driving activity) may be provided. The method may include, via one or more processors, servers, transceivers, and/or sensors, (i) receiving (and/or generating) availability data corresponding to a gig-economy worker; (ii) responsive to receiving the availability data, collecting a set of data indicative of one or more gig-related behaviors (e.g., driving behaviors) of the gig-economy worker; (iii) determining a risk score for each gig-related behavior indicated in the set of data; and/or (iv) determining a gig-economy worker profile (e.g., a commercial driving profile) corresponding to the gig-economy worker by evaluating each risk score. The method may include additional, less, or alternate actions, including those discussed elsewhere herein.

“In another aspect, a computer-implemented method for detecting gig-economy work (e.g., commercial driving activity) may be provided. The method may include, via one or more processors, servers, transceivers, and/or sensors, (i) receiving (and/or generating) movement data representing movement (e.g., movement of a vehicle) associated with a gig-economy worker; (ii) responsive to receiving the movement data, determining likelihoods that portions of the movement data are attributable to gig-economy work (e.g., commercial driving activities) based upon the movement data; and/or (iii) determining an aspect of an insurance policy for the gig-economy work or the gig-economy worker (e.g., insurance for a vehicle) based upon the likelihoods. The method may include additional, less, or alternate actions, including those discussed elsewhere herein.

“In yet another aspect, a computer-implemented method for optimizing gig-economy work (e.g., commercial driving activity) may be provided. The method may include, via one or more processors, servers, transceivers, and/or sensors, (i) receiving, at one or more processors, one or more gig optimization criteria indicating one or more outcome gig metrics to optimize; (ii) obtaining condition data indicating a plurality of conditional values for gig metrics; (iii) selecting one or more gig-economy data models associated with the one or more outcome gig metrics; (iv) generating one or more gig optimization recommendations associated with the one or more gig optimization criteria by applying at least some of the condition data to the one or more gig-economy data models; and/or (v) causing at least one of the one or more gig optimization recommendations to be presented to a gig-economy worker by a display of a mobile computing device associated with the gig-economy worker. The method may include additional, less, or alternate actions, including those discussed elsewhere herein.

“In a still a further aspect, a computer-implemented method for generating a transferable token for a gig-economy worker may be provided. Generating such a transferable token may include: (1) receiving data representing at least one of an activity, a behavior or a work of the gig-economy worker; (2) responsive to receipt of the data, determining at least one of a risk level or a risk profile for the gig-economy worker based upon the data; (3) forming a transferable token that includes the at least one of the risk level or the risk profile; and/or (4) when requested by a third party, providing the transferable token to the third party. The transferable token may be used by the third party to offer a new or updated policy, service, agreement, or account. The method may include additional, less, or alternate actions, including those discussed elsewhere herein.”

The claims supplied by the inventors are:

“1. A computer-implemented method for detecting commercial driving activity by a gig-economy worker, the method comprising: receiving, at one or more processors, movement data representing driving behaviors associated with measured movement of a vehicle associated with the gig-economy worker at a plurality of times during operation of the vehicle during the course of one or more vehicle trips, wherein the movement data includes telematics data regarding speed and acceleration of the vehicle over a plurality of trip segments of each of the one or more vehicle trips, wherein each of the plurality of trip segments is associated with a time interval and a travel path between a starting location and an ending location of the respective trip segment; training, by the one or more processors, a machine-learning model to generate likelihoods of commercial driving activities for vehicle trip segments based upon input movement data including at least speed and acceleration data; responsive to receiving the movement data: classifying, by the one or more processors implementing a classifier using the machine-learning model, the movement data associated with each of the plurality of trip segments as being either indicative of commercial driving behaviors or indicative of personal driving behaviors; and determining, by the one or more processors, (i) first likelihoods that a first set of trip segments are attributable to commercial driving activities based upon the classifications of the movement data associated with each of the first set of trip segments being classified as indicating commercial driving behaviors and (ii) second likelihoods that a second set of trip segments are attributable to non-commercial driving activities based upon the classifications of the movement data associated with each of the second set of trip segments being classified as indicating personal driving behaviors; determining, by the one or more processors, an education point for the gig-economy worker based upon the movement data associated with the first set of trip segments indicating commercial driving activities, wherein the education point comprises a recommended change in a particular driving behavior relating to control of the vehicle while engaged in commercial driving activities; causing, by the one or more processors, the education point to be presented to the gig-economy worker during vehicle operation via a display within the vehicle; receiving, at the one or more processors, gig-economy worker log data indicating a definitive classification of at least some of the trip segments of the first set of trip segments and the second set of trip segments, the definitive classification indicating whether the at least some of trip segments are associated with commercial driving activities or non-commercial driving activities; and retraining, by the one or more processors, the machine-learning model based upon the definitive classification of the at least some of the trip segments.

“2. The computer-implemented method of claim 1, wherein the telematics data is collected by one or more on-board sensors of the vehicle that are communicatively coupled to the one or more processors or by at least one of one or more sensors of a mobile device in the vehicle.

“3. The computer-implemented method of claim 1, wherein training the machine-learning model is based upon a set of prior data indicating one or more segments of the movement data.

“4. The computer-implemented method of claim 1, further comprising: determining, by the one or more processors, an aspect of an insurance policy for the vehicle based upon the first and second likelihoods, 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.

“5. The computer-implemented method of claim 1, wherein the movement data additionally represents movement of another vehicle associated with another gig-economy worker.

“6. The computer-implemented method of claim 1, wherein classifying the movement data as being attributable to commercial driving activities is based upon a set of data including the movement data and at least one of log data, behavior data, gig applications data, scraped data or environmental data.

“7. The computer-implemented method of claim 1, wherein training the machine-learning model is based upon the movement data and additional movement data for a plurality of other gig-economy workers.

“8. The computer-implemented method of claim 1, further comprising: receiving a set of data including at least one of log data, behavior data, gig applications data, scraped data or environmental data for a plurality of gig-economy workers and a plurality of non-gig economy workers, wherein training the machine-learning model is based upon the set of data.

“9. A system comprising: a processor; and a non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by the processor, cause the system to: receive movement data representing driving behaviors associated with measured movement of a vehicle associated with a gig-economy worker at a plurality of times during operation of the vehicle during the course of one or more vehicle trips, wherein the movement data includes telematics data regarding speed and acceleration of the vehicle over a plurality of trip segments of each of the one or more vehicle trips, wherein each of the plurality of trip segments is associated with a time interval and a travel path between a starting location and an ending location of the respective trip segment; train a machine-learning model to generate likelihoods of commercial driving activities for vehicle trip segments based upon input movement data including at least speed and acceleration data; responsive to receiving the movement data: classify, by implementing a classifier using the machine-learning model, the movement data associated with each of the plurality of trip segments as being either indicative of commercial driving behaviors or indicative of personal driving behaviors; and determine (i) first likelihoods that a first set of trip segments are attributable to commercial driving activities based upon the classifications of the movement data associated with each of the first set of trip segments being classified as indicating commercial driving behaviors and (ii) second likelihoods that a second set of trip segments are attributable to non-commercial driving activities based upon the classifications of the movement data associated with each of the second set of trip segments being classified as indicating personal driving behaviors; determine an education point for the gig-economy worker based upon the movement data associated with the first set of trip segments indicating commercial driving activities, wherein the education point comprises a recommended change in a particular driving behavior relating to control of the vehicle while engaged in commercial driving activities; cause the education point to be presented to the gig-economy worker during vehicle operation via a display within the vehicle, receive gig-economy worker log data indicating a definitive classification of at least some of the trip segments of the first set of trip segments and the second set of trip segments, the definitive classification indicating whether the at least some of trip segments are associated with commercial driving activities or non-commercial driving activities; and retrain the machine-learning model based upon the definitive classification of the at least some of the trip segments.

“10. The system of claim 9, wherein: the computer-readable instructions, when executed by the processor, cause the system to receive the telematics data from at least one of one or more on-board sensors of the vehicle or one or more sensors of a mobile device in the vehicle.

“11. The system of claim 9, wherein the movement data additionally represents movement of another vehicle associated with another gig-economy worker.

“12. The system of claim 9, wherein the computer-readable instructions, when executed by the processor, cause the system to classify the movement data as being attributable to commercial driving activities based upon a set of data including the movement data and at least one of log data, behavior data, gig applications data, scraped data or environmental data.

“13. The system of claim 9, wherein the computer-readable instructions, when executed by the processor, cause the system to: receive a set of data including at least one of log data, behavior data, gig applications data, scraped data or environmental data for a plurality of gig-economy workers and a plurality of non-gig economy workers, wherein the machine-learning model is trained based upon the set of data.”

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

For the URL and additional information on this patent, see: Abella, Elijah. Systems and methods for automatic detection of gig-economy activity. U.S. Patent Number 11663675, filed February 8, 2021, and published online on May 30, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11663675)&db=USPAT&type=ids

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