Patent Issued for Controlling vehicles using contextual driver and/or rider data based on automatic passenger detection and mobility status (USPTO 11651316): Allstate Insurance Company

2023 JUN 05 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Allen, Rachel Edelshteyn (Chicago, IL, US), filed on July 14, 2017, was published online on May 16, 2023.

The assignee for this patent, patent number 11651316, is Allstate Insurance Company (Northbrook, Illinois, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Aspects of the disclosure relate to controlling the operation of one or more vehicles of a shared mobility service, such as a rideshare service, car-share service, carpool service, peer to peer pickup service, and the like. Shared mobility services are becoming increasingly common as shared mobility services and applications continue to improve. Autonomous vehicles may further increase the utility and appeal of shared mobility services. Despite advances in various technologies, however, it may be difficult to effectively match riders with other riders and/or drivers (e.g., for shared mobility services that do not rely on autonomous vehicles). Such effective matching is hampered by lack of data about riders, drivers, and vehicles, especially when a new rider, driver, or vehicle first joins a shared mobility service. Additionally, it may be difficult for a shared mobility service to control vehicles of the shared mobility service to incentivize safe and effective operation, provide risk insurance that accounts for the needs of shared mobility services, and otherwise control operation of a shared mobility service.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “Aspects of the disclosure provide effective, efficient, scalable, and convenient technical solutions that address and overcome the technical problems associated with matching riders with other riders and/or drivers of a shared mobility service, particularly in instances in which riders and drivers vary in terms of their personal attributes and/or when drivers vary in terms of safe driving and other abilities.

“In accordance with one or more embodiments, a computing platform having at least one processor, a memory, and a communication interface may receive driving information associated with a first driver of a shared mobility service. Subsequently, the computing platform may determine, based on at least one of recorded audio signals and a wireless signal, one or more time periods during which the first driver was transporting at least one passenger of the shared mobility service. Thereafter, the computing platform may determine, based on correlating the driving information with the one or more time periods, a first score for the first driver. Then, the computing platform may transmit a notification of a ride opportunity to the first driver responsive to determining that the first score for the first driver is higher than a second score for a second driver.

“In some embodiments, the computing platform may also determine a safety score estimating the first driver’s safety, determine a revenue score estimating the first driver’s revenue, and combine the safety score with the revenue score to yield a composite score.

“In some embodiments, the computing platform may determine the one or more time periods by analyzing the recorded audio signals to detect a voice of the at least one passenger. For example, the computing platform may analyze the recorded audio signals to detect a voice of the least one passenger by generating, from the recorded audio signals, a first voice print, comparing the first voice print to a second voice print associated with the driver, and determining, based on the comparison, that the first voice print does not match the second voice print. Additionally or alternatively, the computing platform may determine the one or more time periods by analyzing the wireless signal associated with a mobile device of the at least one passenger. The computing platform may also determine, for the one or more time periods, a number of passengers of the shared mobility service.

“In some embodiments, the computing platform may determine that the first driver and the second driver are within a threshold distance of a pickup location associated with the ride opportunity. In some embodiments, the computing platform may determine, based on the first score, a percentage of a fare to award to the first driver.”

The claims supplied by the inventors are:

“1. A method comprising: at a shared mobility service management computing platform comprising at least one processor, memory, and a communication interface: receiving, by the at least one processor, via the communication interface, driving information associated with a first driver of a shared mobility service, the driving information based on processed sensor data received from one or more sensors in proximity of a vehicle associated with the first driver during driving; determining, by the at least one processor, one or more first time periods when the first driver was transporting at least one passenger by detecting at least one indicator of the at least one passenger, the at least one indicator being a recorded voice of the at least one passenger, a recorded video of the at least one passenger, or a recorded passive wireless signal of a passenger device associated with the at least one passenger, wherein the one or more first time periods are associated with a passenger mobility status; determining at least one of one or more second time periods when the first driver is not transporting at least one passenger and waiting for a ride associated with a waiting mobility status, one or more third time periods when the first driver is heading towards a ride associated with a ride-bound mobility status, or one or more fourth time periods when the first driver is driving on personal time associated with a personal mobility status; filtering, by the at least one processor and based on at least one of the at least one indicator of the at least one passenger or trip data, the driving information to obtain a first subset of the driving information associated with the one or more first time periods and at least one of a second subset of the driving information associated with the one or more second time periods, a third subset of the driving information associated with the one or more third time periods, or a fourth subset of the driving information associated with the one or more fourth time periods; using a first machine learning model to generate, by the at least one processor, based on the first subset of the driving information, a first safety score indicating a level of safety of the first driver during the one or more first time periods based on at least the processed sensor data, wherein the first machine learning model is trained by trip data that correlates to the passenger mobility status; using at least one of a second machine learning model, a third machine learning model, or a fourth machine learning model to generate, by the at least one processor, a second safety score indicating a level of safety during the one or more second time periods, a third safety score indicating a level of safety during the one or more third time periods, a fourth safety score indicating a level of safety during the one or more fourth time periods, respectively, based on at least the processed sensor data, wherein the second machine learning model is trained by trip data that correlates to the waiting mobility status, wherein the third machine learning model is trained by trip data that correlates to the ride-bound mobility status, and wherein the second machine learning model is trained by trip data that correlates to the personal mobility status; setting different insurance costs per mile for the first driver between when the first driver is transporting at least one passenger and at least one of waiting for a ride, heading toward a ride, or driving on personal time, based on the first safety score and at least one of the second safety score, the third safety score, or the fourth safety score, respectively; and determining, by the at least one processor, based on the first safety score, a percentage of a fare to award to the first driver.

“2. The method of claim 1, further comprising: receiving, by the at least one processor, during the one or more first time periods in which the first driver was transporting the at least one passenger associated with the shared mobility service, a recorded audio signal of the at least one passenger; and analyzing, by the at least one processor, the recorded audio signal to detect a voice of a passenger associated with the shared mobility service.

“3. The method of claim 2, wherein the analyzing of the recorded audio signal to detect the voice of the passenger associated with the shared mobility service comprises: determining, based on one or more acoustic properties of the recorded audio signal, whether the recorded audio signal contains a media program; and detecting the voice of the passenger associated with the shared mobility service responsive to determining that the recorded audio signal does not contain a media program.

“4. The method of claim 2, wherein the analyzing of the recorded audio signal to detect the voice of the passenger associated with the shared mobility service comprises: generating, by the at least one processor, from the recorded audio signal, a first voice print; comparing, by the at least one processor, the first voice print to a second voice print associated with the first driver; and determining, by the at least one processor, based on the comparison, that the first voice print does not match the second voice print.

“5. The method of claim 1, further comprising: after receiving the wireless signal, analyzing, by the at least one processor, the wireless signal to determine a number of mobile devices present in the vehicle.

“6. The method of claim 1, further comprising: determining, by the at least one processor, that the first driver is within a threshold distance of a pickup location associated with a ride opportunity.

“7. The method of claim 1, further comprising: determining, by the at least one processor, a number of passengers associated with the shared mobility service inside the vehicle associated with the first driver.

“8. The method of claim 1, further comprising: transmitting, by the at least one processor, via the communication interface, to a mobile system associated with the first driver, an indication of the first safety score and a recommendation for improving the first safety score.

“9. The method of claim 1, further comprising: determining, based on the driving information, an attribute characterizing the first driver.

“10. The method of claim 9, further comprising: increasing, based on a determination that a potential passenger associated with a ride opportunity is also associated with the attribute, a percentage of a fare awarded to the first driver.

“11. The method of claim 1, further comprising: determining a similarity between a first profile of a potential passenger associated with a ride opportunity and a second profile of a current passenger being transported by the first driver; and determining, based on the similarity, a fare for the potential passenger.”

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

For more information, see this patent: Allen, Rachel Edelshteyn. Controlling vehicles using contextual driver and/or rider data based on automatic passenger detection and mobility status. U.S. Patent Number 11651316, filed July 14, 2017, and published online on May 16, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11651316)&db=USPAT&type=ids

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