Session-based transportation dispatch

Abstract

The present application discloses an improved transportation matching system, and corresponding methods and computer-readable media. According to disclosed embodiments, a transportation matching system receives session information from a requestor computing device in response to one or more session events. The system utilizes the received session information to determine a likelihood that the associated session on the requestor computing device will result in a transportation request. If the determined likelihood is above a threshold amount, the system generates an upfront dispatch that matches the associated session to a provider computing device. The system then reserves the provider computing device and generates a predicted dispatch for the reserved provider computing device.

We claim: 
     
         1 . A computer-implemented method comprising:
 monitoring, by one or more servers of a transportation matching system, a first set of pre-transportation request user interface interactions with a first user interface of a transportation matching application executed on a first requestor computing device within a geographic region;   identifying, via a global positioning system, a second requestor computing device within a threshold distance of the first requestor computing device in the geographic region;   monitoring, by the one or more servers of the transportation matching system, a second set of pre-transportation request user interface interactions with a second user interface of the transportation matching application executed on the second requestor computing device;   generating, by the one or more servers utilizing a session model without receiving transportation requests form the first requestor computing device or the second requestor computing device, a bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device; and   generating, based on the bundled session transportation request likelihood, an upfront dispatch of one or more provider computing devices to the geographic region.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein generating the bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device comprises:
 generating, utilizing the session model, a first transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device;   generating, utilizing the session model, a second transportation request likelihood based on the second set of pre-transportation request user interface interactions of the second requestor computing device; and   generating the bundled session transportation request likelihood by combining the first transportation request likelihood and the second transportation request likelihood.   
     
     
         3 . The computer-implemented method of  claim 1 , wherein generating the bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device comprises:
 generating bundled session information by combining the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device; and   generating, utilizing the session model, the bundled session transportation request likelihood based on the bundled session information.   
     
     
         4 . The computer-implemented method of  claim 1 , further comprising generating the upfront dispatch in response to determining that the bundled session transportation request likelihood satisfied an upfront dispatch threshold. 
     
     
         5 . The computer-implemented method of  claim 1 , further comprising:
 transmitting, from the one or more servers to the one or more provider computing devices, a predicted dispatch notification based on the bundled session transportation request likelihood; and   receiving, from the one or more provider computing devices, a pre-acceptance notification.   
     
     
         6 . The computer-implemented method of  claim 5 , further comprising in response to receiving, at the one or more servers from the one or more provider computing devices, the pre-acceptance notification, providing, for display via the first requestor computing device, an upfront dispatch indication. 
     
     
         7 . The computer-implemented method of  claim 6 , further comprising in response to providing the upfront dispatch indication for display via the first requestor computing device, receiving, from the first requestor computing device, a transportation request. 
     
     
         8 . The computer-implemented method of  claim 1 , further comprising determining, by the one or more servers and based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device, a predicted time until a transportation request is received. 
     
     
         9 . The computer-implemented method of  claim 8 , further comprising generating the upfront dispatch in response to determining that the predicted time satisfies a time threshold. 
     
     
         10 . A transportation matching system comprising:
 at least one processor; and   at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the transportation matching system to:   monitor a first set of pre-transportation request user interface interactions with a first user interface of a transportation matching application executed on a first requestor computing device within a geographic region;   identify, via a global positioning system, a second requestor computing device within a threshold distance of the first requestor computing device in the geographic region;   monitor a second set of pre-transportation request user interface interactions with a second user interface of the transportation matching application executed on the second requestor computing device;   generating, utilizing a session model without receiving transportation requests form the first requestor computing device or the second requestor computing device, a bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device; and   generating, based on the bundled session transportation request likelihood, an upfront dispatch of one or more provider computing devices to the geographic region.   
     
     
         11 . The transportation matching system of  claim 10 , further storing instructions thereon that, when executed by the at least one processor, cause the transportation matching system to generate the bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device by:
 generating, utilizing the session model, a first transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device;   generating, utilizing the session model, a second transportation request likelihood based on the second set of pre-transportation request user interface interactions of the second requestor computing device; and   generating the bundled session transportation request likelihood by combining the first transportation request likelihood and the second transportation request likelihood.   
     
     
         12 . The transportation matching system of  claim 10 , further storing instructions thereon that, when executed by the at least one processor, cause the transportation matching system to generate the bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device by:
 generating bundled session information by combining the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device; and   generating, utilizing the session model, the bundled session transportation request likelihood based on the bundled session information.   
     
     
         13 . The transportation matching system of  claim 10 , further storing instructions thereon that, when executed by the at least one processor, cause the transportation matching system to generate the upfront dispatch in response to determining that the bundled session transportation request likelihood satisfied an upfront dispatch threshold. 
     
     
         14 . The transportation matching system of  claim 10 , further storing instructions thereon that, when executed by the at least one processor, cause the transportation matching system to:
 transmit, to the one or more provider computing devices, a predicted dispatch notification based on the bundled session transportation request likelihood;   receiving, from the one or more provider computing devices, a pre-acceptance notification; and   in response to receiving, from the one or more provider computing devices, the pre-acceptance notification, providing, for display via the first requestor computing device, an upfront dispatch indication.   
     
     
         15 . The transportation matching system of  claim 10 , further storing instructions thereon that, when executed by the at least one processor, cause the transportation matching system to:
 determine, based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device, a predicted time until a transportation request is received; and   generate the upfront dispatch in response to determining that the predicted time satisfies a time threshold.   
     
     
         16 . A non-transitory computer-readable medium storing instructions thereon that, when executed by at least one processor, cause the at least one processor to:
 monitor a first set of pre-transportation request user interface interactions with a first user interface of a transportation matching application executed on a first requestor computing device within a geographic region;   identify, via a global positioning system, a second requestor computing device within a threshold distance of the first requestor computing device in the geographic region;   monitor a second set of pre-transportation request user interface interactions with a second user interface of the transportation matching application executed on the second requestor computing device;   generating, utilizing a session model without receiving transportation requests form the first requestor computing device or the second requestor computing device, a bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device; and   generating, based on the bundled session transportation request likelihood, an upfront dispatch of one or more provider computing devices to the geographic region.   
     
     
         17 . The non-transitory computer-readable medium of  claim 16  further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate the bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device by:
 generating, utilizing the session model, a first transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device; 
 generating, utilizing the session model, a second transportation request likelihood based on the second set of pre-transportation request user interface interactions of the second requestor computing device; and 
 generating the bundled session transportation request likelihood by combining the first transportation request likelihood and the second transportation request likelihood. 
 
     
     
         18 . The non-transitory computer-readable medium of  claim 16  further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate the bundled session transportation request likelihood based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device by:
 generating bundled session information by combining the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device; and 
 generating, utilizing the session model, the bundled session transportation request likelihood based on the bundled session information. 
 
     
     
         19 . The non-transitory computer-readable medium of  claim 16  further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate the upfront dispatch in response to determining that the bundled session transportation request likelihood satisfied an upfront dispatch threshold. 
     
     
         20 . The non-transitory computer-readable medium of  claim 16  further comprising instructions that, when executed by the at least one processor, cause the at least one processor to:
 determine, based on the first set of pre-transportation request user interface interactions of the first requestor computing device and the second set of pre-transportation request user interface interactions of the second requestor computing device, a predicted time until a transportation request is received; and 
 
       generate the upfront dispatch in response to determining that the predicted time satisfies a time threshold.