Abstract: A computing system can receive a request for the service from a client device of a user. In response to receiving the request, the system can generate a unique identifier for the request to facilitate a rendezvous between the user and a service provider.

Abstract: A system can receive a request for service from the computing device of a requesting user of the network service. The system can select a driver to provide the service for the requesting user, and transmit an invitation to the computing device of the selected driver to facilitate the request for service. The system can receive a dataset from a first device of the computing device of the requesting user or the computing device of the selected driver, the dataset indicating that the first device has detected an ultrasonic signal outputted by a second device of the computing device of the requesting user or the computing device of the selected driver. Based on receiving the dataset, the system can verify that a rendezvous between the requesting user and the selected driver has occurred.

Abstract: An estimated time of arrival (ETA) of a vehicle is predicted by receiving a request for the vehicle to conduct a trip that includes a first location. A predicted ETA for the vehicle to travel from a particular location to the first location is computed. The predicted ETA is refined to compute a refined ETA using a machine-learned model that takes as input a plurality of features associated with the trip. The plurality of features including at least geospatial features transformed using a locality-sensitive hashing function. An action is performed based on the refined ETA. The action may include one or more of estimating a pickup time or drop-off time for the trip, matching a driver to the trip, and planning a delivery.

Abstract: A computing system can receive, over the one or more networks, a request for a service from a client device of a user. In response to receiving the request, the system can generate a unique identifier for the request to facilitate a rendezvous between the user and a service provider, and transmit the unique identifier to the client device of the user. Based on the user and the service provider making the rendezvous, the system receives data corresponding to the unique identifier from a provider application executing on a client device of the service provider. Based on receiving the data corresponding to the unique identifier from the client device of the service provider, the system updates a status for the user to indicate that the service has been provided by the service provider for the user.

Abstract: A system can receive a request for service from the computing device of a requesting user of the users of the network service and select a driver to provide the service for the requesting user. The system transmits an invitation to the computing device of the selected driver to facilitate the request, and transmits a first set of data to the computing device of the requesting user or the selected driver. The first set of data enabling the computing device of the requesting user or selected driver to output an ultrasonic signal. The system then receives a second set of data indicating that the computing device of the selected driver or the user detected the ultrasonic signal. Based on receiving the second set of data, the system verifies that a rendezvous between the requesting user and the selected driver has occurred.

Abstract: A system can receive a request for service from the computing device of a requesting user of the users of the network service and select a driver to provide the service for the requesting user. The system transmits an invitation to the computing device of the selected driver to facilitate the request, and transmits a first set of data to the computing device of the requesting user or the selected driver. The first set of data enabling the computing device of the requesting user or selected driver to output an ultrasonic signal. The system then receives a second set of data indicating that the computing device of the selected driver or the user detected the ultrasonic signal. Based on receiving the second set of data, the system verifies that a rendezvous between the requesting user and the selected driver has occurred.

Abstract: A network service can detect an ultrasonic signal by an ultrasonic receptive component of a first device. The ultrasonic signal can be based on an ultrasonic output signal transmitted from an audio output component. In response to the detected ultrasonic signal, the network service can perform a network service operation.

Abstract: A computing system can receive, over the one or more networks, a request for a service from a client device of a user. In response to receiving the request, the system can generate a unique identifier for the request to facilitate a rendezvous between the user and a service provider, and transmit the unique identifier to the client device of the user. Based on the user and the service provider making the rendezvous, the system receives data corresponding to the unique identifier from a provider application executing on a client device of the service provider. Based on receiving the data corresponding to the unique identifier from the client device of the service provider, the system updates a status for the user to indicate that the service has been provided by the service provider for the user.

Abstract: A computing system can receive a request for a transport service from a client device of a rider and determine a unique identifier for the transport service. The system may then transmit the unique identifier to the client device of the rider and receive data corresponding to the unique identifier from a driver application executing on a client device of a driver. Based on receiving the data corresponding to the unique identifier from the client device of the driver the system can transmit match data to the client device of the driver to cause the driver application to execute an on-trip sub-state for providing the transport service for the rider.

Abstract: A computing system can receive a request for a transport service from a client device of a rider and determine a unique identifier for the transport service. The system may then transmit the unique identifier to the client device of the rider and receive data corresponding to the unique identifier from a driver application executing on a client device of a driver. Based on receiving the data corresponding to the unique identifier from the client device of the driver the system can transmit match data to the client device of the driver to cause the driver application to execute an on-trip sub-state for providing the transport service for the rider.

Abstract: A network system analyzes data samples using embeddings based on, for example, symbolic representations of the data samples or representations in latent dimension space. The network system coordinates providers who provide geographical location-based services to users. The network system may receive data samples from the client device of a provider. For instance, a sensor of the client device captures the data samples during a transportation service along a particular route. To verify that the data samples accurately indicate the location or movement of the provider, the network system can generate a test embedding representing the data samples and compare the test embedding with a reference embedding. The reference embedding is generated based on data samples captured for other similar services, e.g., corresponding to providers who also provided transportation services along the same particular route.

Abstract: A computing system can receive a pick-up request for a transport service from a requesting user within a given region. Based at least in part on the requesting user being within the given region, the computing system can transmit match code data corresponding to a match code to the computing device of the requesting user. The computing system may then receive input data indicating the match code from a computing device of an available driver, signifying that the available driver is to provide the transport service for the requesting user, and update a status for the requesting user to indicate that the transport service is being provided by the available driver for the requesting user.

Abstract: A network service can detect an ultrasonic signal by an ultrasonic receptive component of a first device. The ultrasonic signal can be based on an ultrasonic output signal transmitted from an audio output component. In response to the detected ultrasonic signal, the network service can perform a network service operation.

Abstract: A network system analyzes data samples using embeddings based on, for example, symbolic representations of the data samples or representations in latent dimension space. The network system coordinates providers who provide geographical location-based services to users. The network system may receive data samples from the client device of a provider. For instance, a sensor of the client device captures the data samples during a transportation service along a particular route. To verify that the data samples accurately indicate the location or movement of the provider, the network system can generate a test embedding representing the data samples and compare the test embedding with a reference embedding. The reference embedding is generated based on data samples captured for other similar services, e.g., corresponding to providers who also provided transportation services along the same particular route.

Abstract: A computing system can receive a pick-up request for a transport service from a requesting user within a given region. Based at least in part on the requesting user being within the given region, the computing system can transmit match code data corresponding to a match code to the computing device of the requesting user. The computing system may then receive input data indicating the match code from a computing device of an available driver, signifying that the available driver is to provide the transport service for the requesting user, and update a status for the requesting user to indicate that the transport service is being provided by the available driver for the requesting user.

Abstract: A network service can detect an ultrasonic signal by an ultrasonic receptive component of a first device. The ultrasonic signal can be based on an ultrasonic output signal transmitted from an audio output component. In response to the detected ultrasonic signal, the network service can perform a network service operation.

Abstract: A network system analyzes data samples using embeddings based on, for example, symbolic representations of the data samples or representations in latent dimension space. The network system coordinates providers who provide geographical location-based services to users. The network system may receive data samples from the client device of a provider. For instance, a sensor of the client device captures the data samples during a transportation service along a particular route. To verify that the data samples accurately indicate the location or movement of the provider, the network system can generate a test embedding representing the data samples and compare the test embedding with a reference embedding. The reference embedding is generated based on data samples captured for other similar services, e.g., corresponding to providers who also provided transportation services along the same particular route.

Abstract: Example methods and systems disclosed herein train an accurate machine-learned model that detects fraud within an electronic transportation system. A first model is trained on a first (comparatively small) set of trip data items representing trips taken, or requested, in the electronic transportation system. The first set of trip data items have been manually labeled by human analysts to determine whether the trips were or were not fraudulent. The first model is used to generate weak labels for a second (comparatively larger) set of trip data items that lack manual labels. The weak labels are used along with the second set of trip data items to train a second model that is more accurate than the first model for detecting fraud.

Abstract: A transport facilitation can identify a mass egress area within a given region and receive a pick-up request from a rider device within the mass egress area. In response to receiving the pick-up request, the transport facilitation system transmit a match code to the rider device. The system may then receive an indication of the match code from a driver device, the indication signifying a pick-up event between a requesting user of the rider device and an available driver of the driver device within the mass egress area, and record a state for both the rider device and the driver device indicating an initiation of a ride to a destination of the requesting user.

Abstract: A computing system can receive a first transport request from a computing device of a respective user while a rider application is operating in the default mode, and transmit a confirmation indicating information about a paired driver that is assigned to the first transport request to the computing device of the respective user. The computing system may further receive a second transport request from the computing device of the respective user while the rider application is operating in the secondary mode, and transmit data comprising a unique match code to the computing device of the respective user, causing the rider application to generate and output digital signature.