Abstract: The disclosed examples are directed to systems and methods for performing co-presence estimation. The systems and methods detect, by a first device associated with a first user, a beacon signal generated by a second device associated with a second user and generate co-presence information representing proximity between the first device and the second device based on detecting the beacon signal. The systems and methods select a graphical indicator from a plurality of graphical indicators of co-presence based on the generated co-presence information and present a proximity graphical user interface (GUI) comprising a map portion and a co-presence portion using the selected graphical indicator.

Abstract: Route guidance using less client device power and bandwidth is enabled by automatically selecting portions of a map to display with higher and lower levels of detail. An origin location and destination location are displayed at a higher level of detail, while portions between origin and destination are displayed at a lower level of detail. A user of a transportation service may request a ride, specifying her pickup location and destination locations using a map rendered at a higher level of detail. While waiting for pickup, and while in route to the destination location, the user may consult a map that is rendered at a lower level of detail. When multiple users participate as riders in a transportation service, sharing a common driver but each having different pickup and drop off locations, portions of a map may be rendered differently for each user.

Abstract: A computer-implemented method includes accessing data descriptive of a plurality of freight lanes, each freight lane being associated with a pickup region and a dropoff region for one or more loads, wherein each of the plurality of freight lanes includes one or more lane attributes; determining that two or more freight lanes of the plurality of freight lanes satisfy at least one clustering criteria indicative of a similarity between the two or more freight lanes based at least in part on the one or more freight lane attributes; in response to determining that the two or more freight lanes meet the at least one clustering criteria, clustering the two or more freight lanes to generate a clustered freight lane including the two or more freight lanes; receiving a request from a carrier computing device to associate a carrier with the clustered freight lane; and assigning at least one load of the one or more loads associated with the two or more freight lanes including the clustered freight lane to the carrier bas

Abstract: Various examples are directed to systems and methods for providing transportation services. A service assignment system may receive a transportation service request from a user. The transportation service request may describe a transportation service having a start location and an end location. The service assignment system may select a first autonomous vehicle (AV) of a first AV type and determine a first predicted route for the first AV using vehicle capability data describing the first AV type and first difference data describing a difference between a previous predicted route for a previous AV of the first AV type and a previous planned route received from the previous AV of the first AV type. The service assignment system may receive, from the first AV, a first planned route for executing the transportation service and instruct the first AV to begin executing the transportation service.

Abstract: Systems and methods for advertisement-based vehicle matching a routing. For example, a computer-implemented method includes obtaining data associated with a vehicle that is online with a service entity associated with providing vehicle services. The method includes obtaining data associated with a vehicle that is online with a service entity associated with providing one or more vehicle services. The method includes determining that the vehicle is not currently associated with a vehicle service instance for performing the vehicle services and determining a selected advertisement content item for the vehicle. The method includes determining a selected route for the vehicle based on the selected advertisement content item. The method includes communicating data that initiates display of the selected advertisement content item via a display device positioned on an exterior of the vehicle and data indicative of route information to a computing device associated with the vehicle.

Abstract: Systems and methods for anonymizing targeted data entries. A method includes accessing a dataset comprising targeted data and parsing the dataset into a plurality of data entities. The method includes detecting a plurality of targeted data entries among the plurality of parsed data entities and determining a confidence score associated with each of the plurality of targeted data entries. The method includes determining at least two overlapping targeted data entries and determining at least one contained targeted data entry. The method further includes determining a subset of targeted data entries each having a confidence score below a threshold confidence score and removing at least one targeted data entry. The method includes converting remaining targeted data entries of the plurality of targeted data entries to anonymized data entries.

Abstract: Systems and methods for evaluating and deploying fleets of autonomous in operational domains are described. A computing system may obtain data indicative of one or more capabilities of at least one autonomous vehicle, data indicative of vehicle service dynamics in an operational domain over a period of time, and determining a plurality of resource performance parameters respectively for a plurality of autonomous vehicle fleets associated with potential deployment in the operational domain. Each autonomous vehicle fleet can be associated with a different number of autonomous vehicles The resource performance parameter for each autonomous vehicle fleet can be based at least in part on the one or more capabilities of the at least one autonomous vehicle and the vehicle service dynamics in the operational domain. The computing system can initiate an action associated with the operational domain based at least in part on the plurality of resource performance parameters.

Abstract: Systems and methods for improving inbound/outbound prioritization and processing for large blob workloads. The system can receive latency profiles and determine parameters that control movement of data across data tiers. The method includes receiving a plurality of commands to interact with data. The method includes detecting conditions that fail to satisfy at least one latency profile. The method includes adjusting parameters based on detecting the conditions. Adjusting the parameters adjusts a percentage of data being classified in a first tier to being reclassified in a second tier to satisfy the latency profiles. The method includes processing the plurality of commands based on the adjusted percentage of data.

Abstract: A computer system receives a freight request from a shipper, where the freight request specifies a destination for a load of the shipper. The computer system implements a selection process to select a freight operator to haul a corresponding trailer of the trailer module from a location of the shipper to a destination. The trailer module may be monitored using information transmitted from the trailer, to determine when the trailer is picked up and/or delivered at the destination.

Abstract: An online system receives a trip request including a location of the user requesting the trip. The online system identifies buildings or geographies based on the received location and determines location boundaries associated with the identified buildings or geographies. The online system identifies a set of hotspots representing locations that are frequently used for pickup or drop off. The online system additionally identifies a set of points of interest. The points of interest are, for example, businesses, landmarks, building names, or other visible information related to the location. The online system scores the set of points of interest based on a relative value of displaying the point of interest for orientation or navigation purposes. The online system modifies a user interface to display a map of the area including the identified location boundaries, hotspots, and one or more points of interest based on the scoring.

Abstract: Systems and methods of generating active notifications for users of a networked computer system using transportation service prediction are disclosed herein. In some example embodiments, a computer system uses a prediction model to generate a transportation service prediction for a user based on an identification of the user, location data for the user, prediction time data, and historical user data for instances of the user using the transportation, and then causes a notification to be displayed on a computing device of the user based on the transportation service prediction, with the notification indicating a recommended use of the transportation service in association with the place for the time of day and the day of the week, and the notification comprising a selectable user interface element configured to enable the user to submit an electronic request for the recommended use of the transportation service.

Abstract: A network system can receive, from a user device of a requesting user, a query related to a first service. If the network system determines that a first service provider is in progress of providing a second service for the requesting user, the network system can identify, based on a service location of the second service, a plurality of entities that provide items available for selection in association with the first service. The network system can further determine whether to select the first service provider to fulfill the request for the first service based on an estimated first service duration associated with the first service and an estimated duration remaining for the second service. The first service duration can be estimated based on respective timing information associated one or more items selected by the requesting user. The network system can update a route for the first service provider.

Abstract: Systems and methods for dynamic mapping and routing using machine learning. The system can access requested items, a map, and process data signals to generate route segments that indicate a path to the requested items. The method includes accessing data associated with a delivery request that includes requested items. The method includes accessing map data associated with the initial location of the items. The method includes processing data signals from computing devices to confirm an initial location of an item, determine a new location of an item, or determine an availability of an item. The method includes iteratively generating a plurality of route segments for a user to follow that indicates a path to the requested items. The method includes outputting a command instruction to generate a user interface that iteratively displays each route segment based on the user selecting or disregarding the respective items.

Abstract: Systems and methods are disclosed herein for monitoring a location of a client device associated with a transportation service and generating augmented reality images for display on the client device. The systems and methods use sensor data from the client device and a device localization process to monitor the location of the client device by comparing renderings of images captured by the client device to renderings of the vicinity of the pickup location. The systems and methods determine navigation instructions from the user's current location to the pickup location and select one or more augmented reality elements associated with the navigation instructions and/or landmarks along the route to the pickup location. The systems and methods instruct the client device to overlay the selected augmented reality elements on a video feed of the client device.

Abstract: A system and method for dynamically adjusting attributes for a network service is described. A computing system can determine a change that is to be implemented to an attribute of the network service. For each of a plurality of computing devices, the computing system can receive information associated with that computing device from a designated application operating on that computing device. The designated application is associated with the network service. The computing system automatically implements the change to at least one but not all of the plurality of computing devices based on the information received from each of the plurality of computing devices.

Abstract: Systems and methods for determining out-of-stock predictions for merchant items and performing intervention actions based on the out-of-stock predictions using machine-learned models. The method includes obtaining feature data including at least (i) aggregations of historical found rate data, (ii) item level metadata, and (iii) merchant signal data into an out-of-stock model. The method includes determining a number of output scores for a number of items. The output scores can be indicative of a likelihood of an item being out-of-stock. The method includes determining a first output score for a first item of the plurality of items satisfies an intervention criterion. The method includes responsive to determining the first output score satisfies the intervention criterion, performing an intervention action.

Abstract: A method includes receiving one or more search terms at a mobile computing device while the mobile computing device is located at a particular location. A search query that includes the one or more search terms and a location history of the mobile computing device is transmitted to a server. The method also includes receiving one or more search results in response to the search query, where the one or more search results include content identified based on a predicted destination of the mobile computing device. An interface identifying the one or more search results is displayed at the mobile computing device.

Abstract: Systems and methods of using sensor data for coordinate prediction are disclosed herein. In some example embodiments, for a place, a computer system accesses corresponding service data comprising pick-up data and drop-off data for requests, and accesses corresponding sensor data indicating at least one path of mobile devices of the requesters of the requests, with the at least one path comprising at least one of a pick-up path ending at the pick-up location indicated by the pick-up data and a drop-off path beginning at the drop-off location indicated by the drop-off data. In some example embodiments, the computer system generates at least one predicted geographic location using the paths indicated by the sensor data, and stores the at least one predicted geographic location in a database in association with an identification of the place.

Abstract: A system can receive location data from a computing device of a requesting user, where the location data indicates a current position of the requesting user. The system can determine a rendezvous location for the requesting user prior to the requesting user transmitting a service request to the network computer system. The system may then transmit data corresponding to the rendezvous location to the computing device of the requesting user. The system may further periodically receive an update request from the computing device of the user, and for each update request, (i) determine a second plurality of transport providers with the predetermined distance or time from the current position of the user, and (ii) based on respective locations of these transport providers, transmit updated map data to the computing device to indicate an updated rendezvous location on the map interface.

Abstract: A computing system can detect, based on data received via the network communication interface, a launch of a service application on a computing device of a user to initiate an application session. During the application session, the system can obtain contextual data corresponding to user interactions with the service application by the user. Based on the contextual data, the system can perform at least one of (i) acquire first additional user data corresponding to the user from one or more local data sources, or (ii) derive second additional user data associated with the contextual data to avoid a network call and reduce network latency. The system may then classify the user in a specified group for providing targeted content.