Abstract: A technique generates estimated time-of-arrival (ETA) information to assist in navigating from one physical location to another. The technique uses a computer-implemented route-finding engine to identify a route between a specified starting location and an ending location of a trip. The route includes a sequence of segments. The technique then uses a machine-trained model to map information regarding the segments to ETA information. The ETA information provides an estimate of a time-of-arrival for the trip as a whole. The ETA information also provides an estimate of parameters that describe the level of confidence of the time-of-arrival estimate for the trip. A training system produces the machine-trained model using a loss function, part of which models the time-of-arrival for the trip as a mixture of distributions.

Abstract: A technique automatically identifies and resolves prohibited maneuvers in candidate routes generated by a routing system. Examples of prohibited maneuvers include traveling over a non-navigable path, traveling in an incorrect direction over a roadway, and an improper turn. The technique determines whether the candidate routes contain prohibited maneuvers by comparing the candidate routes with plural types of route-related validation data in plural respective validation processes. For example, a first validation process compares the candidate routes with a collection of GPS traces. A second validation process compares the candidate routes with map reference data. The technique further includes provisions for correcting the causes of identified prohibited maneuvers. Overall, the technique reduces the amount of manual effort involved in verifying the accuracy of routes produced by the routing system, and improves the accuracy, reliability, and safety of the routing system.

Abstract: Various embodiments discussed herein relate to route optimization and query understanding for route and/or direction queries with complex user preferences. Each route candidate, for example, is treated as a richly annotated document. The routing engine, in addition to performing route optimization, acts as a retriever and ranker of route documents according to user intent. Various embodiments rank routes not just based on a simple cost model, but based on many more or alternative factors according to user preferences, user intent, and/or contextual data.

Abstract: A technique automatically identifies and resolves prohibited maneuvers in candidate routes generated by a routing system. Examples of prohibited maneuvers include traveling over a non-navigable path, traveling in an incorrect direction over a roadway, and an improper turn. The technique determines whether the candidate routes contain prohibited maneuvers by comparing the candidate routes with plural types of route-related validation data in plural respective validation processes. For example, a first validation process compares the candidate routes with a collection of GPS traces. A second validation process compares the candidate routes with map reference data. The technique further includes provisions for correcting the causes of identified prohibited maneuvers. Overall, the technique reduces the amount of manual effort involved in verifying the accuracy of routes produced by the routing system, and improves the accuracy, reliability, and safety of the routing system.

Abstract: A technique generates estimated time-of-arrival (ETA) information to assist in navigating from one physical location to another. The technique uses a computer-implemented route-finding engine to identify a route between a specified starting location and an ending location of a trip. The route includes a sequence of segments. The technique then uses a machine-trained model to map information regarding the segments to ETA information. The ETA information provides an estimate of a time-of-arrival for the trip as a whole. The ETA information also provides an estimate of parameters that describe the level of confidence of the time-of-arrival estimate for the trip. A training system produces the machine-trained model using a loss function, part of which models the time-of-arrival for the trip as a mixture of distributions.

Abstract: Described herein are technologies related to generating a predicted routine of a user of a mobile computing device. Location entries generated by the mobile computing device are processed to generate visit entries, wherein the visit entries are representative of visits made by the user to places over several days. An input sequence of states is constructed based upon the visit entries, wherein each state has a place identifier assigned thereto, and further wherein each state corresponds to a time interval of predefined length. A predicted routine of the user is generated based upon the input sequence of states.

Abstract: Technology is described herein for ranking candidate result items in at least two stages. In a first stage, the technology uses a first attention-based neural network to determine an extent of attention that each token of an input query should pay to the tokens of each candidate result item. In a second stage, the technology uses a ranking subsystem to perform listwise inference on output results provided by the first stage, to generate a plurality of ranking scores that establish an order of relevance of the candidate results items. The ranking subsystem may use a second attention-based neural network to perform the listwise inference. According to some implementations, the technology is configured to process queries and candidate result items having different kinds and combinations of features. For instance, one kind of input query may include text-based features, structure-based features, and geographic-based features.

Abstract: Technology is described herein for ranking candidate result items in at least two stages. In a first stage, the technology uses a first attention-based neural network to determine an extent of attention that each token of an input query should pay to the tokens of each candidate result item. In a second stage, the technology uses a ranking subsystem to perform listwise inference on output results provided by the first stage, to generate a plurality of ranking scores that establish an order of relevance of the candidate results items. The ranking subsystem may use a second attention-based neural network to perform the listwise inference. According to some implementations, the technology is configured to process queries and candidate result items having different kinds and combinations of features. For instance, one kind of input query may include text-based features, structure-based features, and geographic-based features.

Abstract: Described herein are technologies related to generating a predicted routine of a user of a mobile computing device. Location entries generated by the mobile computing device are processed to generate visit entries, wherein the visit entries are representative of visits made by the user to places over several days. An input sequence of states is constructed based upon the visit entries, wherein each state has a place identifier assigned thereto, and further wherein each state corresponds to a time interval of predefined length. A predicted routine of the user is generated based upon the input sequence of states.

Abstract: Described herein are technologies related to generating a predicted routine of a user of a mobile computing device. Location entries generated by the mobile computing device are processed to generate visit entries, wherein the visit entries are representative of visits made by the user to places over several days. An input sequence of states is constructed based upon the visit entries, wherein each state has a place identifier assigned thereto, and further wherein each state corresponds to a time interval of predefined length. A predicted routine of the user is generated based upon the input sequence of states.

Abstract: The present disclosure is directed to systems, methods and devices for replacing a static map image with an interactive map that approximates the geographic area depicted by the static map image. A static image may be inspected and a determination may be made as to whether the static image meets a map identification threshold value. At least one signal associated with the static image may be evaluated and based on that evaluation at least one geo-entity of intent may be identified. The static image may be replaced with a static image corresponding to at least one of the identified geo-entities of intent.

Abstract: The present disclosure is directed to systems, methods and devices for replacing a static map image with an interactive map that approximates the geographic area depicted by the static map image. A static image may be inspected and a determination may be made as to whether the static image meets a map identification threshold value. At least one signal associated with the static image may be evaluated and based on that evaluation at least one geo-entity of intent may be identified. The static image may be replaced with a static image corresponding to at least one of the identified geo-entities of intent.