公开(公告)号：US20230211692A1

公开(公告)日：2023-07-06

申请号：US17257298

申请日：2020-09-03

Applicant: GOOGLE LLC

Inventor： Alex Donaldson ,  David X. Wang ,  Kostas Kollias ,  Xin Wei Chow ,  Navin Gunatillaka ,  Jesse Head ,  Michael Graham Woodward ,  Ingrid Trollope ,  Anddrew Foster ,  Ivan Kuznetsov ,  Sreenivas Gollapudi

IPC: B60L53/65 ,  G01C21/34

CPC classification number: B60L53/65 ,  G01C21/3469 ,  B60L2240/62 ,  B60L2240/70

Abstract: To navigate an electric vehicle from a starting location to a destination, a system identifies multiple charging stations between the starting location and the destination and determining a navigation route that requires a least amount of time for the electric vehicle to travel from the starting location to the destination via one or more of the charging stations, including determining a non-linear relationship between an amount of time and an amount of charge the EV receives during the amount of time.

公开(公告)号：US20230281430A1

公开(公告)日：2023-09-07

申请号：US18118061

申请日：2023-03-06

Applicant: Google LLC

Inventor： Ali Kemal Sinop ,  Sreenivas Gollapudi ,  Petar Velickovic ,  Sofia Ira Ktena ,  Ameya Avinash Velingker

IPC: G06N3/047 ,  G06N3/082

CPC classification number: G06N3/047 ,  G06N3/082

Abstract: Methods and systems for conditioning graph neural networks on affinity features. One of the methods includes obtaining graph data representing an input graph that comprises a set of nodes and a set of edges that each connect a respective pair of nodes, the graph data comprising respective node features for each of the nodes, edge features for each of the edges, and a respective weight for each of the edges; generating one or more affinity features, each affinity feature representing a property of one or more random walks through the graph guided by the respective weights for the edges; and processing the graph data using a graph neural network that is conditioned on the one or more affinity features to generate a task prediction for a machine learning task for the input graph.

公开(公告)号：US20230388224A1

公开(公告)日：2023-11-30

申请号：US17886764

申请日：2022-08-12

Applicant: Google LLC

Inventor： Ali Kemal Sinop ,  Sreenivas Gollapudi ,  Konstantinos Kollias

IPC: H04L45/00 ,  H04L45/02

CPC classification number: H04L45/38 ,  H04L45/22 ,  H04L45/02

Abstract: Example aspects of the present disclosure provide for an example computer-implemented method for generating alternative network paths, the example method including obtaining a network graph; determining flows respectively for edges of the network graph by: resolving a linear system of weights associated with the edges, the linear system resolved over a reduced network graph, and propagating a solution of the linear system into a respective partition of a plurality of partitions of the network graph to determine at least one of the flows within the respective partition; and determining a plurality of alternative paths across the network graph.