Amazon Technologies, Inc.

Yahoo! Inc.

Jiefeng Shen

Benoit F Dumoulin

Omer Emre Velipasaoglu

Su-Lin Wu

Richard Kasperski

Eric Crestan

Qaseem Ahmed Shaikh

Mikael O Weigelt

Chi-Hoon Lee

Various embodiments of a system and method for generating predictions for unit allocation in a materials processing network are described. Various embodiments may include a capacity planner for defining a model including, for each of a plurality of discrete periods of time, a corresponding representation of a materials processing network including materials handling facilities, constraints associated with ones of the materials handling facilities, and logic for determining efficient flows of materials within the materials processing network during that discrete period of time. In order to determine efficient flows of materials within the materials processing network for a particular period of time, the capacity planner may determine the discrete periods of time corresponding to representations of the model required to determine the one or more efficient flows, and evaluate the logic of the those representations without evaluating logic of representations of the model corresponding to other discrete periods of time.

System and method for generating predictions for unit allocation in a materials processing network

One embodiment selects from a set of query-suggestion pairs a first query and a subset of query-suggestion pairs that each has the first query as its query; computes a Log Likelihood Ratio (LLR) value for each query-suggestion pair from the subset of query-suggestion pairs; ranks the subset of query-suggestion pairs according to their respective LLR values; removes from the subset of query-suggestion pairs all query-suggestion pairs whose LLR values are below a predetermined LLR threshold; computes a Pointwise Mutual Information (PMI) value for each remaining query suggestion pair from the subset of query-suggestion pairs; removes from the subset of query-suggestion pairs all query-suggestion pairs whose PMI values are below a predetermine PMI threshold; and constructs a ranked set of suggestions for the first query, wherein the ranked set of suggestions comprises one or more suggestions of the remaining query-suggestion pairs from the subset of query-suggestion pairs.

Search assist powered by session analysis

Growing community of inventors

Sammamish, WA, United States of America

Jiefeng Shen