公开(公告)号：US20140324602A1

公开(公告)日：2014-10-30

申请号：US14082966

申请日：2013-11-18

Applicant: Google Inc.

Inventor： Patrick Hummel ,  Uri Nadav

IPC: G06Q30/02

CPC classification number: G06Q30/0275

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing utilization of distribution parameters are disclosed. In one aspect, a method includes a restrictive distribution parameter that is different from any distribution parameters in a first set of distribution parameters. An acceptable peak bid for a second set of distribution parameters that includes the restrictive distribution parameter is determined based on a first bid for the first set of distribution parameters. A determination is made that a second bid received from the content item provider does not exceed the acceptable peak bid, and the second bid is associated with the second set of distribution parameters based on the determination.

Abstract translation: 公开了包括在计算机存储介质上编码的用于管理分布参数利用的计算机程序的方法，系统和装置。 一方面，一种方法包括与第一组分布参数中的任何分布参数不同的限制性分布参数。 基于用于第一组分布参数的第一投标来确定包括限制性分布参数的第二组分布参数的可接受的峰值出价。 确定从内容项目提供者接收的第二投标不超过可接受的峰值出价，并且基于该确定，第二投标与第二组分布参数相关联。

公开(公告)号：US20180046940A1

公开(公告)日：2018-02-15

申请号：US15352318

申请日：2016-11-15

Applicant: Google Inc.

Inventor： Patrick Hummel ,  Uri Nadav

IPC: G06N99/00

CPC classification number: G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing machine learning systems. In one aspect a method includes determining an average error of a machine learning system (“MLS”). An evaluation function that provides a result that would have been achieved using a specified value of a given parameter is defined. An expected outcome function that provides expected results for prior events based on the error of the MLS is defined. For each of multiple prior events, a target value of the given parameter is determined, e.g., using the expected outcome function. A model is generated using the MLS based on features of the prior events and the determined target values of the given parameter for the prior events. A value is assigned to the given parameter for a new event based on application of the model to features of the new event.