公开(公告)号：US20170039483A1

公开(公告)日：2017-02-09

申请号：US14820751

申请日：2015-08-07

Applicant: Google Inc.

Inventor： Heng-Tze Cheng ,  Jeremiah Harmsen ,  Alexandre Tachard Passos ,  David Edgar Lluncor ,  Shahar Jamshy ,  Tal Shaked ,  Tushar Deepak Chandra

IPC: G06N99/00 ,  G06N5/04 ,  G06F17/30

CPC classification number: G06N99/005 ,  G06F17/30477 ,  G06F17/30864 ,  G06N5/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a factorization model to learning features of model inputs of a trained model such that the factorization model is predictive of outcome for which the machine learned model is trained.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于训练因子分解模型以学习训练模型的模型输入的特征，使得因式分解模型预测机器学习模型被训练的结果。

公开(公告)号：US09160631B1

公开(公告)日：2015-10-13

申请号：US14335462

申请日：2014-07-18

Applicant: GOOGLE INC.

Inventor： David Edgar Lluncor ,  Joel Darnauer ,  Richard Charles Chiburis

IPC: G06F17/30 ,  H04L12/24 ,  G06F3/0484 ,  G06F17/22

CPC classification number: H04L41/22 ,  G06F8/656 ,  G06F11/34 ,  G06F17/2241 ,  G06F17/2247

Abstract: A system and method for summarizing changes between a first set of metrics and a second set of metrics are disclosed. An example method includes obtaining and categorizing a first set of metrics for an application. A second set of metrics for the application may be obtained and categorized. A statistical process may be used to determine metrics that should be displayed. Metrics may be organized into a metric tree data structure that is hierarchical including parent metrics and child submetrics. Metrics that have been determined to be displayed may be displayed in the tree data structure so that the metrics are selectable with a single user input. In response to receiving a selection of a metric via the single user input, traffic categories and submetrics may be displayed that are children of the metric within the tree data structure may be displayed.

Abstract translation: 公开了一种用于总结第一组度量和第二组度量之间的变化的系统和方法。 示例性方法包括获得和分类用于应用的第一组度量。 可以获得并分类应用程序的第二组度量。 可以使用统计过程来确定应显示的度量。 度量可以被组织成分级的度量树数据结构，包括父度量和子子度量。 已经被确定要显示的度量可以显示在树状数据结构中，使得度量可以用单个用户输入来选择。 响应于通过单个用户输入接收到度量的选择，可以显示作为树状数据结构内的度量的子节点的业务类别和子度量。