公开(公告)号：US10042961B2

公开(公告)日：2018-08-07

申请号：US14811397

申请日：2015-07-28

申请人： Microsoft Technology Licensing, LLC

发明人： Yelong Shen ,  Xinying Song ,  Jianfeng Gao ,  Chenlei Guo ,  Byungki Byun ,  Ye-Yi Wang ,  Brian D. Remick ,  Edward Thiele ,  Mohammed Aatif Ali ,  Marcus Gois ,  Yang Zou ,  Mariana Stepp ,  Divya Jetley ,  Stephen Friesen

IPC分类号： G06F17/30 ,  G06Q10/06 ,  H04L12/58

摘要： Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation. In an exemplary embodiment, a plurality of conversation boxes associated with communications between a user and target recipients, or between other users and recipients, are collected and stored as user history. During a training phase, the user history is used to train encoder and decoder blocks in a de-noising auto-encoder model. During a prediction phase, the trained encoder and decoder are used to predict one or more recipients for a current conversation box composed by the user, based on contextual and other signals extracted from the current conversation box. The predicted recipients are ranked using a scoring function, and the top-ranked individuals or entities may be recommended to the user.

公开(公告)号：US20160321283A1

公开(公告)日：2016-11-03

申请号：US14811397

申请日：2015-07-28

申请人： Microsoft Technology Licensing, LLC

发明人： Yelong Shen ,  Xinying Song ,  Jianfeng Gao ,  Chenlei Guo ,  Byungki Byun ,  Ye-Yi Wang ,  Brian D. Remick ,  Edward Thiele ,  Mohammed Aatif Ali ,  Marcus Gois ,  Yang Zou ,  Mariana Stepp ,  Divya Jetley ,  Stephen Friesen

IPC分类号： G06F17/30 ,  H04L12/58

CPC分类号： G06F17/3097 ,  G06F17/3053 ,  G06F17/30598 ,  G06F17/30699 ,  G06Q10/06311 ,  G06Q10/06313 ,  G06Q10/06315 ,  H04L51/04

摘要： Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation. In an exemplary embodiment, a plurality of conversation boxes associated with communications between a user and target recipients, or between other users and recipients, are collected and stored as user history. During a training phase, the user history is used to train encoder and decoder blocks in a de-noising auto-encoder model. During a prediction phase, the trained encoder and decoder are used to predict one or more recipients for a current conversation box composed by the user, based on contextual and other signals extracted from the current conversation box. The predicted recipients are ranked using a scoring function, and the top-ranked individuals or entities may be recommended to the user.

摘要翻译： 提供用于预测和推荐相关人（或其他实体）包括在对话中的人推荐系统的技术。 在示例性实施例中，与用户和目标接收者之间或其他用户和接收者之间的通信相关联的多个会话框被收集并存储为用户历史。 在训练阶段，用户历史用于在去噪自动编码器模型中训练编码器和解码器块。 在预测阶段期间，经训练的编码器和解码器用于基于从当前会话框提取的上下文和其他信号来预测用户组成的当前会话框的一个或多个接收者。 使用评分功能对预测的收件者进行排名，并且可以向用户推荐排名最高的个人或实体。