公开(公告)号：WO2017053208A1

公开(公告)日：2017-03-30

申请号：PCT/US2016/052362

申请日：2016-09-17

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： HAKKANI-TUR, Dilek Zeynep ,  HE, Xiaodong ,  CHEN, Yun-Nung

IPC: G10L15/22 ,  G06F17/27 ,  G10L15/26

CPC classification number: G10L15/16 ,  G06F17/2785 ,  G06F17/279 ,  G06N99/005 ,  G06Q10/10 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26

Abstract: A computer-implemented technique is described herein for detecting actionable items in speech. In one manner of operation, the technique entails: receiving utterance information that expresses at least one utterance made by one participant of a conversation to at least one other participant of the conversation; converting the utterance information into recognized speech information; using a machine-trained model to recognize at least one actionable item associated with the recognized speech information; and performing at least one computer-implemented action associated the actionable item(s).The machine-trained model may correspond to a deep-structured convolutional neural network. In some implementations, the technique produces the machine-trained model using a source environment corpus that is not optimally suited for a target environment in which the model is intended to be applied. The technique further provides various adaptation techniques for adapting a source-environment model so that it better suits the target environment.

Abstract translation: 本文描述了一种用于检测语音中的可操作项目的计算机实现的技术。 在一种操作方式中，技术包括：接收表达至少一个对话参与者的至少一个话语的话语信息给对话的至少一个其他参与者; 将话语信息转换成识别的语音信息; 使用机器训练的模型来识别与所识别的语音信息相关联的至少一个可操作项目; 并且执行与可操作项目相关联的至少一个计算机实现的动作。机器训练的模型可以对应于深层结构的卷积神经网络。 在一些实现中，该技术使用源环境语料库产生机器训练的模型，该源环境语料库不是最适合于其中应用模型的目标环境。 该技术进一步提供了各种适应技术，以适应源 - 环境模型，使其更适合于目标环境。

公开(公告)号：WO2017019318A1

公开(公告)日：2017-02-02

申请号：PCT/US2016/042374

申请日：2016-07-15

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： DENG, Li ,  GAO, Jianfeng ,  HE, Xiaodong ,  SINGH, Prabhdeep

IPC: G06Q10/06

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06Q10/067

Abstract: A deep learning network is trained to automatically analyze enterprise data. Raw data from one or more global data sources is received, and a specific training dataset that includes data exemplary of the enterprise data is also received. The raw data from the global data sources is used to pre-train the deep learning network to predict the results of a specific enterprise outcome scenario. The specific training dataset is then used to further train the deep learning network to predict the results of a specific enterprise outcome scenario. Alternately, the raw data from the global data sources may be automatically mined to identify semantic relationships there-within, and the identified semantic relationships may be used to pre-train the deep learning network to predict the results of a specific enterprise outcome scenario.

Abstract translation: 培训深入学习网络，自动分析企业数据。 接收来自一个或多个全局数据源的原始数据，并且还接收包括企业数据示例的数据的特定训练数据集。 来自全球数据源的原始数据用于预培训深度学习网络，以预测特定企业成果情景的结果。 然后将具体的培训数据集用于进一步训练深入学习网络，以预测特定企业成果情景的结果。 或者，来自全球数据源的原始数据可以被自动挖掘以识别其中的语义关系，并且所识别的语义关系可以用于预培训深度学习网络以预测特定企业成果情景的结果。

公开(公告)号：WO2017003886A1

公开(公告)日：2017-01-05

申请号：PCT/US2016/039463

申请日：2016-06-27

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： HE, Xiaodong ,  CHEN, Jianshu ,  CLEMENT, Brendan W.L. ,  DENG, Li ,  GAO, Jianfeng ,  JIN, Bochen ,  SINGH, Prabhdeep ,  SOLANKI, Sandeep P. ,  WANG, Luming ,  XIAN, Hanjun ,  ZHANG, Yilei ,  ZHAO, Mingyang ,  ZHENG, Zijian

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06N3/049 ,  G06N99/005

Abstract: A processing unit can acquire datasets from respective data sources, each having a respective unique data domain. The processing unit can determine values of a plurality of features based on the plurality of datasets. The processing unit can modify input-specific parameters or history parameters of a computational model based on the values of the features. In some examples, the processing unit can determine an estimated value of a target feature based at least in part on the modified computational model and values of one or more reference features. In some examples, the computational model can include neural networks for several input sets. An output layer of at least one of the neural networks can be connected to the respective hidden layer(s) of one or more other(s) of the neural networks. In some examples, the neural networks can be operated to provide transformed feature value(s) for respective times.

Abstract translation: 处理单元可以从相应的数据源获取数据集，每个数据源具有相应的唯一数据域。 处理单元可以基于多个数据集来确定多个特征的值。 处理单元可以基于特征的值修改计算模型的输入特定参数或历史参数。 在一些示例中，处理单元可以至少部分地基于修改的计算模型和一个或多个参考特征的值来确定目标特征的估计值。 在一些示例中，计算模型可以包括用于多个输入集合的神经网络。 至少一个神经网络的输出层可以连接到神经网络的一个或多个其他神经网络的相应隐藏层。 在一些示例中，可以操作神经网络以在相应时间提供变换的特征值。

公开(公告)号：WO2015160544A1

公开(公告)日：2015-10-22

申请号：PCT/US2015/024417

申请日：2015-04-06

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： GUO, Chenlei ,  GAO, Jianfeng ,  WANG, Ye-Yi ,  DENG, Li ,  HE, Xiaodong

IPC: G06F17/30

CPC classification number: G06F17/30554 ,  G06F17/3053 ,  G06F17/30867 ,  G06N3/0454

Abstract: A search engine is described herein for providing search results based on a context in which a query has been submitted, as expressed by context information. The search engine operates by ranking a plurality of documents based on a consideration of the query, and based, in part, on a context concept vector and a plurality of document concept vectors, both generated using a deep learning model (such as a deep neural network). The context concept vector is formed by a projection of the context information into a semantic space using the deep learning model. Each document concept vector is formed by a projection of document information, associated with a particular document, into the same semantic space using the deep learning model. The ranking operates by favoring documents that are relevant to the context within the semantic space, and disfavoring documents that are not relevant to the context.

Abstract translation: 本文描述了一种搜索引擎，用于根据上下文信息所表示的提交查询的上下文来提供搜索结果。 搜索引擎通过基于查询的考虑对多个文档进行排序来操作，并且部分地基于上下文概念向量和多个文档概念向量来进行操作，两者都使用深度学习模型（例如深层神经元 网络）。 上下文概念向量是通过使用深度学习模型将上下文信息投影到语义空间中而形成的。 通过使用深度学习模型，将与特定文档相关联的文档信息投影到相同的语义空间中来形成每个文档概念向量。 排名通过有利于与语义空间内的上下文相关的文档，以及不利于与上下文无关的文档。

公开(公告)号：WO2016176229A1

公开(公告)日：2016-11-03

申请号：PCT/US2016/029404

申请日：2016-04-27

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： GUO, Chenlei ,  GAO, Jianfeng ,  SONG, Xinying ,  BYUN, Byungki ,  SHEN, Yelong ,  WANG, Ye-Yi ,  REMICK, Brian D. ,  THIELE, Edward ,  ALI, Mohammed Aatif ,  GOIS, Marcus ,  HE, Xiaodong ,  CHEN, Jianshu ,  JETLEY, Divya ,  FRIESEN, Stephen

IPC: G06Q10/06 ,  G06F17/27

CPC classification number: H04L67/22 ,  G06F17/3053 ,  G06F17/30699 ,  G06N99/005 ,  G06Q10/06311 ,  G06Q10/06313 ,  G06Q10/06315 ,  H04L51/20 ,  H04L67/306

Abstract: Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation based on contextual indicators. In an exemplary embodiment, email recipient recommendations may be suggested based on contextual signals, e.g., project names, body text, existing recipients, current date and time, etc. In an aspect, a plurality of properties including ranked key phrases are associated with profiles corresponding to personal entities. Aggregated profiles are analyzed using first- and second-layer processing techniques. The recommendations may be provided to the user reactively, e.g., in response to a specific query by the user to the people recommendation system, or proactively, e.g., based on the context of what the user is currently working on, in the absence of a specific query by the user.

Abstract translation: 提供人员推荐系统的技术，用于根据情境指标预测和推荐相关人员（或其他实体）包括在对话中。 在示例性实施例中，可以基于上下文信号（例如，项目名称，正文，现有接收者，当前日期和时间等）来建议电子邮件接收者建议。在一方面，包括排序关键短语的多个属性与简档相关联 对应个人实体。 使用第一层和第二层处理技术分析聚集剖面。 可以例如响应于用户对人们推荐系统的特定查询，或主动地，例如，基于用户当前正在工作的上下文，在没有 用户的具体查询。

公开(公告)号：WO2015191652A1

公开(公告)日：2015-12-17

申请号：PCT/US2015/034994

申请日：2015-06-10

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： GAO, Jianfeng ,  DENG, Li ,  GAMON, Michael ,  HE, Xiaodong ,  PANTEL, Patrick

IPC: G06F17/30

CPC classification number: G06N3/04 ,  G06F17/30967 ,  G06N3/0427 ,  G06N3/082

Abstract: An "Interestingness Modeler" uses deep neural networks to learn deep semantic models (DSM) of "interestingness." The DSM, consisting of two branches of deep neural networks or their convolutional versions, identifies and predicts target documents that would interest users reading source documents. The learned model observes, identifies, and detects naturally occurring signals of interestingness in click transitions between source and target documents derived from web browser logs. Interestingness is modeled with deep neural networks that map source-target document pairs to feature vectors in a latent space, trained on document transitions in view of a "context" and optional "focus" of source and target documents. Network parameters are learned to minimize distances between source documents and their corresponding "interesting" targets in that space. The resulting interestingness model has applicable uses, including, but not limited to, contextual entity searches, automatic text highlighting, prefetching documents of likely interest, automated content recommendation, automated advertisement placement, etc.

Abstract translation: “有趣的建模者”使用深层神经网络来学习“趣味性”的深层语义模型（DSM）。 DSM由深度神经网络的两个分支或其卷积版本组成，识别并预测将感兴趣用户阅读源文档的目标文档。 所学习的模型观察，识别和检测从Web浏览器日志导出的源文档和目标文档之间的点击转换中的自然发生的兴趣信号。 有趣的是用深层神经网络建模，将源目标文档对映射到潜在空间中的特征向量，考虑到源文件和目标文档的“上下文”和可选的“焦点”，对文档转换进行了训练。 学习网络参数以最小化源文档与其空间中相应的“有趣”目标之间的距离。 所产生的兴趣模型具有适用的用途，包括但不限于上下文实体搜索，自动文本突出显示，预取可能感兴趣的文档，自动内容推荐，自动广告投放等。