公开(公告)号：US09711167B2

公开(公告)日：2017-07-18

申请号：US13419340

申请日：2012-03-13

申请人： Moshe Wasserblat ,  Tzachi Ashkenazi ,  Merav Ben-Asher ,  Oren Pereg

发明人： Moshe Wasserblat ,  Tzachi Ashkenazi ,  Merav Ben-Asher ,  Oren Pereg

IPC分类号： G10L25/78 ,  G10L17/04

CPC分类号： G10L25/78 ,  G10L17/04

摘要： A system and method for real-time processing a signal of a voice interaction. In an embodiment, a digital representation of a portion of an interaction may be analyzed in real-time and a segment may be selected. The segment may be associated with a source based on a model of the source. The model may updated based on the segment. The updated model is used to associate subsequent segments with the source. Other embodiments are described and claimed.

公开(公告)号：US20170178625A1

公开(公告)日：2017-06-22

申请号：US14976809

申请日：2015-12-21

申请人： Jonathan Mamou ,  Moshe Wasserblat ,  Oren Pereg ,  Michel Assayag ,  Orgad Keller

发明人： Jonathan Mamou ,  Moshe Wasserblat ,  Oren Pereg ,  Michel Assayag ,  Orgad Keller

IPC分类号： G10L15/18 ,  G10L15/26 ,  G10L15/10 ,  G10L15/197

CPC分类号： G10L15/1815 ,  G10L15/10 ,  G10L15/197 ,  G10L15/26

摘要： System and techniques for direct motion sensor input to rendering pipeline are described herein. A ranked list of ASR hypotheses may be obtained. A set of ASR hypotheses may be selected from the list. The set of ASR hypothesis may be re-ranked using semantic coherence scoring between words in the ASR hypotheses. An ASR hypothesis from the set of ASR hypotheses with a highest re-rank may be outputted.

公开(公告)号：US20170178623A1

公开(公告)日：2017-06-22

申请号：US14979142

申请日：2015-12-22

申请人： Oren Shamir ,  Oren Pereg ,  Moshe Wasserblat ,  Jonathan Mamou ,  Michel Assayag

发明人： Oren Shamir ,  Oren Pereg ,  Moshe Wasserblat ,  Jonathan Mamou ,  Michel Assayag

IPC分类号： G10L15/04 ,  G10L25/39 ,  G10L25/87 ,  G10L15/187 ,  G10L15/18

CPC分类号： G10L15/04 ,  G10L15/18 ,  G10L15/1822 ,  G10L15/187 ,  G10L25/39 ,  G10L25/87 ,  G10L2015/025

摘要： Technologies for detecting an end of a sentence in automatic speech recognition are disclosed. An automatic speech recognition device may acquire speech data, and identify phonemes and words of the speech data. The automatic speech recognition device may perform a syntactic parse based on the recognized words, and determine an end of a sentence based on the syntactic parse. For example, if the syntactic parse indicates that a certain set of consecutive recognized words form a syntactically complete and correct sentence, the automatic speech recognition device may determine that there is an end of a sentence at the end of that set of words.

公开(公告)号：US08914285B2

公开(公告)日：2014-12-16

申请号：US13550626

申请日：2012-07-17

申请人： Moshe Wasserblat ,  Dan Eylon ,  Ezra Daya ,  Tzach Ashkenazi ,  Oren Pereg ,  Ohad Pollak ,  Moshe Avlagon

发明人： Moshe Wasserblat ,  Dan Eylon ,  Ezra Daya ,  Tzach Ashkenazi ,  Oren Pereg ,  Ohad Pollak ,  Moshe Avlagon

IPC分类号： G10L15/10 ,  G06Q10/04

CPC分类号： G10L25/51 ,  G10L15/00 ,  G10L25/63 ,  G10L2015/088

摘要： A computerized method for sales optimization including receiving at a computer server a digital representation of a portion of an interaction between a customer and an organization representative, the portion of an interaction comprises a speech signal of the customer and a speech signal of the organization representative; analyzing the speech signal of the organization representative; analyzing the speech signal of the customer; determining a distance vector between the speech signal of the organization representative and the speech signal of the customer; and predicting a sale success probability score for the captured speech signal portion.

摘要翻译： 一种用于销售优化的计算机化方法，包括在计算机服务器处接收客户和组织代表之间的交互的一部分的数字表示，交互的部分包括客户的语音信号和组织代表的语音信号; 分析组织代表的语音信号; 分析客户的语音信号; 确定组织代表的语音信号与客户的语音信号之间的距离向量; 并且预测所捕获的语音信号部分的销售成功概率得分。

公开(公告)号：US20120053990A1

公开(公告)日：2012-03-01

申请号：US13291117

申请日：2011-11-08

申请人： Oren Pereg ,  Tzach Ashkenazi ,  Moshe Wasserblat ,  Ezra Daya ,  Oshrat Kfir ,  Hila Lam ,  Amir Rubin ,  Eyal Hurvitz

发明人： Oren Pereg ,  Tzach Ashkenazi ,  Moshe Wasserblat ,  Ezra Daya ,  Oshrat Kfir ,  Hila Lam ,  Amir Rubin ,  Eyal Hurvitz

IPC分类号： G06Q30/02

CPC分类号： G06Q10/06 ,  G06Q30/0202 ,  G06Q40/02 ,  G06Q40/08

摘要： A computerized method of predicting customer churn from an organization, including: receiving at a computer server a recorded customer interaction with an agent of the organization; analyzing the received customer interaction to extract basic features that provide an indication regarding the churn probability of the customer; extracting the entity information of the customer from the recorded interaction; retrieving from a database accessible by the server previous interactions for the same entity and extracting advanced features that provide an indication regarding the churn probability of the customer by comparing multiple interactions of the same entity; predicting a churn probability for the received interaction by applying a statistical customer churn model to the extracted basic features and extracted advanced features; and wherein the interaction and the previous interactions are recordable from more than one type of communication channel by which the customer can communicate with the organization.

摘要翻译： 一种从组织预测客户流失的计算机化方法，包括：在计算机服务器处接收记录的客户与组织代理人的交互; 分析所接收的客户交互以提取提供关于客户的流失概率的指示的基本特征; 从记录的交互中提取客户的实体信息; 从服务器可访问的数据库中检索先前相同实体的交互，并提取通过比较同一实体的多个交互来提供关于客户的流失概率的指示的高级特征; 通过将统计客户流失模型应用于提取的基本特征和提取的高级特征来预测所接收到的交互的流失概率; 并且其中所述交互和先前的交互可从多于一种类型的通信信道记录，所述客户可以通过该通信渠道与所述组织进行通信。

公开(公告)号：US20110208522A1

公开(公告)日：2011-08-25

申请号：US12709482

申请日：2010-02-21

申请人： Oren PEREG ,  Tzach ASHKENAZI

发明人： Oren PEREG ,  Tzach ASHKENAZI

IPC分类号： G10L15/26 ,  G10L15/18

CPC分类号： G06F17/279 ,  G10L15/26

摘要： A method and apparatus for automatically detecting sentiment in interactions. The method and apparatus include training, in which a model is generated upon features extracted from training interactions and tagging information. and run-time in which the model is used towards detecting sentiment in further interactions.The method and apparatus train and use models for classifying context units as containing sentiment or not, the models generated upon tagging data for indicating whether the context units indeed contain sentiment, and the sentiment polarity and intensity within the context unit. A further, upper level model is generated for providing a total score for the interaction, based on the sentiment detected and the classification scores of context units within the interaction.

摘要翻译： 一种自动检测交互情绪的方法和装置。 该方法和装置包括训练，其中在从训练交互和标记信息提取的特征上生成模型。 和运行时间，其中该模型用于在进一步的交互中检测情绪。 用于将上下文单元分类为包含情绪的方法和装置训练和使用模型，用于指示上下文单元确实包含情绪的标签数据生成的模型以及上下文单元内的情绪极性和强度。 基于检测到的情绪和交互内的上下文单元的分类分数，生成另外的上级模型，用于提供交互的总分数。

公开(公告)号：US20100246799A1

公开(公告)日：2010-09-30

申请号：US12414682

申请日：2009-03-31

申请人： Yuval Lubowich ,  Oren Pereg ,  Ezra Daya

发明人： Yuval Lubowich ,  Oren Pereg ,  Ezra Daya

IPC分类号： H04M3/00 ,  G10L15/26 ,  G06F17/27

CPC分类号： G10L15/22 ,  G10L15/142 ,  G10L15/183 ,  H04M3/5175 ,  H04M2201/12 ,  H04M2201/36

摘要： A method and apparatus for automatically sectioning an interaction into sections, in order to get more insight into interactions. The method and apparatus include training, in which a model is generated upon training interactions and available tagging information, and run-time in which the model is used towards sectioning further interactions. The method and apparatus operate on context units within the interaction, wherein each context unit is characterized by a feature vector relate to textual, acoustic or other characteristics of the context unit.

摘要翻译： 一种将交互自动划分为多个部分的方法和装置，以便更多地了解交互。 该方法和装置包括训练，其中在培训交互和可用的标签信息上生成模型，以及运行时间，其中模型用于分割进一步的交互。 所述方法和装置对所述交互中的上下文单元进行操作，其中每个上下文单元的特征在于与所述上下文单元的文本，声学或其他特征相关的特征向量。

公开(公告)号：US20080189171A1

公开(公告)日：2008-08-07

申请号：US11669955

申请日：2007-02-01

申请人： Moshe Wasserblat ,  Oren Pereg ,  Tsvika Rabkin ,  Dvir Hofman ,  Ilan Kor ,  Ilan Yossef

发明人： Moshe Wasserblat ,  Oren Pereg ,  Tsvika Rabkin ,  Dvir Hofman ,  Ilan Kor ,  Ilan Yossef

IPC分类号： G06F11/34

CPC分类号： G06Q10/10 ,  G06Q10/063 ,  G06Q10/0639 ,  G06Q10/06398 ,  G06Q30/02 ,  G06Q30/0203 ,  G06Q30/0204 ,  G06Q30/0205 ,  H04M3/5232

摘要： A method and apparatus for automated categorization of an interaction between a member of an organization and a second party. The method comprises defining one or more criteria and one or more categories, wherein each category relates to a combination of one or more criteria. The criteria involve data extracted from the interactions as well as external data. Each interaction is checked against the criteria, and is then assigned to one or more categories according to the met criteria. An optional evaluation of the categorization step, and improvement of the categorization if the evaluation results fall below a threshold are disclosed.

摘要翻译： 一种用于对组织成员和第二方之间的交互进行自动分类的方法和装置。 该方法包括定义一个或多个标准和一个或多个类别，其中每个类别涉及一个或多个标准的组合。 这些标准涉及从交互中提取的数据以及外部数据。 根据标准检查每个交互，然后根据满足的条件将其分配到一个或多个类别。 公开了分类步骤的可选评估，以及如果评估结果低于阈值则改进分类。

公开(公告)号：US08996371B2

公开(公告)日：2015-03-31

申请号：US13433417

申请日：2012-03-29

申请人： Eyal Hurvitz ,  Ezra Daya ,  Oren Pereg ,  Moshe Wasserblat

发明人： Eyal Hurvitz ,  Ezra Daya ,  Oren Pereg ,  Moshe Wasserblat

IPC分类号： G10L15/26 ,  G10L15/183

CPC分类号： G10L15/183

摘要： A system and method for adapting a language model to a specific environment by receiving interactions captured the specific environment, generating a collection of documents from documents retrieved from external resources, detecting in the collection of documents terms related to the environment that are not included in an initial language model and adapting the initial language model to include the terms detected.

摘要翻译： 一种用于通过接收捕获特定环境的交互来将语言模型适配到特定环境的系统和方法，从从外部资源检索的文档生成文档的集合，在文档集合中检测与环境相关的术语，其不包括在 初始语言模型和适应初始语言模型以包含检测到的术语。

公开(公告)号：US08762161B2

公开(公告)日：2014-06-24

申请号：US12245778

申请日：2008-10-06

申请人： Tzach Ashkenazi ,  Oren Pereg ,  Yuval Lubowich

发明人： Tzach Ashkenazi ,  Oren Pereg ,  Yuval Lubowich

IPC分类号： G06Q30/02 ,  G06Q10/10 ,  G06Q10/06 ,  G06Q30/06 ,  G06Q10/08 ,  G06F17/30

CPC分类号： G06F17/30994 ,  G06Q10/06

摘要： A method and apparatus for visualization of call categorization, comprising steps and components for: defining or receiving a definition for one or more categories and criteria for each category; receiving or capturing interactions; categorizing the interactions into the categories; determining relations between the categories; determining layout for the categories and relations; and visualizing the layout. The method and apparatus can further comprise steps and components for extracting key-phrases, determining connections between key-phrases, connections between categories based on key-phrases, and connections between categories and key-phrases, and visualizing the categories, key-phrases and connections. The method and apparatus can further comprise steps and components for training models upon which the relations between categories and relations between key-phrases are determined.

摘要翻译： 一种用于可视化呼叫分类的方法和装置，包括步骤和组件，用于：定义或接收每个类别的一个或多个类别和标准的定义; 接收或捕获交互; 将互动分类到类别中; 确定类别之间的关系; 确定类别和关系的布局; 并可视化布局。 该方法和装置还可以包括用于提取关键短语的步骤和组件，基于关键短语确定关键短语之间的连接，类别之间的连接以及类别和关键词之间的连接，以及可视化类别，关键词和 连接。 该方法和装置还可以包括用于训练模型的步骤和组件，在该模型上确定关键短语之间的类别和关系之间的关系。