公开(公告)号：US20170011060A1

公开(公告)日：2017-01-12

申请号：US15271900

申请日：2016-09-21

Applicant: NICE-SYSTEMS LTD.

Inventor： Roi AMIR ,  Dan SHARON ,  Eyal STRASSBERG

IPC: G06F17/30

CPC classification number: G06F17/30165 ,  G06F17/3012 ,  G06F17/30194 ,  G06F17/30598

Abstract: A generic categorization method may include receiving interaction data on a distributed computing system operating on a plurality of computing nodes. The distributed computing system may distribute the received interaction data across the plurality of nodes. On each node, categorization rules may be applied to the interaction data via parallel processing. The results, which may include a category associated with each interaction, may be written to a distributed storage system. A user interface may allow a user to define the categorization rules and schemas of interaction data.

Abstract translation: 通用分类方法可以包括在多个计算节点上操作的分布式计算系统上接收交互数据。 分布式计算系统可以在多个节点之间分配所接收的交互数据。 在每个节点上，分类规则可以通过并行处理应用于交互数据。 可以将包括与每个交互相关联的类别的结果写入分布式存储系统。 用户界面可以允许用户定义交互数据的分类规则和模式。

公开(公告)号：US20160365093A1

公开(公告)日：2016-12-15

申请号：US14736282

申请日：2015-06-11

Applicant: Nice-Systems Ltd.

Inventor： Maor NISSAN

IPC: G10L15/26 ,  G06F17/27 ,  G10L15/187

CPC classification number: G10L15/187 ,  G06F17/2735 ,  G10L15/183

Abstract: A system and method for generating a transcript of an audio input. An embodiment of a system and method may include generating a phonetic lattice by decoding the audio input and producing a transcription based on the phonetic lattice and based on a first language model. A transcription may be analyzed to produce analysis results. Analysis results may be used to select from a plurality of language models, one language model and the selected language model may be used to generate a transcript of the audio input.

Abstract translation: 一种用于生成音频输入的录音的系统和方法。 系统和方法的实施例可以包括通过解码音频输入并基于语音格并基于第一语言模型产生转录来产生语音格子。 可以分析转录以产生分析结果。 分析结果可以用于从多个语言模型中选择，可以使用一种语言模型和所选择的语言模型来生成音频输入的抄本。

公开(公告)号：US20160365090A1

公开(公告)日：2016-12-15

申请号：US14736277

申请日：2015-06-11

Applicant: NICE-SYSTEMS LTD.

Inventor： Maor NISSAN

IPC: G10L15/19 ,  G10L15/26

CPC classification number: G10L15/19 ,  G10L15/187

Abstract: A computer-implemented method of generating a language model. An embodiment of a system and method may include selecting a set of words from a transcription of an audio input, the transcription produced by a current language model. The set of words may be used to obtain a set of content objects. The set of content objects may be used to generate a new language model. The current language model may be replaced by the new language model.

Abstract translation: 一种计算机实现的生成语言模型的方法。 系统和方法的实施例可以包括从音频输入的转录中选择一组单词，由当前语言模型产生的转录。 可以使用该组词来获得一组内容对象。 内容对象集可以用于生成新的语言模型。 当前的语言模型可能被新的语言模型所取代。

公开(公告)号：US20160335728A1

公开(公告)日：2016-11-17

申请号：US14708971

申请日：2015-05-11

Applicant: NICE-SYSTEMS LTD.

Inventor： Yoram POMER ,  Sivan LANDAU ,  Itai VELTZMAN

IPC: G06Q40/00

CPC classification number: G06Q40/04

Abstract: A transaction tracking system includes a display that permits viewing the relationship between related transactions. In the display, individual transactions are depicted as transaction icons sorted in time order horizontal rows according to order ID.

Abstract translation: 交易跟踪系统包括允许查看相关交易之间的关系的显示器。 在显示中，根据订单ID，将各个交易描绘为以时间顺序排列的交易图标。

公开(公告)号：US20160292706A1

公开(公告)日：2016-10-06

申请号：US14829695

申请日：2015-08-19

Applicant: NICE-SYSTEMS LTD.

Inventor： Leonard Michael NEWNHAM

IPC: G06Q30/02 ,  G06N99/00

CPC classification number: G06Q30/0224 ,  G06N20/00 ,  G06Q30/0235 ,  G06Q30/0239

Abstract: Methods and systems for selecting an offer from a set of offers to be served to one or more respondents. In some embodiments, for each of the offers, an expected reward distribution is obtained comprising an estimate of the distribution over time of reward received in response to the offer. Requests are received for the selection of an offer and in response to each request an offer is selected with the selection depending at least partially on the expected reward distribution. The expected reward distributions are updated in repeated update operations after the initial serving of each offer, the updating being based on an observed distribution of reward received in response to the servings of the offer. The updated expected reward distribution is then used in the next selection of an offer. Update operations may take place before a complete set of response data is received.

Abstract translation: 从一组要约提供给一个或多个受访者的方案和系统。 在一些实施例中，对于每个优惠，获得期望的奖励分配，其包括响应于该提议而接收的奖励随时间的分布的估计。 接收请求以选择报价，并且响应于每个请求，至少部分地基于所预期的报酬分布，选择所提供的报价。 预期奖励分配在每个提供的初始服务之后的重复更新操作中被更新，更新是基于响应于提供的份额而接收的奖励的观察分配。 更新的预期奖励分配然后用于下一个优惠的选择。 在收到完整的一组响应数据之前，可能会进行更新操作。

公开(公告)号：US09245523B2

公开(公告)日：2016-01-26

申请号：US13950299

申请日：2013-07-25

Applicant: NICE-SYSTEMS LTD

Inventor： Moshe Wasserblat ,  Maya Gorodetsky ,  Gennadi Lembersky

IPC: G06F17/30 ,  G10L15/26 ,  G10L15/18 ,  G10L15/08

CPC classification number: G10L15/1815 ,  G06F17/3074 ,  G06F17/30746 ,  G10L15/26 ,  G10L2015/088

Abstract: The subject matter discloses a method for expansion of search queries on large vocabulary continuous speech recognition transcripts comprising: obtaining a textual transcript of audio interaction generated by the large vocabulary continuous speech recognition; generating a topic model from the textual transcripts; said topic model comprises a plurality of topics wherein each topic of the plurality of topics comprises a list of keywords; obtaining a search term; associating a topic from the topic model with the search term; and generating a list of candidate term expansion words by selecting keywords from the list of keywords of the associated topic; said candidate term expansion words are of high probability to be substitution errors of the search term that are generated by the large vocabulary continuous speech recognition.

Abstract translation: 主题公开了一种用于扩展大词汇连续语音识别转录的搜索查询的方法，包括：获得由大词汇连续语音识别产生的音频交互的文本转录; 从文本记录中产生主题模型; 所述主题模型包括多个主题，其中所述多个主题的每个主题包括关键字列表; 获取搜索词; 将主题模型中的主题与搜索项相关联; 以及通过从所述关联主题的关键字列表中选择关键字来生成候选词扩展词列表; 所述候选词扩展词的高概率是由大词汇连续语音识别产生的搜索词的替代误差。

公开(公告)号：US20150295850A1

公开(公告)日：2015-10-15

申请号：US14250852

申请日：2014-04-11

Applicant: NICE-SYSTEMS LTD.

Inventor： Tal ZUR ,  Efim Kolodizner

IPC: H04L12/911

CPC classification number: H04L47/783 ,  G06F9/52 ,  G06F11/2028 ,  G06F11/2038 ,  H04L1/22

Abstract: A computing system comprising multiple computing resources in which one resource assumes spare status using a spare election algorithm. According to the algorithm each computing resource on initialisation requests permission to assume spare state from the other computing resources. Then if all of the other computing resources grant the permission the requesting computing resource assumes spare state. If one of the other computing resources does not grant the permission to the requesting resource then the requesting resource assumes normal state.

Abstract translation: 一种包括多个计算资源的计算系统，其中一个资源使用备用选择算法进行备用状态。 根据该算法，初始化时的每个计算资源请求允许从其他计算资源采取备用状态。 然后，如果所有其他计算资源授予请求计算资源占用备用状态的权限。 如果其他计算资源之一不授予请求资源的权限，则请求资源将呈现正常状态。

公开(公告)号：US20150235159A1

公开(公告)日：2015-08-20

申请号：US14184728

申请日：2014-02-20

Applicant: NICE-SYSTEMS LTD.

Inventor： David GEFFEN ,  Yizhar RONEN ,  Hovav LAPIDOT ,  Ohad POLLAK ,  Nadav DORON

IPC: G06Q10/06

CPC classification number: G06Q10/06395

Abstract: In a method for providing guidance to agents of a contact center, a server of an agent guidance system provides a list of key selling points to a plurality of workstations. Each of the workstations is associated with an agent of the contact center. Each key selling point of the list is associated with an effectiveness status. The server receives from a workstation feedback related to an effectiveness of a key selling point of the list. The effectiveness status of a key selling point of the list is automatically modified in accordance with the received feedback. The server provides to the workstations a modified list that incorporates the modified effectiveness status.

Abstract translation: 在向联络中心的代理提供指导的方法中，代理引导系统的服务器向多个工作站提供关键卖点的列表。 每个工作站都与联络中心的代理关联。 列表的每个关键卖点与有效状态相关联。 服务器从工作站收到有关列表关键卖点有效性的反馈。 列表关键卖点的有效性状态将根据收到的反馈进行自动修改。 服务器向工作站提供一个包含修改的有效性状态的修改列表。

公开(公告)号：US09054969B2

公开(公告)日：2015-06-09

申请号：US13731836

申请日：2012-12-31

Applicant: NICE SYSTEMS LTD.

Inventor： Noam Cohen ,  Yoram Ehrlich

IPC: H04L12/26

CPC classification number: H04L43/0876 ,  H04L43/04

Abstract: A system and method for monitoring Internet Protocol (IP) data traffic may include receiving IP data generated by a target device interacting on the Internet, determining at least one activity performed by the target device based on the IP data, wherein an activity describes an interaction on the Internet, and aggregating data describing the at least one activity into one or more chunks, each chunk corresponding to a portion of time and at least one activity performed by the targets.

Abstract translation: 用于监视互联网协议（IP）数据业务的系统和方法可以包括接收由在因特网上交互的目标设备生成的IP数据，基于IP数据确定目标设备执行的至少一个活动，其中活动描述交互 并且将描述所述至少一个活动的数据聚合成一个或多个块，每个块对应于一部分时间和由所述目标执行的至少一个活动。

公开(公告)号：US20150032448A1

公开(公告)日：2015-01-29

申请号：US13950299

申请日：2013-07-25

Applicant: NICE-SYSTEMS LTD

Inventor： Moshe WASSERBLAT ,  Maya GORODETSKY ,  Gennady LAMBERSKY

IPC: G10L15/08 ,  G10L15/26

CPC classification number: G10L15/1815 ,  G06F17/3074 ,  G06F17/30746 ,  G10L15/26 ,  G10L2015/088

Abstract: The subject matter discloses a method for expansion of search queries on large vocabulary continuous speech recognition transcripts comprising: obtaining a textual transcript of audio interaction generated by the large vocabulary continuous speech recognition; generating a topic model from the textual transcripts; said topic model comprises a plurality of topics wherein each topic of the plurality of topics comprises a list of keywords; obtaining a search term; associating a topic from the topic model with the search term; and generating a list of candidate term expansion words by selecting keywords from the list of keywords of the associated topic; said candidate term expansion words are of high probability to be substitution errors of the search term that are generated by the large vocabulary continuous speech recognition.

Abstract translation: 主题公开了一种用于扩展大词汇连续语音识别转录的搜索查询的方法，包括：获得由大词汇连续语音识别产生的音频交互的文本转录; 从文本记录中产生主题模型; 所述主题模型包括多个主题，其中所述多个主题的每个主题包括关键字列表; 获取搜索词; 将主题模型中的主题与搜索项相关联; 以及通过从所述关联主题的关键字列表中选择关键字来生成候选词扩展词列表; 所述候选词扩展词的高概率是由大词汇连续语音识别产生的搜索词的替代误差。