-
公开(公告)号：US20170206890A1
公开(公告)日：2017-07-20
申请号：US15247645
申请日：2016-08-25
Inventor： Tamir Tapuhi , Amir Lev-Tov , Avraham Faizakof , Yochai Konig
CPC classification number: G10L15/063 , G06F17/273 , G06N99/005 , G10L15/183 , G10L15/26 , G10L2015/0635 , G10L2015/0636 , G10L2015/088
Abstract: A method for generating a language model for an organization includes: receiving, by a processor, organization-specific training data; receiving, by the processor, generic training data; computing, by the processor, a plurality of similarities between the generic training data and the organization-specific training data; assigning, by the processor, a plurality of weights to the generic training data in accordance with the computed similarities; combining, by the processor, the generic training data with the organization-specific training data in accordance with the weights to generate customized training data; training, by the processor, a customized language model using the customized training data; and outputting, by the processor, the customized language model, the customized language model being configured to compute the likelihood of phrases in a medium.
-
公开(公告)号：US20170186422A1
公开(公告)日：2017-06-29
申请号：US15402070
申请日：2017-01-09
Inventor： Amir Lev-Tov , Avraham Faizakof , Yochai Konig
CPC classification number: G10L15/19 , G06F17/30389 , G06F17/30746 , G06F17/30769 , G10L15/02 , G10L15/08 , G10L15/1815 , G10L15/30
Abstract: A method including: receiving, on a computer system, a text search query, the query including one or more query words; generating, on the computer system, for each query word in the query, one or more anchor segments within a plurality of speech recognition processed audio files, the one or more anchor segments identifying possible locations containing the query word; post-processing, on the computer system, the one or more anchor segments, the post-processing including: expanding the one or more anchor segments; sorting the one or more anchor segments; and merging overlapping ones of the one or more anchor segments; and searching, on the computer system, the post-processed one or more anchor segments for instances of at least one of the one or more query words using a constrained grammar.
-
公开(公告)号：US09613619B2
公开(公告)日：2017-04-04
申请号：US14067732
申请日：2013-10-30
Inventor： Amir Lev-Tov , Avraham Faizakof , Yochai Konig
Abstract: A method for predicting a speech recognition quality of a phrase comprising at least one word includes: receiving, on a computer system including a processor and memory storing instructions, the phrase; computing, on the computer system, a set of features comprising one or more features corresponding to the phrase; providing the phrase to a prediction model on the computer system and receiving a predicted recognition quality value based on the set of features; and returning the predicted recognition quality value.
-
公开(公告)号：US09542936B2
公开(公告)日：2017-01-10
申请号：US13886205
申请日：2013-05-02
Inventor： Amir Lev-Tov , Avi Faizakof , Yochai Konig
IPC: G10L15/00 , G10L15/04 , G10L21/00 , G10L25/00 , G06F15/00 , G10L15/18 , G06F17/30 , G10L15/19 , G10L15/08
CPC classification number: G10L15/19 , G06F17/30389 , G06F17/30746 , G06F17/30769 , G10L15/02 , G10L15/08 , G10L15/1815 , G10L15/30
Abstract: A method including: receiving, on a computer system, a text search query, the query including one or more query words; generating, on the computer system, for each query word in the query, one or more anchor segments within a plurality of speech recognition processed audio files, the one or more anchor segments identifying possible locations containing the query word; post-processing, on the computer system, the one or more anchor segments, the post-processing including: expanding the one or more anchor segments; sorting the one or more anchor segments; and merging overlapping ones of the one or more anchor segments; and searching, on the computer system, the post-processed one or more anchor segments for instances of at least one of the one or more query words using a constrained grammar.
Abstract translation: 一种方法，包括：在计算机系统上接收文本搜索查询，所述查询包括一个或多个查询词; 在所述计算机系统上为所述查询中的每个查询词生成多个语音识别处理的音频文件内的一个或多个锚段，所述一个或多个锚段标识包含所述查询词的可能位置; 在所述计算机系统上对所述一个或多个锚段进行后处理，所述后处理包括：扩展所述一个或多个锚段; 对一个或多个锚段进行排序; 并且合并所述一个或多个锚段中的重叠部分; 以及在所述计算机系统上使用约束语法来搜索所述后处理的一个或多个锚段，以针对所述一个或多个查询词中的至少一个的实例。
-
35.发明申请SYSTEM AND METHOD FOR INTERACTIVE MULTI-RESOLUTION TOPIC DETECTION AND TRACKING 审中-公开用于交互式多分辨率主题检测和跟踪的系统和方法公开(公告)号：US20160188672A1
公开(公告)日：2016-06-30
申请号：US14586730
申请日：2014-12-30
Inventor： Yoni Lev , Avraham Faizakof , Amir Lev-Tov , Tamir Tapuhi , Yochai Konig
CPC classification number: G06F17/30976 , G06F17/30713 , G06Q30/0281 , G06Q50/01
Abstract: A method for tracking known topics in a plurality of interactions includes: extracting, by a processor, a plurality of fragments from the plurality of interactions; initializing, by the processor, a collection of tracked topics to an empty collection; computing, by the processor, a similarity between each fragment of the fragments and each of the known topics; and adding, by the processor, a known topic of the known topics to the tracked topics in response to the similarity between a fragment and the known topic exceeding a threshold value.
Abstract translation: 用于跟踪多个交互中的已知主题的方法包括：由处理器从多个交互中提取多个片段; 由处理器将跟踪主题的集合初始化为空集合; 由处理器计算片段的每个片段和每个已知主题之间的相似度; 以及响应于片段和超过阈值的已知主题之间的相似度，由处理器将已知主题的已知主题添加到所跟踪的主题。
-
Patent Agency Ranking
36.发明申请公开(公告)号：US20150120289A1
公开(公告)日：2015-04-30
申请号：US14067732
申请日：2013-10-30
Inventor： Amir Lev-Tov , Avraham Faizakof , Yochai Konig
IPC: G10L15/01
Abstract: A method for predicting a speech recognition quality of a phrase comprising at least one word includes: receiving, on a computer system including a processor and memory storing instructions, the phrase; computing, on the computer system, a set of features comprising one or more features corresponding to the phrase; providing the phrase to a prediction model on the computer system and receiving a predicted recognition quality value based on the set of features; and returning the predicted recognition quality value.
Abstract translation: 用于预测包括至少一个单词的短语的语音识别质量的方法包括：在包括处理器的计算机系统和存储指令的存储器上接收短语; 在所述计算机系统上计算包括与所述短语相对应的一个或多个特征的一组特征; 将所述短语提供给所述计算机系统上的预测模型，并基于所述特征集合接收预测的识别质量值; 并返回预测的识别质量值。
-
37.发明申请SYSTEM AND METHOD FOR DISCOVERING AND EXPLORING CONCEPTS AND ROOT CAUSES OF EVENTS 审中-公开发现和探索事件的概念和根本原因的系统和方法公开(公告)号：US20150032746A1
公开(公告)日：2015-01-29
申请号：US13952470
申请日：2013-07-26
Inventor： Amir Lev-Tov , Avraham Faizakof , David Ollinger , Yochai Konig
IPC: G06F17/30
CPC classification number: G06F17/30539 , G06F17/30401 , G10L15/00
Abstract: A method for determining a cause of events detected in a plurality of interactions includes: identifying, on a processor, a plurality of elements in the interactions; detecting, on the processor, a plurality of sequences of elements in the interactions; mining, on the processor, the plurality of sequences for generating a set of supported patterns; computing, on the processor, association rules from the set of supported patterns; and returning the computed association rules.
Abstract translation: 用于确定在多个交互中检测到的事件的原因的方法包括：在处理器上识别所述交互中的多个元素; 在所述处理器中检测所述交互中的多个元素序列; 在处理器上挖掘用于生成一组支持的图案的多个序列; 在所述处理器上计算来自所述一组支持模式的关联规则; 并返回计算的关联规则。
-
公开(公告)号：US11586828B2
公开(公告)日：2023-02-21
申请号：US17002352
申请日：2020-08-25
Inventor： Amir Lev-Tov , Avraham Faizakof , Arnon Mazza , Yochai Konig
IPC: G06F40/30 , G06F40/35 , G06K9/62 , G06F40/284
Abstract: Methods, systems, and computer program product for automatically performing sentiment analysis on texts, such as telephone call transcripts and electronic written communications. Disclosed techniques include, inter alia, lexicon training, handling of negations and shifters, pruning of lexicons, confidence calculation for token orientation, supervised customization, lexicon mixing, and adaptive segmentation.
-
公开(公告)号：US11025775B2
公开(公告)日：2021-06-01
申请号：US16567513
申请日：2019-09-11
Inventor： Tamir Tapuhi , Yochai Konig , Amir Lev-Tov , Avraham Faizakof , Yoni Lev
Abstract: A method for generating a dialogue tree for an automated self-help system of a contact center from a plurality of recorded interactions between customers and agents of the contact center includes: computing, by a processor, a plurality of feature vectors, each feature vector corresponding to one of the recorded interactions; computing, by the processor, similarities between pairs of the feature vectors; grouping, by the processor, similar feature vectors based on the computed similarities into groups of interactions; rating, by the processor, feature vectors within each group of interactions based on one or more criteria, wherein the criteria include at least one of interaction time, success rate, and customer satisfaction; and outputting, by the processor, a dialogue tree in accordance with the rated feature vectors for configuring the automated self-help system.
-
公开(公告)号：US20200327191A1
公开(公告)日：2020-10-15
申请号：US16381452
申请日：2019-04-11
Inventor： Amir Lev-Tov , Avraham Faizakof , Arnon Mazza , Yochai Konig
Abstract: A method, system, and computer program product for unsupervised automated generation of lexicons in a specified target domain, comprising tokens having domain-specific sentiment orientation, by selecting a seed set of tokens from a source lexicon; generating a candidate set of tokens from a text corpus in the target domain based on a similarity parameter with the seed set; calculating a sentiment score for each of the tokens in the candidate set; and automatically updating the source lexicon based on the candidate list.
-
-
-
-
-
-
-
-
-
Search Results
49
records
(took 0.02 seconds)
