公开(公告)号：US20170195491A1

公开(公告)日：2017-07-06

申请号：US15362728

申请日：2016-11-28

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak ,  Thomas Veatch

IPC: H04M3/523 ,  G10L15/30 ,  G06Q10/06 ,  G10L15/08 ,  G10L25/51 ,  G06Q10/10 ,  H04M3/51 ,  G10L17/26

CPC classification number: H04M3/5232 ,  G06F17/21 ,  G06Q10/063112 ,  G06Q10/1053 ,  G10L15/08 ,  G10L15/26 ,  G10L15/30 ,  G10L17/26 ,  G10L25/51 ,  G10L25/60 ,  H04M3/2281 ,  H04M3/51 ,  H04M3/5175 ,  H04M3/5233 ,  H04M3/5235 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2203/402

Abstract: A computer-implemented system and method for assigning call agents to callers is provided. A call from a caller is received into a call center. A voice sample is obtained from the caller during the call and analyzed. Traits of the caller are identified from the analyzed voice sample. A determination that at least one of the identified traits includes characteristics of multiple populations for that trait is made. The identified trait is defined as a percentage of each population included in that trait. The caller traits are compared to traits associated with each active agent within the call center. The agent with the traits most similar to the caller traits is assigned to the caller.

公开(公告)号：US09633658B2

公开(公告)日：2017-04-25

申请号：US15207440

申请日：2016-07-11

Applicant: Intellisist, Inc.

Inventor： David Milstein

IPC: G10L15/01 ,  G10L15/06 ,  G10L15/26 ,  H04M3/51 ,  H04M3/42 ,  G10L15/22 ,  G10L15/10 ,  G10L15/19

CPC classification number: G10L15/26 ,  G10L15/01 ,  G10L15/06 ,  G10L15/063 ,  G10L15/10 ,  G10L15/1822 ,  G10L15/19 ,  G10L15/22 ,  G10L2015/0631 ,  G10L2015/0638 ,  H04M3/42221 ,  H04M3/51 ,  H04M3/5183

Abstract: A computer-implemented system and method for transcription error reduction during a live call is provided. Speech utterances are transcribed during a live call. A confidence score is assigned to each transcribed speech utterance. One of the transcribed speech utterances with a low confidence score is identified. An attempt is made to identify a pool of related transcribed speech utterances by monitoring other live calls for a predetermined amount of time. Similar transcribed speech utterances with low confidence scores are identified and a group of the similar transcribed speech utterances and the identified transcribed speech utterance is formed. A determination is made as to whether the group includes a predetermined number of transcribed speech utterances upon termination of the predetermined time. If so, a sample of the transcribed speech utterances in the pool is processed to verify a validity of the transcribed speech utterances.

公开(公告)号：US09621726B2

公开(公告)日：2017-04-11

申请号：US14667549

申请日：2015-03-24

Applicant: Intellisist, Inc.

Inventor： David Milstein ,  Gilad Odinak ,  Howard M. Lee

IPC: H04M3/00 ,  H04M3/51 ,  H04M3/487 ,  H04M3/42 ,  H04M3/523 ,  G06F17/30

CPC classification number: H04M3/5183 ,  G06F17/30705 ,  G06F17/30861 ,  H04M3/42382 ,  H04M3/4872 ,  H04M3/51 ,  H04M3/5232 ,  H04M2203/556 ,  H04M2203/655

Abstract: A computer-implemented system and method for detecting events for use in an automated call center environment are provided. A plurality of messages is monitored by a call center. Those messages sharing one or more keywords representative of one or more potential events are identified. The one or more potential events are detected based on the shared keywords. At least one of the potential events is identified as an event based on the number of messages that share the keywords representative of that potential event. Metadata regarding the event is extracted from the messages sharing the keywords representative of the event. A message regarding the event that includes the extracted metadata is generated. The generated message from the call center is provided to at least one user related to the event.

公开(公告)号：US09514329B2

公开(公告)日：2016-12-06

申请号：US13853972

申请日：2013-03-29

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak

IPC: H04L29/06 ,  G06F21/62 ,  H04L9/08

CPC classification number: G06F21/6227 ,  G06Q30/0281 ,  H04L9/0861 ,  H04L9/0866 ,  H04L9/0869 ,  H04L9/0894 ,  H04L9/14 ,  H04M3/42221 ,  H04M3/5175 ,  H04M2203/301 ,  H04M2203/609

Abstract: A computer-implemented system and method for individual record encryption is provided. A plurality of records associated with incoming calls to a call center are maintained. A unique encryption key is randomly generated for each record. The records are each encrypted using the encryption key generated for that record. The keys are stored in a location separate from the encrypted records.

Abstract translation: 提供了用于单独记录加密的计算机实现的系统和方法。 保持与呼叫中心的呼入相关联的多个记录。 为每个记录随机生成唯一的加密密钥。 记录都使用为该记录生成的加密密钥进行加密。 密钥存储在与加密记录分开的位置。

公开(公告)号：US20160323451A1

公开(公告)日：2016-11-03

申请号：US15207391

申请日：2016-07-11

Applicant: Intellisist, Inc.

Inventor： David Milstein ,  Gilad Odinak ,  Howard M. Lee

IPC: H04M3/51 ,  G10L25/87 ,  H04M3/523 ,  H04M3/56 ,  H04M3/42

CPC classification number: H04M3/5191 ,  G06Q10/063112 ,  G06Q10/1097 ,  G10L25/87 ,  G10L2015/088 ,  H04M3/42221 ,  H04M3/5166 ,  H04M3/5175 ,  H04M3/5233 ,  H04M3/56 ,  H04M2201/40

Abstract: A system and method for providing ongoing call center call assistance with the aid of a digital computer is provided. A call is received from a caller by an automatic call distributor in a call center and the caller is connected by the automatic call distributor to an agent of the call center. The agent's speech during the call is monitored by an intervention processor included in the call center. The intervention processor determines speech characteristics of the agent during the call, obtains predetermined speech characteristics for the agent, compares the predetermined speech characteristics to the speech characteristics determined during the call, and detects the agent being in need of assistance based on the comparison. The automatic call distributor determines a subject matter of the call and the intervention processor identifies an expert whose expertise matches the subject matter. The intervention processor patches the expert into the call.

Abstract translation: 提供了一种借助数字计算机提供持续呼叫中心呼叫协助的系统和方法。 通过呼叫中心的自动呼叫分配器从呼叫者接收到呼叫，呼叫者通过自动呼叫分配器连接到呼叫中心的代理。 呼叫中的代理人讲话由呼叫中心内的干预处理器进行监控。 干预处理器确定呼叫期间代理的语音特性，获得代理的预定语音特性，将预定语音特征与在呼叫期间确定的语音特征进行比较，并且基于比较来检测需要帮助的代理。 自动呼叫分配器确定呼叫的主题，并且干预处理器识别专家与主题匹配的专家。 干预处理器将专家补丁到呼叫中。

公开(公告)号：US09258414B2

公开(公告)日：2016-02-09

申请号：US14691519

申请日：2015-04-20

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak ,  Alastair Sutherland

IPC: H04M3/00 ,  H04M5/00 ,  H04M3/42 ,  H04M3/51 ,  H04M3/53 ,  H04M3/493 ,  H04W4/12 ,  G10L13/08 ,  G10L15/26 ,  H04M3/523 ,  H04M3/533

CPC classification number: H04M3/5183 ,  G10L13/08 ,  G10L15/265 ,  H04M3/42059 ,  H04M3/42221 ,  H04M3/42382 ,  H04M3/4936 ,  H04M3/51 ,  H04M3/5133 ,  H04M3/5166 ,  H04M3/523 ,  H04M3/5322 ,  H04M3/533 ,  H04M2201/38 ,  H04M2201/39 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2203/306 ,  H04M2203/357 ,  H04M2203/4536 ,  H04W4/12

Abstract: A computer-implemented system and method for facilitating agent-customer calls is provided. A call from a customer is accepted into a call center and is assigned to an agent associated with the call center. At least one text message is received from the customer during the call and is directed to the agent. Outgoing text messages are received from the agent in response to the text message from the customer and content of the outgoing text messages from the agent are converted into synthesized speech. The synthesized speech is provided to the customer during the call.

Abstract translation: 提供了一种用于促进代理客户呼叫的计算机实现的系统和方法。 来自客户的呼叫被接收到呼叫中心并被分配给与呼叫中心相关联的代理。 在通话期间从客户接收至少一个短信，并被指示给代理。 响应于来自客户的文本消息从代理接收到传出短信，并且来自代理的输出文本消息的内容被转换为合成语音。 在通话期间将合成语音提供给客户。

公开(公告)号：US09224389B2

公开(公告)日：2015-12-29

申请号：US14010501

申请日：2013-08-26

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak

IPC: G10L15/18 ,  G10L15/30 ,  G10L15/32 ,  G10L15/34 ,  H04M3/51 ,  G10L15/193

CPC classification number: G10L15/30 ,  G10L13/08 ,  G10L15/18 ,  G10L15/193 ,  G10L15/32 ,  G10L15/34 ,  H04M3/51 ,  H04M3/5166 ,  H04M3/5183 ,  H04M2201/38 ,  H04M2201/40

Abstract: A system and method for performing distributed speech recognition is provided. Audio data is received on a main recognizer and on each of a plurality of secondary recognizers. Secondary grammars are transmitted to each of the secondary recognizers. The secondary recognizers each perform speech recognition on the audio data using the secondary grammar for that secondary recognizer. A new grammar is constructed based on results of the speech recognition by each of the secondary recognizers. The main recognizer performs speech recognition on the audio data using the new grammar.

Abstract translation: 提供了一种用于执行分布式语音识别的系统和方法。 在主识别器和多个次级识别器中的每一个上接收音频数据。 次级语法被传送到每个二级识别器。 次级识别器使用该二级识别器的辅助语法对音频数据进行语音识别。 基于每个二级识别器的语音识别结果构建新的语法。 主识别器使用新的语法对音频数据执行语音识别。

公开(公告)号：US09159054B2

公开(公告)日：2015-10-13

申请号：US14485589

申请日：2014-09-12

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak ,  Thomas Veatch

IPC: H04M3/00 ,  G06Q10/10 ,  H04M3/51 ,  G10L15/08 ,  G10L25/60 ,  H04M3/523 ,  G10L17/26

CPC classification number: H04M3/5232 ,  G06F17/21 ,  G06Q10/063112 ,  G06Q10/1053 ,  G10L15/08 ,  G10L15/26 ,  G10L15/30 ,  G10L17/26 ,  G10L25/51 ,  G10L25/60 ,  H04M3/2281 ,  H04M3/51 ,  H04M3/5175 ,  H04M3/5233 ,  H04M3/5235 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2203/402

Abstract: A system and method for providing guidance to persuade a caller is provided. A call is received from a caller into a call center and an offer is provided to the caller. A likelihood of the caller to accept the offer is measured by analyzing voice input of the caller during the call. One or more paralinguistic voice characteristics in the voice input are determined. A stage of persuasion is assigned to the caller based on the paralinguistic voice characteristics and a recommendation is made for guidance to persuade the caller to accept the offer.

Abstract translation: 提供了一种用于提供指导以说​​服呼叫者的系统和方法。 从呼叫者接收到呼叫中心的呼叫，并向呼叫者提供报价。 呼叫者接受报价的可能性是通过分析呼叫中的呼叫者的语音输入来测量的。 确定语音输入中的一个或多个旁路语音特征。 劝说阶段根据语音特征分配给呼叫者，并建议引导以说服呼叫者接受该提议。

公开(公告)号：US08972261B2

公开(公告)日：2015-03-03

申请号：US14171732

申请日：2014-02-03

Applicant: Intellisist, Inc.

Inventor： David Milstein

IPC: G10L15/00 ,  G10L15/06 ,  G10L15/26

CPC classification number: G10L15/26 ,  G10L15/01 ,  G10L15/06 ,  G10L15/063 ,  G10L15/10 ,  G10L15/1822 ,  G10L15/19 ,  G10L15/22 ,  G10L2015/0631 ,  G10L2015/0638 ,  H04M3/42221 ,  H04M3/51 ,  H04M3/5183

Abstract: A computer-implemented system and method for voice transcription error reduction is provided. Speech utterances are obtained from a voice stream and each speech utterance is associated with a transcribed value and a confidence score. Those utterances with transcription values associated with lower confidence scores are identified as questionable utterances. One of the questionable utterances is selected from the voice stream. A predetermined number of questionable utterances from other voice streams and having transcribed values similar to the transcribed value of the selected questionable utterance are identified as a pool of related utterances. A further transcribed value is received for each of a plurality of the questionable utterances in the pool of related utterances. A transcribed message is generated for the voice stream using those transcribed values with higher confidence scores and the further transcribed value for the selected questionable utterance.

Abstract translation: 提供了一种用于语音转录错误减少的计算机实现的系统和方法。 从语音流中获得语音话语，并且每个语音话语与转录值和置信度得分相关联。 具有与较低置信度得分相关联的转录值的话语被确定为可疑话语。 从语音流中选择一个可疑话语。 来自其他语音流并具有与所选择的可疑话语的转录值类似的转录值的预定数量的可疑话语被识别为相关话语池。 在相关话语池中的多个可疑话语中的每一个接收另外的转录值。 使用具有更高置信度得分的转录值和所选择的可疑话语的另外的转录值，为语音流生成转录消息。

公开(公告)号：US20150003603A1

公开(公告)日：2015-01-01

申请号：US14485596

申请日：2014-09-12

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak ,  Thomas Veatch

IPC: H04M3/523

CPC classification number: H04M3/5232 ,  G06F17/21 ,  G06Q10/063112 ,  G06Q10/1053 ,  G10L15/08 ,  G10L15/26 ,  G10L15/30 ,  G10L17/26 ,  G10L25/51 ,  G10L25/60 ,  H04M3/2281 ,  H04M3/51 ,  H04M3/5175 ,  H04M3/5233 ,  H04M3/5235 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2203/402

Abstract: A system and method for pairing agents and callers within a call center environment is provided. A call is received from a caller into a call center. A voice sample is received from the caller during the call and traits of the caller are identified from the voice sample. The traits of the caller are compared to traits of one or more candidate agents within the call center. A similarity is determined between the caller and each candidate agent based a number of the traits shared by the caller and that candidate agent. One of the candidate agents is selected based on the similarity and the caller is connected with the selected candidate agent.

Abstract translation: 提供了一种用于在呼叫中心环境中配对代理和呼叫者的系统和方法。 从呼叫者接收到呼叫中心呼叫。 在呼叫期间从呼叫者接收到语音样本，并且从语音样本识别呼叫者的特征。 呼叫者的特征与呼叫中心内的一个或多个候选代理的特征进行比较。 基于呼叫者和该候选代理共享的特征的数量，在呼叫者和每个候选代理之间确定相似性。 基于相似性选择候选代理之一，并且呼叫者与选择的候选代理连接。