公开(公告)号：US20070263840A1

公开(公告)日：2007-11-15

申请号：US11510971

申请日：2006-08-28

申请人： Satoshi Shinpuku ,  Yusuke Komaba ,  Takashi Yanase ,  Hideki Yamanaka ,  Sachiko Onodera ,  Isao Namba

发明人： Satoshi Shinpuku ,  Yusuke Komaba ,  Takashi Yanase ,  Hideki Yamanaka ,  Sachiko Onodera ,  Isao Namba

IPC分类号： H04M3/00 ,  H04M5/00

CPC分类号： H04M3/5175 ,  H04M2203/403

摘要： A computer-readable recording medium having recorded therein agent training program in which when each agent has been performing an answer, agent identifier, and enquiry contents and contents of the answer are stored in a storage device. An enquiry pattern is extracted from enquiry contents. Respective agents' answers are evaluated, for each enquiry pattern, and by a model contents of the answer extraction section, contents of the answer of an agent with highest evaluation is extracted as model contents of the answer. The contents of the answer of a trainee agent and model contents of the answer are divided into predetermined phases, and corresponding phase of both are mutually compared to calculate ineptitude-degrees in respective phases of trainee agent. By specifying from the model contents of the answer, a range of contents of the answer containing therein at least one of the phases where the ineptitude-degree is high, and lasting predetermined time,; and generating teaching material with these contents, teaching material specialized for the inept answers of respective agents is provided, and agent training support performed.

摘要翻译： 一种计算机可读记录介质，其中记录有代理训练程序，其中当每个代理已经执行答案时，代理标识符和查询内容以及答案的内容被存储在存储设备中。 从查询内容中提取查询模式。 评估各代理人的答案，对于每个查询模式，并通过答案提取部分的模型内容，提取具有最高评估的代理人的答案的内容作为答案的模型内容。 受训代理人的答案内容和答案的模型内容分为预定阶段，相互比较两者的相应项，以计算受训代理人各阶段的无关程度。 通过从答案的模型内容中指定包含无效度高的持续预定时间的至少一个相位的答案的内容的范围; 并提供具有这些内容的教学材料，提供专门针对各自代理人的无答案的教材，并进行代理培训支持。

公开(公告)号：US20050201546A1

公开(公告)日：2005-09-15

申请号：US10891175

申请日：2004-07-14

申请人： Takashi Yanase ,  Hideki Yamanaka ,  Isao Namba

发明人： Takashi Yanase ,  Hideki Yamanaka ,  Isao Namba

IPC分类号： G06Q10/00 ,  G06Q10/06 ,  G06Q50/00 ,  H04M3/00 ,  H04M5/00

CPC分类号： G06Q10/10 ,  G06Q10/04 ,  G06Q10/06 ,  H04M3/36 ,  H04M3/5175 ,  H04M3/5233

摘要： In a work skill estimating device, an item information receiving unit receives, as item information, duration information of each dealing sequence in a customer call. A dealing duration estimating unit estimates a dealing duration of an item based on the item information received. A work skill estimating unit estimates an operator's work skill based on the dealing duration estimated. A skill map creating unit creates a skill map to comprehend the operator's work skill estimated.

摘要翻译： 在工作技能估计装置中，项目信息接收单元作为项目信息接收客户呼叫中的每个交易序列的持续时间信息。 交易持续时间估计单元基于接收的项目信息来估计项目的交易持续时间。 工作技能估计单元根据估计的交易持续时间来估计运营商的工作技能。 技能地图创建单元创建技能图以理解操作者的估计工作技能。

公开(公告)号：US08341012B2

公开(公告)日：2012-12-25

申请号：US11189825

申请日：2005-07-27

申请人： Hideki Yamanaka ,  Takashi Yanase ,  Isao Namba

发明人： Hideki Yamanaka ,  Takashi Yanase ,  Isao Namba

IPC分类号： G06Q10/00

CPC分类号： H04M3/5233 ,  H04M2201/14

摘要： A working skill estimating program is provided for estimating working skills of each agent in the state of separating a disturbance factor from response records (incidents). A large category classifier is supplied with the incidents within a predetermined time and classifies the incidents according to classification rules, for creating the topic-classified incidents. A small category generator collects the analogous incidents for each task type of the topic-classified incidents and generates a small category. A disturbance distinguisher distinguishes if the incidents belonging to each small category are common response records that appear regularly over time or disturbances whose frequency exhibits a significant time dependency. Then, a skill estimator estimates the working skills of each agent for each task type by using only common incidents determined as the common information.

摘要翻译： 提供了一个工作技能估算计划，用于估计每个代理人在将干扰因素与响应记录（事件）分开的状态下的工作技能。 在预定时间内提供大类分类器，并根据分类规则对事件进行分类，以创建主题分类事件。 小类别生成器针对主题分类事件的每个任务类型收集类似的事件，并生成一个小类别。 干扰辨别器区分属于每个小类别的事件是否是随着时间的推移而出现的常见的响应记录或其频率具有显着的时间依赖性的干扰。 然后，技能估算器仅使用被确定为公共信息的常见事件来估计每个任务类型的每个代理的工作技能。

公开(公告)号：US07783027B2

公开(公告)日：2010-08-24

申请号：US11510971

申请日：2006-08-28

申请人： Satoshi Shinpuku ,  Yusuke Komaba ,  Takashi Yanase ,  Hideki Yamanaka ,  Sachiko Onodera ,  Isao Namba

发明人： Satoshi Shinpuku ,  Yusuke Komaba ,  Takashi Yanase ,  Hideki Yamanaka ,  Sachiko Onodera ,  Isao Namba

IPC分类号： H04M3/00

CPC分类号： H04M3/5175 ,  H04M2203/403

摘要： A computer-readable recording medium having recorded therein agent training program in which when each agent has been performing an answer, agent identifier, and enquiry contents and contents of the answer are stored in a storage device. An enquiry pattern is extracted from enquiry contents. Respective agents' answers are evaluated, for each enquiry pattern, and by a model contents of the answer extraction section, contents of the answer of an agent with highest evaluation is extracted as model contents of the answer. The contents of the answer of a trainee agent and model contents of the answer are divided into predetermined phases, and corresponding phase of both are mutually compared to calculate ineptitude-degrees in respective phases of trainee agent. By specifying from the model contents of the answer, a range of contents of the answer containing therein at least one of the phases where the ineptitude-degree is high, and lasting predetermined time, and generating teaching material with these contents, teaching material specialized for the inept answers of respective agents is provided, and agent training support performed.

摘要翻译： 一种计算机可读记录介质，其中记录有代理训练程序，其中当每个代理已经执行答案时，代理标识符和查询内容以及答案的内容被存储在存储设备中。 从查询内容中提取查询模式。 评估各代理人的答案，对于每个查询模式，并通过答案提取部分的模型内容，提取具有最高评估的代理人的答案的内容作为答案的模型内容。 受训代理人的答案内容和答案的模型内容分为预定阶段，相互比较两者的相应项，以计算受训代理人各阶段的无关度。 通过从答案的模型内容中指定答案的内容范围，其中包含无效度高的持续预定时间的至少一个阶段，并且生成具有这些内容的教学材料，专门用于 提供各代理人的答案，并进行代理培训支持。

公开(公告)号：US07873155B2

公开(公告)日：2011-01-18

申请号：US10891175

申请日：2004-07-14

申请人： Takashi Yanase ,  Hideki Yamanaka ,  Isao Namba

发明人： Takashi Yanase ,  Hideki Yamanaka ,  Isao Namba

IPC分类号： H04M3/00

CPC分类号： G06Q10/10 ,  G06Q10/04 ,  G06Q10/06 ,  H04M3/36 ,  H04M3/5175 ,  H04M3/5233

摘要： In a work skill estimating device, an item information receiving unit receives, as item information, duration information of each dealing sequence in a customer call. A dealing duration estimating unit estimates a dealing duration of an item based on the item information received. A work skill estimating unit estimates an operator's work skill based on the dealing duration estimated. A skill map creating unit creates a skill map to comprehend the operator's work skill estimated.

摘要翻译： 在工作技能估计装置中，项目信息接收单元作为项目信息接收客户呼叫中的每个交易序列的持续时间信息。 交易持续时间估计单元基于接收的项目信息来估计项目的交易持续时间。 工作技能估计单元根据估计的交易持续时间来估计运营商的工作技能。 技能地图创建单元创建技能图以理解操作者的估计工作技能。

公开(公告)号：US20060210052A1

公开(公告)日：2006-09-21

申请号：US11189825

申请日：2005-07-27

申请人： Hideki Yamanaka ,  Takashi Yanase ,  Isao Namba

发明人： Hideki Yamanaka ,  Takashi Yanase ,  Isao Namba

IPC分类号： H04M3/00

CPC分类号： H04M3/5233 ,  H04M2201/14

摘要： A working skill estimating program is provided for estimating working skills of each agent in the state of separating a disturbance factor from response records (incidents). A large category classifier is supplied with the incidents within a predetermined time and classifies the incidents according to classification rules, for creating the topic-classified incidents. A small category generator collects the analogous incidents for each task type of the topic-classified incidents and generates a small category. A disturbance distinguisher distinguishes if the incidents belonging to each small category are common response records that appear regularly over time or disturbances whose frequency exhibits a significant time dependency. Then, a skill estimator estimates the working skills of each agent for each task type by using only common incidents determined as the common information.

摘要翻译： 提供了一个工作技能估算计划，用于估计每个代理人在将干扰因素与响应记录（事件）分开的状态下的工作技能。 在预定时间内提供大类分类器，并根据分类规则对事件进行分类，以创建主题分类事件。 小类别生成器针对主题分类事件的每个任务类型收集类似的事件，并生成一个小类别。 干扰辨别器区分属于每个小类别的事件是否是随着时间的推移而出现的常见的响应记录或其频率具有显着的时间依赖性的干扰。 然后，技能估算器仅使用被确定为公共信息的常见事件来估计每个任务类型的每个代理的工作技能。

公开(公告)号：US20080071609A1

公开(公告)日：2008-03-20

申请号：US11657637

申请日：2007-01-25

申请人： Takashi Yanase ,  Isao Namba

发明人： Takashi Yanase ,  Isao Namba

IPC分类号： G06Q10/00 ,  G06F19/00

CPC分类号： G06Q10/10 ,  G06Q10/06398

摘要： A basic work time corresponding to a work item received as case information is extracted from a basic work-time database. A standard work time generally required to process a case is computed. The standard work time is compared with an actual work time to evaluate work skill of each operator.

摘要翻译： 从基本工作时间数据库中提取与作为案例信息接收的工作项相对应的基本工作时间。 计算一般处理案件所需的标准工作时间。 标准工作时间与实际工作时间进行比较，以评估每个操作员的工作技能。

公开(公告)号：US20090030716A1

公开(公告)日：2009-01-29

申请号：US12043338

申请日：2008-03-06

申请人： Isao Namba

发明人： Isao Namba

IPC分类号： G06Q99/00

CPC分类号： G06Q10/10 ,  G06Q10/101

摘要： A recording medium including an order determining program, an order determining method, and an order determining apparatus. The order determining program causes an apparatus to calculate a total handling time by totaling a handling time corresponding to individual similar incidents. The order determining program also causes the apparatus to determine a knowledge creating order.

摘要翻译： 一种包括顺序确定程序，顺序确定方法和顺序确定装置的记录介质。 订单确定程序使装置通过总计对应于各个类似事件的处理时间来计算总处理时间。 订单确定程序还使装置确定知识创建顺序。

公开(公告)号：US07451139B2

公开(公告)日：2008-11-11

申请号：US10281318

申请日：2002-10-28

申请人： Isao Namba

发明人： Isao Namba

IPC分类号： G06F17/30

CPC分类号： G06F17/3069 ,  Y10S707/99931 ,  Y10S707/99935 ,  Y10S707/99936 ,  Y10S707/99945

摘要： An input section inputs a document set. A normalization section calculates a similarity as a relative value between documents, with respect to combinations of a plurality of documents, in the document set. The normalization section employs the tf·idf method. In tf·idf method, a document vector and a significance of a word included in the document is used to perform normalization to convert each similarity to an absolute value.

摘要翻译： 输入部分输入文档集。 规范化部分计算相对于文档中相对于多个文档的组合的文档之间的相对值。 归一化部分采用tf.idf方法。 在tf.idf方法中，文档矢量和包含在文档中的单词的重要性被用于执行归一化以将每个相似度转换为绝对值。

公开(公告)号：US20080040113A1

公开(公告)日：2008-02-14

申请号：US11648534

申请日：2007-01-03

申请人： Sachiko Onodera ,  Isao Namba

发明人： Sachiko Onodera ,  Isao Namba

IPC分类号： G10L15/04

CPC分类号： G10L15/00 ,  G10L2015/088

摘要： Speech keywords are extracted from voice data on a response that an operator has made to an inquiry from a customer while referring to case data. Response keywords to be responded to the inquiry are extracted from the case data. After detecting a common keyword in the speech and response keywords, a support keyword is extracted from the speech keywords that appears in the response at a time near the appearance of the common keyword and that does not match the response keywords. Auxiliary data is stored which includes case identification information uniquely identifying the case data, a customer level indicating a knowledge level of the customer about the inquiry, and the support keyword.

摘要翻译： 语音关键词是从语音数据中提取出的，在操作者对来自顾客的询问中作出的响应，同时参考案例数据。 从案例数据中提取响应关键字以响应查询。 在检测到语音和响应关键字中的公共关键字之后，从出现在公共关键字出现的那个时间内出现在与响应关键字不匹配的响应中的语音关键字中提取支持关键词。 存储辅助数据，其包括唯一地识别案例数据的案例识别信息，指示顾客关于查询的知识级别的客户级别和支持关键字。