WO2007135820A1 - Dispositif, procédé et logiciel de gestion de workflow - Google Patents

Dispositif, procédé et logiciel de gestion de workflow Download PDF

Info

Publication number
WO2007135820A1
WO2007135820A1 PCT/JP2007/058151 JP2007058151W WO2007135820A1 WO 2007135820 A1 WO2007135820 A1 WO 2007135820A1 JP 2007058151 W JP2007058151 W JP 2007058151W WO 2007135820 A1 WO2007135820 A1 WO 2007135820A1
Authority
WO
WIPO (PCT)
Prior art keywords
business flow
input
data
flow management
business
Prior art date
Application number
PCT/JP2007/058151
Other languages
English (en)
Japanese (ja)
Inventor
Kenji Satoh
Satoshi Nakazawa
Original Assignee
Nec Corporation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nec Corporation filed Critical Nec Corporation
Publication of WO2007135820A1 publication Critical patent/WO2007135820A1/fr

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Definitions

  • the present invention relates to a business flow management apparatus, method and program thereof, and more particularly, to a call center that manages a dialog by defining a business flow according to a procedure for handling an operator's customer.
  • the present invention relates to a business flow management apparatus, its method and program that enable efficient operator management and business flow management.
  • This conventional response management system includes a scenario storage unit, a statistical information storage unit, a click count storage unit, an elapsed time processing unit, a control unit, and a display color control unit.
  • Business flow management by a conventional reception management system having such a configuration operates as follows.
  • the scenario stored in the scenario storage unit is presented on the display device of the operator terminal that accepts the response, and the operator can easily distinguish between the current conversation, the next conversation, and the finished conversation according to each scenario. It is possible to grasp.
  • the operator performs a click operation to move to the next scenario, the number of clicks and elapsed time are automatically stored, and the scenario is analyzed based on the statistics of the number of clicks and the required time. This makes it possible to rewrite scenarios.
  • An object of the present invention is to provide a business flow management system that enables analysis of a business flow while concentrating on a conversation with a customer without placing a special work load on an operator.
  • Another object of the present invention is that the conversation deviates from the business flow when the business flow definition itself is incomplete or when the operator changes the order of the conversation depending on the content of the conversation with the customer. Even in such a case, it is possible to provide a business flow management system that enables a return to a business flow and analysis of the business flow, and enables a business flow administrator to extract a problem of the business flow definition. is there.
  • Still another object of the present invention is that the operator does not correctly grasp the scenario and is conducting an incorrect dialogue, or a lot of operators who are not defined in the business flow in the first place.
  • the present invention provides an input means for inputting data to be sent to a conversation partner, a storage means for storing a business flow, and a data input to the input means and a storage means.
  • Data processing means for managing the business flow using the business flow stored in the data flow, and the data input to the input means and the business flow stored in the storage means by the flow matching means of the data processing means. are automatically collated, and the position corresponding to the data input to the input means is determined among the dialog contents constituting the business flow.
  • the first object of the present invention is achieved by automatically collating the content of dialogue with the operator's customer and the business flow without forcing the operator to perform special terminal input work. be able to.
  • the data input to the input unit among the dialog contents constituting the business flow regardless of the connection information of the business flow transition stored in the storage unit.
  • the dialog is determined in the order of the flow of the business flow, and the content of the dialog is compared with the actual content of the dialog without assuming that the flow proceeds in the order of the flow of the business flow.
  • the second objective of can be achieved.
  • the data input to the input means does not correspond to any position of the dialogue contents constituting the business flow stored in the storage means, the data is Assuming that there is a dialog that is not defined in the business flow when collating the business flow with the actual conversation content, it is determined that it is outside the business flow.
  • the third objective can be achieved by making a determination.
  • the present invention has the following effects.
  • FIG. 1 is a block diagram showing a first embodiment of a business flow management system of the present invention.
  • FIG. 2 is a flowchart for explaining the operation of the business flow management system shown in FIG.
  • FIG. 3 is a block diagram showing a second embodiment of the business flow management system of the present invention.
  • FIG. 4 is a flowchart for explaining the operation of the business flow management system shown in FIG.
  • FIG. 5 is a block diagram showing a third embodiment of the business flow management system of the present invention.
  • FIG. 6 is a flowchart for explaining the operation of the business flow management system shown in FIG.
  • FIG. 7 is a block diagram showing a fourth embodiment of the business flow management system of the present invention.
  • FIG. 8 is a diagram showing a business flow stored in the business flow storage unit shown in FIGS. 1, 3, and 5.
  • FIG. 8 is a diagram showing a business flow stored in the business flow storage unit shown in FIGS. 1, 3, and 5.
  • FIG. 8 is a diagram showing a business flow stored in the business flow storage unit shown in FIGS. 1, 3, and 5.
  • FIG. 9 is a diagram showing the contents of dialogue between the operator and the customer in the first embodiment of the present invention.
  • FIG. 10 is a diagram showing stored contents stored in the collation history storage unit for the dialog contents shown in FIG.
  • FIG. 11 is a diagram showing the contents of dialogue between the operator and the customer in the second embodiment of the present invention.
  • FIG. 12 is a diagram showing the contents of dialogue between the operator and the customer in the third embodiment of the present invention.
  • FIG. 13 shows the contents stored in the collation history storage unit in the third embodiment of the present invention. It is a figure.
  • FIG. 1 is a block diagram showing a first embodiment of a business flow management system of the present invention.
  • an input device 1 such as a keyboard, a mouse, and a microphone
  • an output device 2 such as a display device and a printing device
  • a data processing device 3 that operates under program control
  • It consists of a storage device 4 such as a hard disk or memory for storing information.
  • the input device 1 is an external medium such as a telephone line interface device, a network interface device, and an external storage interface device in addition to a device that manually inputs data to the data processing device 3, such as a keyboard, a mouse, and a microphone. Includes a device for entering data from.
  • a voice recognition device converts voice into text data and is input as the conversation content.
  • the storage device 4 includes a business flow storage unit 41 and a verification history storage unit 42.
  • the business flow storage unit 41 stores a business flow including the content of the operator's dialogue and the flow of the operator that is preliminarily defined as to what should be asked to the customer.
  • the verification history storage unit 42 stores the determination result of the position in the business flow of the data input to the input device 1 as a verification history.
  • the data processing device 3 includes a flow collating unit 31, a collation history analyzing unit 32, and an analysis result displaying unit 33.
  • the flow collating means 31 automatically collates the data constituting the dialogue input to the input device 1 and the business flow stored in the business flow storage unit 41 of the storage device 4 and inputs the data to the input device 1. Determine where the data falls within the dialog content that makes up the business flow.
  • the verification history analysis means 32 analyzes the response problems of the operator, improvement points of the business flow, etc. from the many histories of the verification results of the business flow and the actual conversation contents stored in the verification history storage means 42. .
  • the analysis result display means 33 outputs the result analyzed by the matching history analysis means 32 to the output device 2. The operation of the business flow management system configured as described above will be described below.
  • FIG. 2 is a flow chart for explaining the operation of the business flow management system shown in FIG.
  • the current state of the dialogue flow as the workflow is stored in the workflow storage unit 41.
  • a state is set and the duration of the state is set to 0 (step Al).
  • an utterance which is data constituting a dialogue between the operator and the customer, is input via the input device 1 and stored in the flow matching means 31 (step A2).
  • the flow matching means 31 determines whether or not the input utterance is compatible with the current dialog flow state (step A3). Processing transitions to A6.
  • the input data is selected from the candidates for the next state of the dialog flow stored in the business flow storage unit 41.
  • the state that matches is selected, and the dialog flow state memory transitions to that state (step A4).
  • collation method for determining the conformity between the dialogue flow and the utterance a method for examining the degree of coincidence between the explanatory text of the state given to each state of the workflow and the word of the dialogue content, A keyword list that is spoken in that state is assigned to each state of the business flow, and the degree of coincidence between the keyword list and the word of the utterance content is checked, and each state of the business flow is collated in the past.
  • the duration time of the state after the transition is set to 0 (step A5), and the dialogue flow in which the utterance time of the corresponding new utterance is the current state It is added to the state duration (step A6).
  • step A7 it is determined whether or not the dialog has ended. If not, the process from step A2 is repeated. If the dialog has ended, the dialog with the call ID 'operator name is finally included.
  • the duration of each state of the flow is the verification history storage 4 as the verification history 4
  • the data is stored in 2 and the processing ends (step A8).
  • the data processing device 3 the data input to the input device 1 using the current position in the business flow and the connection information of the business flow transition stored in the business flow storage unit 41.
  • the position of the dialogue content that constitutes the business flow is determined.
  • the speech flow that is data input from the input device 1 is automatically collated with the business flow stored in the business flow storage unit 41.
  • FIG. 3 is a block diagram showing a second embodiment of the business flow management system of the present invention.
  • the data processing device 5 performs arbitrary collation with respect to the first embodiment shown in FIG. It is different in that it has a flow arbitrary state matching means 54 as means.
  • the flow arbitrary state matching means 54 does not depend on the connection information of the transition of the business flow stored in the business flow storage unit 41, and the position of the dialogue content that constitutes the business flow where the data input to the input device 1 is located. Determine if it applies.
  • FIG. 4 is a flow chart for explaining the operation of the business flow management system shown in FIG.
  • the flow arbitrary state collating means 54 inputs the input state from all the flow states stored in the business flow storage unit 41 to the input device 1. Transition to the state that best fits the data (step A10).
  • the data input to the input device 1 is stored in the business flow storage unit 41 regardless of the business flow transition connection information. It is determined which position corresponds to the dialogue contents that make up the flow.
  • FIG. 5 is a block diagram showing a third embodiment of the business flow management system of the present invention.
  • this embodiment is different from the second embodiment shown in FIG. 3 in that the data processing device 6 is out of the flow in addition to the configuration of the data processing device 5 shown in FIG. It differs in that it has a dialogue recognition means 65. If the data input to the input device 1 does not correspond to any position of the dialog contents constituting the business flow stored in the business flow storage unit 41, the out-of-flow dialog authorization means 65 It is determined that
  • FIG. 6 is a flow chart for explaining the operation of the business flow management system shown in FIG.
  • the input is input to the input device 1 from all the flow states stored in the business flow storage unit 41.
  • the utterance content that is the data input to the input device 1 does not match the next flow state candidate, it is input within all flow states. It is checked whether or not there is a state that matches the utterance content that is the data input to device 1 (step All). As a new state is created and transitions to that state (Step A12).
  • collation is performed using the degree of coincidence between words in the explanation text, keyword list, or past utterance contents, etc., and words in the utterance contents.
  • there is a method that incorporates a judgment rule for the state outside the business flow when writing and collating the judgment rule for judging whether it is in the business flow state and various methods can be considered. Any method may be adopted in the invention.
  • FIG. 7 is a block diagram showing a fourth embodiment of the business flow management system of the present invention.
  • this embodiment includes an input processing device 1, an output device 2, a storage device 4, and a data processing device 7, as in the first to third embodiments described above.
  • the business flow management program 8 is read into the data processing device 7 and controls the operation of the data processing device 7, and generates a business flow storage unit 41 and a verification history storage unit 42 in the storage device 4.
  • the data processing device 7 executes the same processing as the processing by the data processing devices 3, 5, 6 in the first to third embodiments under the control of the business flow management program 8.
  • FIG. 8 is a diagram showing a business flow stored in the business flow storage unit 41 shown in FIGS. 1, 3, and 5. The embodiment will be described by taking the case where the business flow shown in FIG. 8 is stored in the business flow storage unit 41 as an example.
  • This example corresponds to the first embodiment.
  • FIG. 9 is a diagram showing the contents of dialogue between the operator and the customer in the first embodiment of the present invention.
  • the business flow storage unit 41 preferentially stores the business flow definition shown in FIG. In this case, the case where the dialogue shown in Fig. 9 is performed between the operator and the customer will be described as an example.
  • the state duration of the state is set to 0 in the state B1 shown in FIG. Is done.
  • the dialogue is started from C1 shown in FIG. 9, it is checked whether the utterance content of C1 constituting the dialogue matches the state of B1.
  • FIG. 10 is a diagram showing the storage contents stored in the collation history storage unit 42 for the conversation contents shown in FIG.
  • the matching history analysis means 32 from the matching history in which a large amount of data as shown in FIG. 10 is stored, for example, “When focusing on a specific person, the duration is By analyzing the “different flow states”, it becomes possible to discover the tendency and problems of the person who has focused on it. Similarly, for example, “a flow state that is rarely used or a flow state that is extremely short in duration compared to other states” or “a flow state that is extremely long in duration compared to other states” is extracted. ”Can be discovered when there is a problem in the business flow itself.
  • This example corresponds to the second embodiment.
  • FIG. 11 is a diagram showing the contents of dialogue between the operator and the customer in the second embodiment of the present invention.
  • the business flow storage unit 41 preliminarily stores the business flow definition shown in FIG. In this case, the case where the dialogue shown in FIG. 11 is performed between the operator and the customer will be described as an example.
  • the dialogue in Fig. 11 is different from the dialogue in Fig. 9 in the first embodiment in that the user number is voluntarily spoken in the utterance number C13 without being prompted by the user.
  • the confirmation of member ID B4 can only be made after confirmation of full name B3.
  • customers do not always speak in the order of their business flows.
  • the customer spoke the member ID first at C13.
  • the operator reversed the order of checking the member ID and first and last name on a case-by-case basis. Asking customers for their first and last names.
  • step A3 in FIG. 4 the next flow state candidates are B2 and B3 shown in Fig. 8, but the dialogue of C13 does not conform to these two states.
  • the process moves to step A10, and the flow arbitrary state matching means 54 shown in FIG. 3 searches for a state in which all the flow state forces of the work flow most closely match the utterance, and transitions to state B4.
  • the process shifts to step A10.
  • the process shifts to the B3 state.
  • the verification history analysis means 32 of the first embodiment Similar to the explanation, the business flow can be analyzed.
  • This example corresponds to the third embodiment.
  • FIG. 12 is a diagram showing the contents of dialogue between the operator and the customer in the third embodiment of the present invention.
  • the business flow storage unit 41 preferentially stores the business flow definition shown in FIG. At this time, the case where the dialogue shown in FIG. 12 is performed between the operator and the customer will be described as an example.
  • the dialog in FIG. 12 differs from the dialog in FIG. 11 in the second embodiment in that the user is asked for his / her name in utterance number C 24 and ignores the operator's question. It is a point that brings up a completely new topic as defined in the business flow.
  • step A10 shown in FIG. It has become.
  • customers do not always speak what is defined in the business flow.
  • the customer may want to confirm something in a hurry, ignoring the operator's question at C23 and asking his new question at C24. It is often seen in actual call center reception that a customer speaks as defined in such a business flow.
  • the collation history processed in this way is stored in the collation history storage unit 42 after the end of this dialogue.
  • FIG. 13 is a diagram showing storage contents stored in the matching history storage unit 42 in the third embodiment of the present invention.
  • the matching history analysis means 62 from a large amount of matching histories including those shown in FIG. 13, for example, only the newly created state is targeted, and what word is included in the utterance content. By analyzing whether it is used a lot, etc., it becomes possible to grasp the "topics that are not defined in the business flow but are often brought up by customers recently", and to include the response to those topics. It becomes possible to review the flow.
  • the present invention can be applied to the business flow analysis for the business of a call center operator who responds to a customer through telephone, electronic mail, chat, or the like. It can also be applied to the analysis of the business flow of the reception staff at the store counter that directly interacts with customers.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Selon la présente invention, l'entrée provenant d'un dispositif d'entrée (1) et un workflow (flux de travaux) stocké dans une section de stockage de workflow (41) sont automatiquement contrôlés par un moyen de contrôle de flux (31) et le résultat du contrôle est intégré dans une section regroupant l'historique des contrôles (42). L'analyse d'une grande quantité de résultats intégrés dans une section d'analyse d'historique de contrôles (32) permet de détecter une tendance ou un problème chez un opérateur ou de détecter un problème pouvant faire partie de la définition du workflow lui-même.
PCT/JP2007/058151 2006-05-19 2007-04-13 Dispositif, procédé et logiciel de gestion de workflow WO2007135820A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2006140120 2006-05-19
JP2006-140120 2006-05-19

Publications (1)

Publication Number Publication Date
WO2007135820A1 true WO2007135820A1 (fr) 2007-11-29

Family

ID=38723132

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2007/058151 WO2007135820A1 (fr) 2006-05-19 2007-04-13 Dispositif, procédé et logiciel de gestion de workflow

Country Status (1)

Country Link
WO (1) WO2007135820A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010134233A (ja) * 2008-12-05 2010-06-17 Fujitsu Ltd 対話選別プログラム、対話選別装置、および対話選別方法
JP2011515028A (ja) * 2007-12-28 2011-05-12 ジェネシス・テレコミュニケーションズ・ラボラトリーズ・インコーポレーテッド 再帰的な適応的インタラクション管理システム
JP2013029868A (ja) * 2012-11-05 2013-02-07 Fujitsu Ltd 対話選別プログラム、対話選別装置、および対話選別方法
JP2016076788A (ja) * 2014-10-03 2016-05-12 みずほ情報総研株式会社 通話評価システム、通話評価方法及び通話評価プログラム
CN108600561A (zh) * 2018-05-10 2018-09-28 上海二六三通信有限公司 一种通信管理系统
US10733555B1 (en) * 2014-03-14 2020-08-04 Walmart Apollo, Llc Workflow coordinator

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002118660A (ja) * 2000-10-06 2002-04-19 Landscape:Kk コールセンタシステム
JP2004212802A (ja) * 2003-01-07 2004-07-29 Fujitsu Ltd 対話情報処理システム
WO2004081701A2 (fr) * 2003-03-11 2004-09-23 Philips Intellectual Property & Standards Gmbh Procede, systeme et generateur de script pour l'acheminement de dialogues guides par script entre l'operateur d'un centre d'appel et un client

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002118660A (ja) * 2000-10-06 2002-04-19 Landscape:Kk コールセンタシステム
JP2004212802A (ja) * 2003-01-07 2004-07-29 Fujitsu Ltd 対話情報処理システム
WO2004081701A2 (fr) * 2003-03-11 2004-09-23 Philips Intellectual Property & Standards Gmbh Procede, systeme et generateur de script pour l'acheminement de dialogues guides par script entre l'operateur d'un centre d'appel et un client

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011515028A (ja) * 2007-12-28 2011-05-12 ジェネシス・テレコミュニケーションズ・ラボラトリーズ・インコーポレーテッド 再帰的な適応的インタラクション管理システム
JP2010134233A (ja) * 2008-12-05 2010-06-17 Fujitsu Ltd 対話選別プログラム、対話選別装置、および対話選別方法
JP2013029868A (ja) * 2012-11-05 2013-02-07 Fujitsu Ltd 対話選別プログラム、対話選別装置、および対話選別方法
US10733555B1 (en) * 2014-03-14 2020-08-04 Walmart Apollo, Llc Workflow coordinator
JP2016076788A (ja) * 2014-10-03 2016-05-12 みずほ情報総研株式会社 通話評価システム、通話評価方法及び通話評価プログラム
CN108600561A (zh) * 2018-05-10 2018-09-28 上海二六三通信有限公司 一种通信管理系统

Similar Documents

Publication Publication Date Title
KR102151681B1 (ko) 언어 모델용 대화 상태들 결정
US8311824B2 (en) Methods and apparatus for language identification
US20060287868A1 (en) Dialog system
US11551692B2 (en) Digital assistant
US20060004570A1 (en) Transcribing speech data with dialog context and/or recognition alternative information
US7907705B1 (en) Speech to text for assisted form completion
US7318031B2 (en) Apparatus, system and method for providing speech recognition assist in call handover
KR102431754B1 (ko) 인공지능기반 상담지원장치
US20070239458A1 (en) Automatic identification of timing problems from speech data
WO2007135820A1 (fr) Dispositif, procédé et logiciel de gestion de workflow
JP5576113B2 (ja) 音声認識システムにモデルを適合させるための方法およびシステム
US20070154006A1 (en) Apparatus and method for determining part of elicitation from spoken dialogue data
US20050234720A1 (en) Voice application system
KR20080024752A (ko) 채팅 에이전트를 위한 대화 관리 장치 및 그 방법
CN110287318B (zh) 业务操作的检测方法及装置、存储介质、电子装置
CN112468665A (zh) 一种会议纪要的生成方法、装置、设备及存储介质
JP5195369B2 (ja) 対話選別プログラム、対話選別装置、および対話選別方法
KR20190065194A (ko) 회의록 열람 문서 생성 방법 및 그 장치
JP3933813B2 (ja) 音声対話装置
JP2001100787A (ja) 音声対話システム
US8051026B2 (en) Rules collector system and method with user interaction
CN114155845A (zh) 服务确定方法、装置、电子设备及存储介质
CN114202363A (zh) 基于人工智能的话术调用方法、装置、计算机设备及介质
JP6781492B2 (ja) 音声解析システム
US11625152B1 (en) Automated workflow selection for agent within an electronic conversation system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07741587

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 07741587

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP