시작
Kore.ai 대화형 플랫폼
챗봇 개요
자연어 처리(NLP)
봇 개념 및 용어들
빠른 시작 가이드
봇 빌더 접근 방법
사용 고지 사항 (영어)
Kore.ai 봇 빌더로 작업하기
봇 구축 시작하기
릴리스 정보
현재 버전 (영어)
이전 버전 (영어)

개념
디자인
스토리보드
대화 작업
개요
Using the Dialog Builder Tool
노드 유형
사용자 의도 노드
대화 노드
엔티티 노드
양식 노드
확인 노드
서비스 노드
봇 조치 노드
Service Node
WebHook 노드
스크립트 노드
노드 그룹화하기
Agent Transfer Node
사용자 프롬프트
음성 통화 속성
대화 관리
노드 및 전환
구성 요소 전환
컨텍스트 개체
이벤트 기반 봇 조치
지식 그래프
소개
지식 추출
지식 그래프 생성
봇에 지식 그래프 추가
그래프 생성
지식 그래프 작성
FAQ 추가
작업 실행
기존 소스에서 FAQ 구축
특성, 동의어 및 불용어
변수 네임스페이스 관리
수정
용어 편집 및 삭제
용어 편집 및 삭제
질문과 응답 편집
Knowledge Graph Training
지식 그래프 분석
봇 온톨로지 가져오기 및 내보내기
지식 그래프 가져오기
지식 그래프 내보내기
지식 그래프 생성
CSV 파일에서
JSON 파일
지식 그래프 생성
경고 작업
스몰 토크
Digital Skills
디지털 양식
Views
Digital Views
Panels
Widgets
기차
봇 성능 향상 – NLP 최적화
기계 학습
소개
모델 검증
기초 의미
지식 그래프 학습
특성
순위 및 해결
고급 NLP 설정
NLP 설정 및 지침
봇 인텔리전스
소개
컨텍스트 관리
컨텍스트 관리
대화 관리
다중 – 의도 탐지
엔티티 수정
기본 대화
정서 관리
어조 분석
Test & Debug
봇과 대화
발화 테스트
배치 테스트하기
대화 테스트
배포
채널 활성화
봇 게시
분석
봇 분석하기
Conversations Dashboard
Performance Dashboard
사용자 정의 대시보드
소개
맞춤형 메타 태그
사용자 정의 대시보드 생성 방법
Conversation Flows
NLP 지표
Containment Metrics
사용량 지표
스마트 봇
소개
범용 봇
소개
범용 봇 정의
범용 봇 생성
범용 봇 학습
범용 봇 커스터마이징
범용 봇용 추가 언어 활성화
스토어
Manage Assistant
플랜 및 사용량
Overview
Usage Plans
Support Plans
플랜 관리
봇 인증
다국어 봇
개인 식별 정보 삭제하기
봇 변수 사용
IVR 통합
일반 설정
봇 관리

방법
간단한 봇 생성하기
Design Conversation Skills
뱅킹 봇 생성
뱅킹 봇 – 자금 이체
뱅킹 봇 – 잔액 업데이트
Knowledge Graph (KG) 구축
스마트 경고를 예약하는 방법
Design Digital Skills
디지털 양식 설정 방법
디지털 보기 설정 방법
데이터 테이블에 데이터를 추가하는 방법
데이터 테이블 내 데이터 업데이트 방법
UI 양식에서 데이터 테이블에 데이터를 추가하는 방법
Train the Assistant
특성 사용 방법
의도와 엔티티에 대한 패턴 사용 방법
컨텍스트 전환 관리 방법
Deploy the Assistant
상담사 전환을 설정하는 방법
봇 기능 사용 방법
콘텐츠 변수 사용 방법
전역 변수 사용 방법
Kore.ai 웹 SDK 튜토리얼
Kore.ai 위젯 SDK 튜토리얼
Analyze the Assistant
사용자 정의 대시보드 생성 방법
사용자 지정 태그를 사용하여 봇 메트릭을 필터링하는 방법

API 및 SDK
API 참조
Kore.ai API 사용
API 목록
API 컬렉션
koreUtil Libraries
SDK 참조
상담사 전환을 설정하는 방법
봇 기능 사용 방법
콘텐츠 변수 사용 방법
전역 변수 사용 방법
소개
Kore.ai 웹 SDK 튜토리얼
Kore.ai 위젯 SDK 튜토리얼

관리
소개
봇 관리자 콘솔
대시보드
사용자 관리
사용자 관리
그룹 관리
역할 관리
봇 관리 모듈
등록
사용자 초대
사용자 등록을 위한 대량 초대 보내기
사용자 및 사용자 데이터 가져오기
Active Directory에서 사용자 동기화
보안 및 준수
싱글 사인 온 사용
보안 설정
Kore.ai 커넥터
봇 관리자용 분석
Billing (지원하지 않음)
  1. Docs
  2. Virtual Assistants
  3. Bot Settings
  4. Feedback Survey

Feedback Survey

The Kore.ai XO Platform allows you to design and create feedback surveys for products, services, and overall experiences using out-of-the-box templates on the web and mobile channels. You can configure a Virtual Assistant to launch these surveys at a certain point in a conversation or at the end of a conversation (when the end of conversation event is triggered). The NPS, CSAT, and Like/Dislike survey types are currently supported.

Key Feature Highlights

  1. The Feedback Module is use-case and channel-agnostic. But by default, it only shows text messages. You can always add additional channel-specific prompts to collect feedback from voice channels.
  2. When a feedback survey is created on the platform, all messages are in text format. The text from the platform gets converted into a voice using the ASR and TTS engines.
  3. You can leverage channel-specific configuration to modify the feedback prompts.
  4. Feedback flows are fully customizable.
  5. The Kore.ai XO Platform lets you configure feedback in two ways:
  • Using the built-in flows to collect the feedback and the new service type called feedback service to submit the feedback to the bots platform.
  • Collecting feedback from other sources that can be pushed to the platform as part of the conversation execution.
  1. Feedback Surveys get created as dialog tasks with a series of entities, service calls, and message notes. You have complete control of modifying the out-of-the-box messages, adding additional messages to specific channels, such as voice channels, and capturing the feedback on voice.
  2. You can use the automatic feedback template that the platform generates or build their flows and submit the feedback to the platform feedback service. Alternatively, it could be a hybrid approach where the feedback flow can emerge from or integrate with another flow.
  3. Once a customer responds to a Feedback Survey, the event displays on the chat transcript slider of the Conversations History Dashboard. Learn more.
  4. Additionally, you can filter and analyze Conversations (with feedback survey enabled) based on the Feedback Type, Response, and Score using prebuilt and custom filters. Learn more.
  5. The feedback response from a customer is captured and pushed to the platform for further analysis in three ways:
  • By creating a Dialog to capture feedback responses/scores and generate the required analytics to derive actionable insights on the Feedback Analysis Dashboard. Learn more.
  • By pushing feedback data to the platform using the Public API. Learn more.
  • By pushing feedback data via the Botkit. Learn more.
  1. In addition to the primary survey question, you can configure a Follow-up Question for negative feedback to gather specific details and better understand any primary survey issues.
  2. Additionally, you can set an Acknowledgement Message to customers after they complete the survey to show appreciation and let them know that it has been received.

Navigating to Feedback Survey

To navigate to the Feedback Survey feature, follow the steps below:

  1. On the Bot Builder, click the Build tab.
  2. Navigate to Configurations > Feedback Survey on the left navigation menu.

Feedback Template Types

The Platform provides the following in-built feedback template types, to create and define a feedback survey:

NPS Scale Categorization

Known as New Promoter Score, this is a standard customer experience metric that measures the experience and loyalty of customers based on their feedback response. For a single-question survey, respondents give a rating between 0 (not at all likely) and 10 (extremely likely), and based on their response, they fall into one of the following NPS score categories:

Customer Category NPS Score Description
Promoters 9 & 10 This score indicates a loyal customer who is satisfied with the conversation and is highly likely to return.
Passives 6,7, & 8 This score represents a satisfied customer who may or may not be willing to continue the conversation and return for a service.
Detractors 0,1,2,3,4, & 5 This score indicates that the customer is unsatisfied with the conversation and has given negative feedback. As a result, the customer will mostly not return to the platform and may detract other customers by sharing their experiences.

CSAT Score Categorization

CSAT or Customer SATisfaction is a customer experience metric that measures or quantifies how happy the customer is with a Virtual Assistant interaction. The customer is asked to rate on a five-point scale, 1 meaning very satisfied and 5 meaning very unsatisfied, for a survey question like “How satisfied were you with the conversation?” The response score is mapped to the relevant category as shown below:

Category Score
Very Satisfied 1
Satisfied 2
Neutral 3
Unsatisfied 4
Very Unsatisfied 5

 

Like/Dislike

The customer is asked to respond to the feedback survey by clicking a Like or Dislike icon. Like or Extremely Likely denotes the customer’s positive experience and is allocated a score of 1 internally. Dislike or Extremely Unlikely indicates a negative customer experience, and is allocated a score of 0 internally.

Feedback Survey Creation and Definition

To create a Feedback Survey on the Bot Builder, follow the steps below:

  1. Navigate to Build > Configurations > Feedback Survey.
  2. If this is your first feedback survey, click Add Feedback on the Feedback Survey screen.
  3. Otherwise, click New Survey.

  4. In the Add Feedback Survey window, define the survey details and design, and launch the survey to be visible to customers.

The Feedback Survey definition and design flow steps are given below:

Step 1: Define the Survey Details

In this section, you can define a survey name and the type you want to use. To define the survey details, follow the steps below:

  1. Enter the Survey Name in the relevant text area.
  2. Select the Survey Type as either NPS, CSAT, or Like/Dislike. Based on your selection, the survey definition changes.
  3. Click Next to move to the next step.

Step 2: Define the Survey Design

You can define how to present the survey in the Survey Design stage which includes the following:

  • Gathering the customer’s feedback using one of the out-of-the-box default templates.
  • Defining the primary question that will be posed to the customer when the system triggers the feedback survey.
  • Setting the follow-up questions based on the feedback conditionally.

To define the survey design, follow the steps below:

  1. Select the relevant option in the Add Feedback Survey window based on how you want to create the survey.
  2. If you want to create a new Feedback Survey along with a Dialog Task (customizable) which will have the flow required to collect the feedback and capture the analytics, select Create a survey with a New Dialog and follow the steps below:
  • Enter the Dialog Name in the text area.
  • Set the default Primary Question to be posed to the customer for the selected survey type when it’s triggered.
  • Alternatively, modify/change the Primary Question in the text area.
  • The Primary Question response options the customer will see are displayed below based on the selected survey type:

NPS

CSAT

Like/Dislike

Note: The default response names provided for CSAT and the Like/Dislike types are editable; however, the scores set in the system cannot be changed for any survey type.

  1. To create your flow, select Create survey without Dialog and click Next
  2. Optional Step: To capture additional details from the customer for a negative feedback, configure the follow-up question with the steps below:
  • Enable the Follow-up Question option (default setting).
  • Define when to post the follow-up question by configuring the IF condition, where you must select the conditional option from the list for User Score.
  • Next, increment or decrement the feedback score counter for the selected condition to set the validation criterion.
  • Either edit the default follow-up question in the text area provided for the THEN clause or keep it unchanged.
  1. Modify the Acknowledgement Message in the text area or retain the default message to acknowledge the customer’s effort in taking the survey.
  2. Click Next to move to survey launch configuration.

Step 3: Define Launch Configuration

After defining the survey, you can choose how and when to launch the survey in one of the following ways with the Launch Configuration:

  1. Associate the survey with the end-of-task (conversation) event.
  2. Add the survey task as a sub-dialog to other primary tasks.

To configure the feedback survey launch, follow the steps below:

  1. Select one of the following options:
  • Launch after End of Task: The dialog task is considered as the ‘End of Task‘ event, and the survey is triggered at the end of every conversation. When selected, End of Task (End of Conversation Event) under Intelligence > Events > End Of Task will be overridden and the feedback survey is launched. Through the survey dialog you’ve created in the previous step.
  • I will decide how to launch the Survey: You can manually initiate the feedback survey at any time by using the associated dialog task in the Kore.ai XO platform. A dialog task will be made available under Build → Conversational Skills. This allows you to control when the survey is launched and gather feedback at your own convenience.
  1. Click Create to launch the feedback survey.

A success confirmation message, as shown below, is displayed with your survey details.

Feedback Survey Dialog Flow

After you’ve created the survey, you can view the built-in survey flow as a dialog task under Build > Conversational Skills > Dialog Tasks on the left menu.

The Task Flow will include a combination of Entity, Message, and Service nodes to represent the survey flow.

You can customize the dialog flow as per your need by changing the dialog flow definition fields.

Important

  • Feedback Service is introduced as the new Service Type option under General Settings. You can use this service to submit feedback on the surveys you may have captured using your custom flows.
  • You can invoke feedback as a sub-dialog from any other point in the conversation where you would like to capture the feedback.

Feedback Survey

The Kore.ai XO Platform allows you to design and create feedback surveys for products, services, and overall experiences using out-of-the-box templates on the web and mobile channels. You can configure a Virtual Assistant to launch these surveys at a certain point in a conversation or at the end of a conversation (when the end of conversation event is triggered). The NPS, CSAT, and Like/Dislike survey types are currently supported.

Key Feature Highlights

  1. The Feedback Module is use-case and channel-agnostic. But by default, it only shows text messages. You can always add additional channel-specific prompts to collect feedback from voice channels.
  2. When a feedback survey is created on the platform, all messages are in text format. The text from the platform gets converted into a voice using the ASR and TTS engines.
  3. You can leverage channel-specific configuration to modify the feedback prompts.
  4. Feedback flows are fully customizable.
  5. The Kore.ai XO Platform lets you configure feedback in two ways:
  • Using the built-in flows to collect the feedback and the new service type called feedback service to submit the feedback to the bots platform.
  • Collecting feedback from other sources that can be pushed to the platform as part of the conversation execution.
  1. Feedback Surveys get created as dialog tasks with a series of entities, service calls, and message notes. You have complete control of modifying the out-of-the-box messages, adding additional messages to specific channels, such as voice channels, and capturing the feedback on voice.
  2. You can use the automatic feedback template that the platform generates or build their flows and submit the feedback to the platform feedback service. Alternatively, it could be a hybrid approach where the feedback flow can emerge from or integrate with another flow.
  3. Once a customer responds to a Feedback Survey, the event displays on the chat transcript slider of the Conversations History Dashboard. Learn more.
  4. Additionally, you can filter and analyze Conversations (with feedback survey enabled) based on the Feedback Type, Response, and Score using prebuilt and custom filters. Learn more.
  5. The feedback response from a customer is captured and pushed to the platform for further analysis in three ways:
  • By creating a Dialog to capture feedback responses/scores and generate the required analytics to derive actionable insights on the Feedback Analysis Dashboard. Learn more.
  • By pushing feedback data to the platform using the Public API. Learn more.
  • By pushing feedback data via the Botkit. Learn more.
  1. In addition to the primary survey question, you can configure a Follow-up Question for negative feedback to gather specific details and better understand any primary survey issues.
  2. Additionally, you can set an Acknowledgement Message to customers after they complete the survey to show appreciation and let them know that it has been received.

Navigating to Feedback Survey

To navigate to the Feedback Survey feature, follow the steps below:

  1. On the Bot Builder, click the Build tab.
  2. Navigate to Configurations > Feedback Survey on the left navigation menu.

Feedback Template Types

The Platform provides the following in-built feedback template types, to create and define a feedback survey:

NPS Scale Categorization

Known as New Promoter Score, this is a standard customer experience metric that measures the experience and loyalty of customers based on their feedback response. For a single-question survey, respondents give a rating between 0 (not at all likely) and 10 (extremely likely), and based on their response, they fall into one of the following NPS score categories:

Customer Category NPS Score Description
Promoters 9 & 10 This score indicates a loyal customer who is satisfied with the conversation and is highly likely to return.
Passives 6,7, & 8 This score represents a satisfied customer who may or may not be willing to continue the conversation and return for a service.
Detractors 0,1,2,3,4, & 5 This score indicates that the customer is unsatisfied with the conversation and has given negative feedback. As a result, the customer will mostly not return to the platform and may detract other customers by sharing their experiences.

CSAT Score Categorization

CSAT or Customer SATisfaction is a customer experience metric that measures or quantifies how happy the customer is with a Virtual Assistant interaction. The customer is asked to rate on a five-point scale, 1 meaning very satisfied and 5 meaning very unsatisfied, for a survey question like “How satisfied were you with the conversation?” The response score is mapped to the relevant category as shown below:

Category Score
Very Satisfied 1
Satisfied 2
Neutral 3
Unsatisfied 4
Very Unsatisfied 5

 

Like/Dislike

The customer is asked to respond to the feedback survey by clicking a Like or Dislike icon. Like or Extremely Likely denotes the customer’s positive experience and is allocated a score of 1 internally. Dislike or Extremely Unlikely indicates a negative customer experience, and is allocated a score of 0 internally.

Feedback Survey Creation and Definition

To create a Feedback Survey on the Bot Builder, follow the steps below:

  1. Navigate to Build > Configurations > Feedback Survey.
  2. If this is your first feedback survey, click Add Feedback on the Feedback Survey screen.
  3. Otherwise, click New Survey.

  4. In the Add Feedback Survey window, define the survey details and design, and launch the survey to be visible to customers.

The Feedback Survey definition and design flow steps are given below:

Step 1: Define the Survey Details

In this section, you can define a survey name and the type you want to use. To define the survey details, follow the steps below:

  1. Enter the Survey Name in the relevant text area.
  2. Select the Survey Type as either NPS, CSAT, or Like/Dislike. Based on your selection, the survey definition changes.
  3. Click Next to move to the next step.

Step 2: Define the Survey Design

You can define how to present the survey in the Survey Design stage which includes the following:

  • Gathering the customer’s feedback using one of the out-of-the-box default templates.
  • Defining the primary question that will be posed to the customer when the system triggers the feedback survey.
  • Setting the follow-up questions based on the feedback conditionally.

To define the survey design, follow the steps below:

  1. Select the relevant option in the Add Feedback Survey window based on how you want to create the survey.
  2. If you want to create a new Feedback Survey along with a Dialog Task (customizable) which will have the flow required to collect the feedback and capture the analytics, select Create a survey with a New Dialog and follow the steps below:
  • Enter the Dialog Name in the text area.
  • Set the default Primary Question to be posed to the customer for the selected survey type when it’s triggered.
  • Alternatively, modify/change the Primary Question in the text area.
  • The Primary Question response options the customer will see are displayed below based on the selected survey type:

NPS

CSAT

Like/Dislike

Note: The default response names provided for CSAT and the Like/Dislike types are editable; however, the scores set in the system cannot be changed for any survey type.

  1. To create your flow, select Create survey without Dialog and click Next
  2. Optional Step: To capture additional details from the customer for a negative feedback, configure the follow-up question with the steps below:
  • Enable the Follow-up Question option (default setting).
  • Define when to post the follow-up question by configuring the IF condition, where you must select the conditional option from the list for User Score.
  • Next, increment or decrement the feedback score counter for the selected condition to set the validation criterion.
  • Either edit the default follow-up question in the text area provided for the THEN clause or keep it unchanged.
  1. Modify the Acknowledgement Message in the text area or retain the default message to acknowledge the customer’s effort in taking the survey.
  2. Click Next to move to survey launch configuration.

Step 3: Define Launch Configuration

After defining the survey, you can choose how and when to launch the survey in one of the following ways with the Launch Configuration:

  1. Associate the survey with the end-of-task (conversation) event.
  2. Add the survey task as a sub-dialog to other primary tasks.

To configure the feedback survey launch, follow the steps below:

  1. Select one of the following options:
  • Launch after End of Task: The dialog task is considered as the ‘End of Task‘ event, and the survey is triggered at the end of every conversation. When selected, End of Task (End of Conversation Event) under Intelligence > Events > End Of Task will be overridden and the feedback survey is launched. Through the survey dialog you’ve created in the previous step.
  • I will decide how to launch the Survey: You can manually initiate the feedback survey at any time by using the associated dialog task in the Kore.ai XO platform. A dialog task will be made available under Build → Conversational Skills. This allows you to control when the survey is launched and gather feedback at your own convenience.
  1. Click Create to launch the feedback survey.

A success confirmation message, as shown below, is displayed with your survey details.

Feedback Survey Dialog Flow

After you’ve created the survey, you can view the built-in survey flow as a dialog task under Build > Conversational Skills > Dialog Tasks on the left menu.

The Task Flow will include a combination of Entity, Message, and Service nodes to represent the survey flow.

You can customize the dialog flow as per your need by changing the dialog flow definition fields.

Important

  • Feedback Service is introduced as the new Service Type option under General Settings. You can use this service to submit feedback on the surveys you may have captured using your custom flows.
  • You can invoke feedback as a sub-dialog from any other point in the conversation where you would like to capture the feedback.
메뉴