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. Test your Bot
  4. Test Case Execution Summary

Test Case Execution Summary

The Test Case Execution Summary allows you to view the test case results, identify the failed test cases, and resolve the flow of the virtual assistant. It gives complete details of the overall test results and the defects found.

The following sections explain the options available on the Conversation Testing to execute the test cases and interpret the results, which help analyze the performance of the test suite as a whole and the individual test cases.

Test Case Execution

You can execute test cases on the Conversation Testing Landing Page and the individual Test Case details page.
Follow these steps for test execution:

  1. On the Test Suite Details page, select the test suite and then click the Run Test Suite button for that specific suite.

    Note: You can also execute the test cases by clicking the Run Test button on the Test Suite Details page.

  2. Choose the Version of the VA you want to test.
    Note: Ensure that you have valid authorization tokens for the VA to make the service calls that would be part of the test suite.

  3. You can monitor the progress of the test suite in the Result column and the status docker. The Result column displays the Passed or Failed status upon successful execution.

When a test case is executed, the test case result is determined with the features like assertions, dynamic texts, OneOf, and so on. To know more, see Test Case Assertion.

The platform simulates all the user inputs against the current VA definition in sequence, as available in the test case. For every user input, the VA’s responses are captured along with the metadata. See Capture Test Suite Metadata under Validate Test Suite to know more.

Test Assertions Execution

The platform performs the assertions tagged to each VA response of a test case. For example, a VA’s response can have Flow, Text, and Context Assertions tagged. The platform performs all three assertions to determine their assertion results.

Flow Assertion

  • For any VA response in a test case, the assertion is determined as pass when the following conditions are true:
    • The Intent ID of the Expected and Actual responses is the same.
    • The Node ID of the Expected and Actual responses is the same.
    • The Transition(s) of the Expected and Actual responses are the same.
    • The Prompt type (Error or User Prompt) is the same in case of Entity nodes.
  • If the above conditions are not met, the assertion is determined as Failed.

Text Assertion

  • For any VA response in a test case, the assertion is determined as passed when the following condition is true:
    • The expected and actual responses are the same (string comparison).
  • Dynamic text values are not considered when performing the comparison.
  • In case of multiple responses in the Expected Output (when a node has multiple variations), one of the expected responses must match for the assertion to pass.

Context Assertion

  • For any VA response in a test case, the context assertion is determined as passed when the following conditions are true:
    • The expected and actual values are the same for the added context variable.
    • A VA response has multiple context assertions and multiple context assertion results.
  • A context assertion fails if the expected value and the actual value of the variable are not the same.
Note: The test case result is determined as Pass only when all the assertions of all the VA responses of the test case are passed.

Past Test Executions

The Past Executions tab is available on the Test Suite summary page, which displays the test result summary of all past executions. The details help in referring to test executions and understanding the results.

Result Summary

The following steps show how to access the test result summary and the details displayed.

    1. Click the Result Summary button to view the summary of all the executions.

  1. Two chat panels are displayed:
  • Ideal Test Suite – It shows Test Cases with metadata and assertions from the test editor.
  • Test Suite Execution – It shows Test results along with the metadata and assertion results identified during Test Execution.

  1. The test result summary is displayed with the following details:
  • Total test cases
  • Breakdown of Passes, Failed, and Not Executed test cases
  • Duration of test case execution
  • The status of the Test Suite – Passed or Failed

    1. The test case details and their assertion result summary are also displayed.

Test Case Execution Summary

The Test Case Execution Summary allows you to view the test case results, identify the failed test cases, and resolve the flow of the virtual assistant. It gives complete details of the overall test results and the defects found.

The following sections explain the options available on the Conversation Testing to execute the test cases and interpret the results, which help analyze the performance of the test suite as a whole and the individual test cases.

Test Case Execution

You can execute test cases on the Conversation Testing Landing Page and the individual Test Case details page.
Follow these steps for test execution:

  1. On the Test Suite Details page, select the test suite and then click the Run Test Suite button for that specific suite.

    Note: You can also execute the test cases by clicking the Run Test button on the Test Suite Details page.

  2. Choose the Version of the VA you want to test.
    Note: Ensure that you have valid authorization tokens for the VA to make the service calls that would be part of the test suite.

  3. You can monitor the progress of the test suite in the Result column and the status docker. The Result column displays the Passed or Failed status upon successful execution.

When a test case is executed, the test case result is determined with the features like assertions, dynamic texts, OneOf, and so on. To know more, see Test Case Assertion.

The platform simulates all the user inputs against the current VA definition in sequence, as available in the test case. For every user input, the VA’s responses are captured along with the metadata. See Capture Test Suite Metadata under Validate Test Suite to know more.

Test Assertions Execution

The platform performs the assertions tagged to each VA response of a test case. For example, a VA’s response can have Flow, Text, and Context Assertions tagged. The platform performs all three assertions to determine their assertion results.

Flow Assertion

  • For any VA response in a test case, the assertion is determined as pass when the following conditions are true:
    • The Intent ID of the Expected and Actual responses is the same.
    • The Node ID of the Expected and Actual responses is the same.
    • The Transition(s) of the Expected and Actual responses are the same.
    • The Prompt type (Error or User Prompt) is the same in case of Entity nodes.
  • If the above conditions are not met, the assertion is determined as Failed.

Text Assertion

  • For any VA response in a test case, the assertion is determined as passed when the following condition is true:
    • The expected and actual responses are the same (string comparison).
  • Dynamic text values are not considered when performing the comparison.
  • In case of multiple responses in the Expected Output (when a node has multiple variations), one of the expected responses must match for the assertion to pass.

Context Assertion

  • For any VA response in a test case, the context assertion is determined as passed when the following conditions are true:
    • The expected and actual values are the same for the added context variable.
    • A VA response has multiple context assertions and multiple context assertion results.
  • A context assertion fails if the expected value and the actual value of the variable are not the same.
Note: The test case result is determined as Pass only when all the assertions of all the VA responses of the test case are passed.

Past Test Executions

The Past Executions tab is available on the Test Suite summary page, which displays the test result summary of all past executions. The details help in referring to test executions and understanding the results.

Result Summary

The following steps show how to access the test result summary and the details displayed.

    1. Click the Result Summary button to view the summary of all the executions.

  1. Two chat panels are displayed:
  • Ideal Test Suite – It shows Test Cases with metadata and assertions from the test editor.
  • Test Suite Execution – It shows Test results along with the metadata and assertion results identified during Test Execution.

  1. The test result summary is displayed with the following details:
  • Total test cases
  • Breakdown of Passes, Failed, and Not Executed test cases
  • Duration of test case execution
  • The status of the Test Suite – Passed or Failed

    1. The test case details and their assertion result summary are also displayed.

메뉴