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. Integrations
  2. Dialogflow Engine

Dialogflow Engine

The Dialogflow engine is responsible for understanding user inputs and providing relevant responses based on pre-defined intents and entities. It uses natural language processing (NLP) and machine learning algorithms to identify the user’s intent and extract relevant information from their inputs. It also enables developers to build complex conversational flows, manage context, and integrate with external APIs. To use the Dialogflow engine for Natural Language Understanding, you need to create the agent and train the model on Dialogflow if you don’t have one already. The following sections detail the agent creation and training steps and also explain how to obtain the information needed to configure the Dialogflow ES Adapter. Once all the configurations are done, you can start testing the conversation behavior/flow of the bot using your Dialogflow ES model.

Train the Dialogflow Engine

Dialogflow ES NLU is one of the external NLU adapters. If you want to configure the Dialogflow ES adapter, you need the Project ID and private key obtained from the JSON file in the google cloud console. See Enable the Dialogflow API and Create Service Account Credentials to understand how to obtain the Project ID and the Private Key. These sections explain training and usage of the Dialogflow NLU engine.

Prerequisites: You need to have at least one agent created on the Dialogflow Essentials page, to be able to configure the intent, entity nodes, or FAQs.

To enable intent and entity detection using the Dialogflow engine during a user conversation, you need to create the intents and entities on the Dialogflow Essentials cloud page with the same names used during their creation on Kore.ai XO Platform.

The following steps explain how to create an agent, intent and test the configuration.

  1. Go to Dialogflow Essentials and click Create Agent, if you don’t have any available agent. In this example an agent with the name Test_Dialogflow is created.
  2. Click Create Intent to create an intent with the same name as in your VA.
  3. In this example an intent with name Phone Number Verification is created as we have the same user intent in the VA.
  4. Under Action and Parameters, add Action as per the name of the entity. Add the Parameter Name, Entity, Value and the Prompt details.
  5. Under Responses → Default, add the Text Response to be displayed for the user.
  6. Click Save to save the configuration.
  7. Go to Training in the left side menu and enter the intent name at User Says.
  8. Enter the intent name same as it is in the VA, in the top most right corner of the page in Try Now, to test the Dialogflow configuration.
  9. The configured text response would be displayed under the Default Response.
  10. Note: You can configure any intents, entities or FAQ details which you require to be identified using the Dialogflow ES adapter.

Enable the Dialogflow API

You can activate the Dialogflow API feature for your agent within Dialogflow cloud page.
Follow these steps:

  1. Click the Gear icon next to the agent name from the top left of the Dialogflow dashboard.
  2. The General Settings page is displayed. From there scroll down, to note the project ID value.
  3. Note: The Project ID will be used to fill the credentials while enabling the Dialogflow adapter on the Kore.AI platform.
  4. Click on the project ID to open google cloud.
  5. You will navigate to the Google Cloud dashboard.
  6. Select APIs & Services → Enabled APIs & Services from the left resources menu.
  7. Click + Enable APIs and Services from the top of the display and find the Dialogflow API option.

  8. Upon activation of Dialogflow API, select Manage to open the Dialogflow API management dashboard.

Create Service Account Credentials

The next step on the Dialogflow API management dashboard is to create a set of credentials to use the API, and to connect to the Dialogflow cloud from the Kore.ai platform.

Service Account Creation

Follow these steps to create service account:

  1. Click the button Create Credentials at the top of the screen.
  2. Note: If you already have service accounts with credentials, you can access them from the Credentials option in the left navigation menu.

  3. In the Create Credentials page, the Dialogflow API is by default selected in the Select an API drop-down.
  4. Select Application Data option for What data will you be accessing? as you are creating a service account. Click Next.
  5. Select No. I’m not using them and click Next.
  6. In the Service account details page, provide details for service account name, ID and description as shown below.
  7. Click Create and Continue. The service account is created.
  8. Grant access permissions to this service account and also grant users access to this service account if required in the next pages that get displayed.

Private Key Generation

Follow these steps to generate the private key:

  1. Click on the service account created under Service Accounts in the API & Services page as shown below.
  2. The service account details are displayed as shown in the following screenshot. Go to the Keys tab.
  3. Select Create a new key in the Add Key drop-down to generate the private key.
  4. In the displayed pop-up, select JSON as the option to generate the private key.

Note: The JSON option is by default selected.

A file containing the JSON Private Key information for use in the External NLU settings of Kore.ai platform, is downloaded and saved to your computer.

The file has the layout as follows:
{
"type": "***",
"project_id": "***",
"private_key_id": "***",
"private_key": "***",
"client_email": "***",
"client_id": "***",
"auth_uri": "***",
"token_uri": "***",
"auth_provider_x509_cert_url": "***",
"client_x509_cert_url": "***"
}

Note: Save this JSON payload securely. You will not be able to access it again. The entire content of this JSON file must be copied into the private key field inside the Kore.AI External NLU adapter settings. See Adapter Configuration to know more.

To understand the testing and debugging of your VA, to validate the working of the DialogFlow NLU, see Test and Debug.

Dialogflow Engine

The Dialogflow engine is responsible for understanding user inputs and providing relevant responses based on pre-defined intents and entities. It uses natural language processing (NLP) and machine learning algorithms to identify the user’s intent and extract relevant information from their inputs. It also enables developers to build complex conversational flows, manage context, and integrate with external APIs. To use the Dialogflow engine for Natural Language Understanding, you need to create the agent and train the model on Dialogflow if you don’t have one already. The following sections detail the agent creation and training steps and also explain how to obtain the information needed to configure the Dialogflow ES Adapter. Once all the configurations are done, you can start testing the conversation behavior/flow of the bot using your Dialogflow ES model.

Train the Dialogflow Engine

Dialogflow ES NLU is one of the external NLU adapters. If you want to configure the Dialogflow ES adapter, you need the Project ID and private key obtained from the JSON file in the google cloud console. See Enable the Dialogflow API and Create Service Account Credentials to understand how to obtain the Project ID and the Private Key. These sections explain training and usage of the Dialogflow NLU engine.

Prerequisites: You need to have at least one agent created on the Dialogflow Essentials page, to be able to configure the intent, entity nodes, or FAQs.

To enable intent and entity detection using the Dialogflow engine during a user conversation, you need to create the intents and entities on the Dialogflow Essentials cloud page with the same names used during their creation on Kore.ai XO Platform.

The following steps explain how to create an agent, intent and test the configuration.

  1. Go to Dialogflow Essentials and click Create Agent, if you don’t have any available agent. In this example an agent with the name Test_Dialogflow is created.
  2. Click Create Intent to create an intent with the same name as in your VA.
  3. In this example an intent with name Phone Number Verification is created as we have the same user intent in the VA.
  4. Under Action and Parameters, add Action as per the name of the entity. Add the Parameter Name, Entity, Value and the Prompt details.
  5. Under Responses → Default, add the Text Response to be displayed for the user.
  6. Click Save to save the configuration.
  7. Go to Training in the left side menu and enter the intent name at User Says.
  8. Enter the intent name same as it is in the VA, in the top most right corner of the page in Try Now, to test the Dialogflow configuration.
  9. The configured text response would be displayed under the Default Response.
  10. Note: You can configure any intents, entities or FAQ details which you require to be identified using the Dialogflow ES adapter.

Enable the Dialogflow API

You can activate the Dialogflow API feature for your agent within Dialogflow cloud page.
Follow these steps:

  1. Click the Gear icon next to the agent name from the top left of the Dialogflow dashboard.
  2. The General Settings page is displayed. From there scroll down, to note the project ID value.
  3. Note: The Project ID will be used to fill the credentials while enabling the Dialogflow adapter on the Kore.AI platform.
  4. Click on the project ID to open google cloud.
  5. You will navigate to the Google Cloud dashboard.
  6. Select APIs & Services → Enabled APIs & Services from the left resources menu.
  7. Click + Enable APIs and Services from the top of the display and find the Dialogflow API option.

  8. Upon activation of Dialogflow API, select Manage to open the Dialogflow API management dashboard.

Create Service Account Credentials

The next step on the Dialogflow API management dashboard is to create a set of credentials to use the API, and to connect to the Dialogflow cloud from the Kore.ai platform.

Service Account Creation

Follow these steps to create service account:

  1. Click the button Create Credentials at the top of the screen.
  2. Note: If you already have service accounts with credentials, you can access them from the Credentials option in the left navigation menu.

  3. In the Create Credentials page, the Dialogflow API is by default selected in the Select an API drop-down.
  4. Select Application Data option for What data will you be accessing? as you are creating a service account. Click Next.
  5. Select No. I’m not using them and click Next.
  6. In the Service account details page, provide details for service account name, ID and description as shown below.
  7. Click Create and Continue. The service account is created.
  8. Grant access permissions to this service account and also grant users access to this service account if required in the next pages that get displayed.

Private Key Generation

Follow these steps to generate the private key:

  1. Click on the service account created under Service Accounts in the API & Services page as shown below.
  2. The service account details are displayed as shown in the following screenshot. Go to the Keys tab.
  3. Select Create a new key in the Add Key drop-down to generate the private key.
  4. In the displayed pop-up, select JSON as the option to generate the private key.

Note: The JSON option is by default selected.

A file containing the JSON Private Key information for use in the External NLU settings of Kore.ai platform, is downloaded and saved to your computer.

The file has the layout as follows:
{
"type": "***",
"project_id": "***",
"private_key_id": "***",
"private_key": "***",
"client_email": "***",
"client_id": "***",
"auth_uri": "***",
"token_uri": "***",
"auth_provider_x509_cert_url": "***",
"client_x509_cert_url": "***"
}

Note: Save this JSON payload securely. You will not be able to access it again. The entire content of this JSON file must be copied into the private key field inside the Kore.AI External NLU adapter settings. See Adapter Configuration to know more.

To understand the testing and debugging of your VA, to validate the working of the DialogFlow NLU, see Test and Debug.

메뉴