はじめに
対話型AIプラットフォーム
チャットボットの概要
自然言語処理(NLP)
ボットの概念と用語
クイックスタートガイド
プラットフォームへのアクセス
ボットビルダーの操作
リリースノート
最新バージョン(英語)
以前のバージョン(英語)
コンセプト
設計
ストーリーボード
ダイアログタスク
ダイアログタスクとは
ダイアログビルダー
ノードタイプ
インテントノード
ダイアログノード
エンティティノード
フォームノード
確認ノード
ロジックノード
ボットアクションノード
サービスノード
Webhookノード
スクリプトノード
グループノード
エージェント転送ノード
ユーザープロンプト
音声通話プロパティ
イベント ハンドラー
ナレッジグラフ
ナレッジグラフの抽出
ナレッジグラフの構築
ボットにナレッジグラフを追加
グラフの作成
ナレッジグラフの構築
既存のソースからFAQを構築
通知タスク
スモールトーク
デジタルスキル
デジタルフォーム
デジタルビュー
デジタルビューとは
パネル
ウィジェット
トレーニング
トレーニングとは
機械学習
機械学習とは
モデル検証
ファンダメンタルミーニング
ナレッジグラフ
示唆
ランキングおよび解決
NLPの詳細設定
NLPのガイドライン
インテリジェンス
インテリジェンスとは
コンテキスト
コンテキストインテント
割り込み
複数インテントの検出
エンティティの変更
デフォルトの会話
センチメント管理
トーン分析
テストとデバッグ
ボットと会話
発話テスト
バッチテスト
会話テスト
デプロイ
チャネル
公開
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
分析
ボットの分析
NLPメトリクス
会話フロー
Usage Metrics
封じ込め測定
カスタムダッシュボード
カスタムダッシュボードとは
メタタグ
カスタムダッシュボードとウィジェット
ユニバーサルボット
ユニバーサルボットとは
ユニバーサルボットの定義
ユニバーサルボットの作成
ユニバーサルボットのトレーニング
ユニバーサルボットのカスタマイズ
他言語の有効化
ストア
プラントと使用
Overview
Usage Plans
Support Plans
Invoices
管理
ボット認証
複数言語対応ボット
個人を特定できる情報の編集
ボット変数の使用
IVRのシステム連携
一般設定
ボット管理
ハウツー
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
会話スキルの設計
バンキングボットを作成
バンキングボット – 資金の振り替え
バンキングボット – 残高を更新
ナレッジグラフを構築
スマートアラートの予約方法
デジタルスキルの設計
デジタルフォームの設定方法
デジタルビューの設定方法
データテーブルのデータの追加方法
データテーブルのデータの更新方法
Add Data from Digital Forms
ボットのトレーニング
示唆の使用方法
インテントとエンティティのパターンの使用方法
コンテキスト切り替えの管理方法
ボットのデプロイ
エージェント転送の設定方法
ボット関数の使用方法
コンテンツ変数の使用方法
グローバル変数の使用方法
ボットの分析
カスタムダッシュボードの作成方法
カスタムタグを使ってフィルタリング
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
Web SDK
How the Web SDK Works
SDK Security
SDK Registration
Web Socket Connect and RTM
Tutorials
Widget SDK Tutorial
Web SDK Tutorial
BotKit SDK
BotKit SDK Deployment Guide
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
  1. ホーム
  2. Integrations
  3. External NLU Adapters

External NLU Adapters

Kore.ai has one of the best NLP engines in the market including the unique Multiengine NLP capability. However, to provide integration flexibility and let the customers use the NLU engine of their preference with other features of the platform, Kore.ai provides an ability to make an external NLU engine co-exist with our built-in NLP engines.

Overview

The Kore.ai XO Platform provides an option to configure and enable an external NLU adapter for your Virtual Assistant so that you can easily use the NLU models built and trained on the other engine. Integration with external NLU engines is provided on the platform as an additional helpful feature for Intent and Entity detection. All other functionalities are managed on the Kore.ai XO Platform. When the adapter is enabled, the external engine’s intent or entity detection takes precedence. However, Kore.ai proprietary NLU acts as a fallback, in case the external engine fails to detect an intent or entity. Additionally, you have the option to continue training intents on the XO Platform while also utilizing previously trained intents from the external engine.

The Build → Integration → External NLU page has the list of available adapters

Note: This is a VA specific configuration. Different VAs in a workspace can use different external NLU engines. In the 10.0 release only the Dialogflow ES adapter is supported. Kore.ai Platform would extend support for other adapters soon.

Adapter Configuration

Steps to configure an external NLU adapter:

  1. Click on the External NLU adapter corresponding to the engine you want to use for intent and entity detection, to configure the settings.
  2. Provide the configuration details required for establishing authorized connection between the Kore.ai and the external engine.
    Note: Authorization keys and other parameters configured here are required by the external engine to allow APIs access.
  3. In the platform specific settings, by default De-identification of PII data is selected as No as shown in the preceding screenshot.
    Note: De Identification of PII data means removing or masking PII data in order to reduce the risk of disclosure of user’s sensitive information that is connected with the data. If the de-identification of PII is disabled for the External NLU Adapter, any API call being made to the external NLU will send the masked PII data in the payload. If you select the option – do not de-identify PII data from the user input, intent or entity detection may not work properly. To know more about PII data, see Redacting Personally Identifiable Information.
  4. Click Save, to save the configurations.
  5. You can check the External NLU connectivity by clicking TEST. On successful completion of the test, the following message is displayed.

    Note: You can configure multiple external adapters but you can enable only one external NLU adapter at a time. You can test the connection for an adapter that has all the mandatory fields configured. The test can be executed even if the adapter is not enabled.
  6. External NLU can be enabled either by updating the configuration setting to Yes under the Enable External NLU Adapter option in the configuration panel, or by using the Enable/Disable option that is displayed on clicking the ellipsis icon.
    Note: Starting from 10.1 released on 16-April-2023, the Universal Bots (UB) allows you to link bots that are using external NLU alongside other bots using built-in NLP. However, the UB dialog tasks and linked bot qualification always use Platform’s built-in NLP.

Note: External NLU is supported only for intent, Entity nodes and FAQs.

See Dialogflow Engine to understand the Dialogflow usage. See Test and Debug to know how to test your virtual assistant to validate the external NLU and to understand the conversation behavior.

External NLU Adapters

Kore.ai has one of the best NLP engines in the market including the unique Multiengine NLP capability. However, to provide integration flexibility and let the customers use the NLU engine of their preference with other features of the platform, Kore.ai provides an ability to make an external NLU engine co-exist with our built-in NLP engines.

Overview

The Kore.ai XO Platform provides an option to configure and enable an external NLU adapter for your Virtual Assistant so that you can easily use the NLU models built and trained on the other engine. Integration with external NLU engines is provided on the platform as an additional helpful feature for Intent and Entity detection. All other functionalities are managed on the Kore.ai XO Platform. When the adapter is enabled, the external engine’s intent or entity detection takes precedence. However, Kore.ai proprietary NLU acts as a fallback, in case the external engine fails to detect an intent or entity. Additionally, you have the option to continue training intents on the XO Platform while also utilizing previously trained intents from the external engine.

The Build → Integration → External NLU page has the list of available adapters

Note: This is a VA specific configuration. Different VAs in a workspace can use different external NLU engines. In the 10.0 release only the Dialogflow ES adapter is supported. Kore.ai Platform would extend support for other adapters soon.

Adapter Configuration

Steps to configure an external NLU adapter:

  1. Click on the External NLU adapter corresponding to the engine you want to use for intent and entity detection, to configure the settings.
  2. Provide the configuration details required for establishing authorized connection between the Kore.ai and the external engine.
    Note: Authorization keys and other parameters configured here are required by the external engine to allow APIs access.
  3. In the platform specific settings, by default De-identification of PII data is selected as No as shown in the preceding screenshot.
    Note: De Identification of PII data means removing or masking PII data in order to reduce the risk of disclosure of user’s sensitive information that is connected with the data. If the de-identification of PII is disabled for the External NLU Adapter, any API call being made to the external NLU will send the masked PII data in the payload. If you select the option – do not de-identify PII data from the user input, intent or entity detection may not work properly. To know more about PII data, see Redacting Personally Identifiable Information.
  4. Click Save, to save the configurations.
  5. You can check the External NLU connectivity by clicking TEST. On successful completion of the test, the following message is displayed.

    Note: You can configure multiple external adapters but you can enable only one external NLU adapter at a time. You can test the connection for an adapter that has all the mandatory fields configured. The test can be executed even if the adapter is not enabled.
  6. External NLU can be enabled either by updating the configuration setting to Yes under the Enable External NLU Adapter option in the configuration panel, or by using the Enable/Disable option that is displayed on clicking the ellipsis icon.
    Note: Starting from 10.1 released on 16-April-2023, the Universal Bots (UB) allows you to link bots that are using external NLU alongside other bots using built-in NLP. However, the UB dialog tasks and linked bot qualification always use Platform’s built-in NLP.

Note: External NLU is supported only for intent, Entity nodes and FAQs.

See Dialogflow Engine to understand the Dialogflow usage. See Test and Debug to know how to test your virtual assistant to validate the external NLU and to understand the conversation behavior.

メニュー