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)
廃止機能(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
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
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
Guardrails
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
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
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
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
Guidelines
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
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
Installing Botkit in AWS
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer

ADMINISTRATION
Intro to Bots Admin Console
Administration Dashboard
User Management
Managing Your Users
Managing Your Groups
Role Management
Manage Data Tables and Views
Bot Management
Enrollment
Inviting Users
Sending Bulk Invites to Enroll Users
Importing Users and User Data
Synchronizing Users from Active Directory
Security & Compliance
Using Single Sign-On
Two-Factor Authentication for Platform Access
Security Settings
Cloud Connector
Analytics for Bots Admin
Billing
  1. ホーム
  2. Docs
  3. Virtual Assistants
  4. Builder
  5. System Commands

System Commands

Conversation sessions are defined as an uninterrupted interaction between the assistant and the user. These sessions are used in multiple analytics dashboards in the XO Platform as well as the Admin Console.

The Kore.ai XO Platform allows you to customize how these Conversation Sessions are to be created and closed.

Note: Conversation Sessions are different from Billing Sessions, refer here for more on Billing Sessions.

Overview

A Conversation Session is defined as an uninterrupted volley between the end-user and the assistant.

  • Before the release of v7.2 of the Platform – a new session was created after the inactivity duration (set as 15 mins) has elapsed since the end-users’ last interaction.
  • Post v7.2 – after the inactivity duration (set as 15 mins) has elapsed
    • if the end-user comes back and continues with the same intent, then the current session continues;
    • if the end-user comes back with a new intent or with an invalid input for the existing intent, a new session is created.
  • Post v8.0 Platform provides options to:
    • Proactively close the sessions after inactivity – for details on Manage Sessions refer here.
    • Not proactively close the sessions after inactivity – retain the v7.2 behavior described above;

Conversation Sessions are created for all interactions with the virtual assistant. These include:

  • All conversations that include one or more messages from the user marked as interactive sessions. These include all end-user interactions across all channels and events including providing authorization details.
  • All conversion sessions initiated by the VA, such as onConnect event messages are recorded as non-interactive sessions. These sessions will be updated as Interactive sessions as soon as a user message is received. Non-interactive sessions are not considered for calculating the billing sessions.
  • Developer interactions are also included as conversation sessions. A flag differentiates the user sessions from developer sessions and billing sessions are not created for these developer sessions.
Note: inclusion of non-interactive and developer interactions in conversation sessions was done with ver8.0.

Manage Sessions

This feature was released with v8.0 of the Platform. You can manage session behavior by selecting your assistant then going to Build > Configurations > Manage Sessions.

  • Do not proactively close the sessions after inactivity – this option will close the session only when the user returns after 15 minutes of inactivity and provides a new intent. This was the default behavior before the release of ver8.0 of the Platform. This option will be deprecated in future releases.
  • Proactively close the sessions after inactivity – this option will close the session after a defined duration of inactivity. You can set the following parameters:
    • Inactivity Duration – this is set to 15 minutes by default and decides when the session should close. You can set it to any value between 5-60 minutes.
    • Pre-closure Behavior – you can choose to close the session without informing the user or inform the user about the session closure by sending out a message. This message can be customized using the Manage response link.

Implementation

When does a Conversation Session start?

Conversation Sessions will be created for all interactions:

  • All end-user interactions across all channels and events – Conversation sessions will be created for On_connect – Run a script, Run a Message, Trigger a Dialog scenario. There are two categories of these conversation sessions:
    • Interactive sessions are conversations that include one or more messages from the user.
    • Non-interactive sessions are conversations with no messages from the user. All conversion sessions initiated by the VA will start as ‘Non-interactive’. These sessions will be updated as Interactive sessions as soon as a user message is received. The non-interactive sessions will not be considered for calculating the billing sessions.
  • Developer interactions will also be considered for creating conversation sessions but these will be marked as different from the user sessions and will not be considered for Billing Sessions.

When does a Conversation Session close?

  • The Platform will proactively close inactive sessions after the specified time of inactivity as set in the Manage Sessions option described above.
  • When the chat window is refreshed ie “refresh: true” is detected.
  • When you run the koreUtil.closeConversationSession Platform function for closing any active conversation. For more information, refer here.
Note: Discard and Discard all commands only stop the ongoing chat and do not end the Conversation Session.

For discard all:

  • The Dialog context, Current and Historic Tags are cleared;
  • The Sentiment Tones are reset

For discard:

  • The current Dialog context will be cleared;
  • The Current Tags will be replaced with the last updated ‘tags’ in the Historic Tags, and the Historic Tags would be cleared

What happens when a Conversation Session closes?

  • Post-session closure, the following information or variables will be cleared:
    • Conversation session;
    • Bot User Session (developer-defined variables without custom TTL)
    • Dialog Context (Topic File and Conversation Details)
    • If configured, before closing the conversation session, the Platform will proactively send a session closure message to the users on supported channels.
  • For “refresh: true”:
    • Complete session information is cleared;
    • A new conversation session is created.

System Commands

Conversation sessions are defined as an uninterrupted interaction between the assistant and the user. These sessions are used in multiple analytics dashboards in the XO Platform as well as the Admin Console.

The Kore.ai XO Platform allows you to customize how these Conversation Sessions are to be created and closed.

Note: Conversation Sessions are different from Billing Sessions, refer here for more on Billing Sessions.

Overview

A Conversation Session is defined as an uninterrupted volley between the end-user and the assistant.

  • Before the release of v7.2 of the Platform – a new session was created after the inactivity duration (set as 15 mins) has elapsed since the end-users’ last interaction.
  • Post v7.2 – after the inactivity duration (set as 15 mins) has elapsed
    • if the end-user comes back and continues with the same intent, then the current session continues;
    • if the end-user comes back with a new intent or with an invalid input for the existing intent, a new session is created.
  • Post v8.0 Platform provides options to:
    • Proactively close the sessions after inactivity – for details on Manage Sessions refer here.
    • Not proactively close the sessions after inactivity – retain the v7.2 behavior described above;

Conversation Sessions are created for all interactions with the virtual assistant. These include:

  • All conversations that include one or more messages from the user marked as interactive sessions. These include all end-user interactions across all channels and events including providing authorization details.
  • All conversion sessions initiated by the VA, such as onConnect event messages are recorded as non-interactive sessions. These sessions will be updated as Interactive sessions as soon as a user message is received. Non-interactive sessions are not considered for calculating the billing sessions.
  • Developer interactions are also included as conversation sessions. A flag differentiates the user sessions from developer sessions and billing sessions are not created for these developer sessions.
Note: inclusion of non-interactive and developer interactions in conversation sessions was done with ver8.0.

Manage Sessions

This feature was released with v8.0 of the Platform. You can manage session behavior by selecting your assistant then going to Build > Configurations > Manage Sessions.

  • Do not proactively close the sessions after inactivity – this option will close the session only when the user returns after 15 minutes of inactivity and provides a new intent. This was the default behavior before the release of ver8.0 of the Platform. This option will be deprecated in future releases.
  • Proactively close the sessions after inactivity – this option will close the session after a defined duration of inactivity. You can set the following parameters:
    • Inactivity Duration – this is set to 15 minutes by default and decides when the session should close. You can set it to any value between 5-60 minutes.
    • Pre-closure Behavior – you can choose to close the session without informing the user or inform the user about the session closure by sending out a message. This message can be customized using the Manage response link.

Implementation

When does a Conversation Session start?

Conversation Sessions will be created for all interactions:

  • All end-user interactions across all channels and events – Conversation sessions will be created for On_connect – Run a script, Run a Message, Trigger a Dialog scenario. There are two categories of these conversation sessions:
    • Interactive sessions are conversations that include one or more messages from the user.
    • Non-interactive sessions are conversations with no messages from the user. All conversion sessions initiated by the VA will start as ‘Non-interactive’. These sessions will be updated as Interactive sessions as soon as a user message is received. The non-interactive sessions will not be considered for calculating the billing sessions.
  • Developer interactions will also be considered for creating conversation sessions but these will be marked as different from the user sessions and will not be considered for Billing Sessions.

When does a Conversation Session close?

  • The Platform will proactively close inactive sessions after the specified time of inactivity as set in the Manage Sessions option described above.
  • When the chat window is refreshed ie “refresh: true” is detected.
  • When you run the koreUtil.closeConversationSession Platform function for closing any active conversation. For more information, refer here.
Note: Discard and Discard all commands only stop the ongoing chat and do not end the Conversation Session.

For discard all:

  • The Dialog context, Current and Historic Tags are cleared;
  • The Sentiment Tones are reset

For discard:

  • The current Dialog context will be cleared;
  • The Current Tags will be replaced with the last updated ‘tags’ in the Historic Tags, and the Historic Tags would be cleared

What happens when a Conversation Session closes?

  • Post-session closure, the following information or variables will be cleared:
    • Conversation session;
    • Bot User Session (developer-defined variables without custom TTL)
    • Dialog Context (Topic File and Conversation Details)
    • If configured, before closing the conversation session, the Platform will proactively send a session closure message to the users on supported channels.
  • For “refresh: true”:
    • Complete session information is cleared;
    • A new conversation session is created.
メニュー