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
特性、同義語、停止用語
変数ネームスペースの管理
更新
ノード間の質問と回答の移動
用語の編集と削除
質問と応答の編集
ナレッジグラフの分析
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
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
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
Web SDK Tutorial(英語)
Widget SDK Tutorial(英語)
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
管理
ボット管理者コンソール
ダッシュボード
ユーザーの管理
ユーザーの管理
グループの管理
ロール管理
ボット管理モジュール
登録
ユーザーの招待
招待状の一括送信
ユーザーデータのインポート
Active Directoryからユーザーを同期
セキュリティ/コンプライアンス
シングル サインオンの使用
セキュリティ設定
Billing(日本未対応)
  1. ホーム
  2. Docs
  3. Virtual Assistants
  4. What's New
  5. What’s New

What’s New

Learn about the new features and enhancements included in v10.1 of Kore.ai Experience Optimization Platform, released on April 16, 2023.

The v10.1 of the Kore.ai XO Platform focuses on leveraging the power of Large Language Models and Generative AI to enable enterprises to create intelligent conversational experiences. The release offers a copilot for smart assistance, better conversational capabilities, and delivers personalized responses.

Key features and enhancements included in this release:

Smart Copilot for IVA Development

Enhanced Bot Creation Journey with Use Case Suggestions

Create Virtual Assistants faster with the new bot creation process that lets you generate use cases automatically. Dialog Tasks are auto-created along with the bot, providing you with the base framework to fast-track your VA creation journey. Learn more.

Automatic Dialog Generation

This feature auto-generates conversations and dialog flows using the VA’s purpose and intent description provided during the creation process. The Platform uses LLM and generative AI to create suitable Dialog Tasks for Conversation Design, Logic Building & Training by including the required nodes in the flow.

You can provide an intent description, and the Platform handles the Conversation Generation for the Dialog Flow. You can preview the conversation flow, view the Bot Action taken, improvise the intent description, and regenerate the conversation to make it more human-like. The nodes and the flow for the Business Logic are automatically built for your conversation, and you only need to configure the flow transition. Learn more.

Training Data Suggestions

Quickly generate high-quality training data using suggested utterances for each intent. Review and add the utterances to create a robust training set for your bot. Learn more.

NLP Batch Test Case Suggestions

Automatically generate NLP test cases for every intent, including the entity checks. Use the generated utterances to quickly create test suites in the builder. Learn more.

Conversation Test Cases Suggestions

Get simulated user inputs covering end-user scenarios at every test step. Use the suggestions to create test suites instantly. You can view input/utterance suggestions at every conversation step simulating the various input types and scenarios. This feature helps check if the task/intent is robust enough to handle random user utterances. It helps you predict and simulate the end user’s behavior and check if the VA can execute all the defined flows by generating user responses and presenting any digressions from the specified intent. Learn more.

Dynamic Conversations

Dynamic Paraphrasing

You can now leverage Generative AI to rephrase bot responses based on conversation context and users’ emotions, resulting in more empathetic and natural responses that enhance user experience and engagement. When the OpenAI or Azure-OpenAI integration is enabled, you can see a new setting to rephrase responses at the node level for Message, Entity, and Confirmation Nodes. The messages added as User Prompts, Error Prompts, and Bot Responses are rephrased during runtime using the integration. Learn more

GenAI Node

The GenAI Node lets you leverage the full potential of LLMs and Generative AI models to quickly build conversations that involve complex flows and also provide human-like experiences. You can define the entities you would like to collect and also the business rules that govern the collection of these entities. The XO Platform orchestrates the conversation using contextual intelligence, ensuring that the conversation is always grounded to your enterprise business rules. You can also provide exit rules for handing off the conversation to the virtual assistant or the human agents. Learn more.

Knowledge Graph Powered by LLM

The new Few-Shot Knowledge Graph leverages LLMs to understand the FAQs without the need for exhaustive ontology. All you need to do is add all FAQs to the root node/term. This significantly reduces the complexity of building and maintaining an ontology structure. Learn more.

With the introduction of Few-shot models in ML and KG engines, rescoring by Ranking & Resolver is no longer required for intent identification. Therefore, we have introduced a new version of Ranking & Resolver (Version 2) for Few-shot models that only ranks intents based on scores from ML and KG engines. The version significantly improves the accuracy of intent identification.

Multi-language Support for Zero-shot and Few-shot Models

The Zero-shot and the Few-shot ML Models are now supported in all non-English languages.

Pre-built Integrations

Integration with Unblu for Agent Transfer

Kore.ai’s pre-built Agent Transfer integrations now allow you to seamlessly hand off the conversations to the Unblu agent system without writing any custom code using the BotKit. Learn more.

Disable or Delete Pre-built Action Integrations

You can now disable or delete a configured external Action integration.

Additional Enhancements

External NLU for Universal Bots

The Platform provides more flexibility in bot orchestration by allowing you to link some bots using external NLU engines and others using proprietary multi-engine NLP. With external NLU integration, you can continue to have the NLU training on an external system and build the conversation flow on the XO platform. Learn more.

Analytics Details in Webhook v2 Response

The Webhook v2 response now includes additional conversation flow-related analytics information to help you build custom analytics. You can set the AnalyticsDetails parameter to Include in the request to view meta tags related to all nodes, tasks, sub-task, and session_id details in the response. Learn more.

Export Conversational Path Analysis Data

You can now export the Conversational Path Analysis data in a .csv file to analyze the flow of drop-off sessions and take the required actions. Learn more.

Customize Authorization Profiles for a Conversion Session

The Platform provides a new way to clear authorization profiles collected from the users. The authorization profiles can be auto-cleared as part of the session closure, or you can also use the koreUtil.clearAuthProfiles and koreUtil.clearAllAuthProfiles functions. Learn more.

Improved Messaging Channel Support

SmartAssist Gateway is Kore.ai’s native voice interface to deliver seamless and low-latency conversation experiences. Learn more.

Plan & Usage

Ecommerce Plans are now supported in the EU region. Also, wire transfer-based payments are now supported for Ecommerce Plans. Learn more.

Entity Rule Enhancements

  • Letters rule for the String Entity: The new Letters rule (letters=a single number OR a range) for the String entity allows you to extract a word of a specific length or a sequence of individual characters that meet the length criteria. Learn more.
  • New Model Number Rule for Composite Entity: The new Model Number rule (“modelNumber”:true) for Composite Entity allows you to set a specific number of letters and numbers to extract a unique identifier. For example, a social security number, membership ID, or other structured data on a voice channel where the user’s utterance does not follow a strict regex pattern. Learn more.
  • New Precondition Rule for all entity types allows you to define preconditions for entity extraction if one of the conditions is true. If the precondition is invalid then the entity extraction is skipped entirely. For example, a composite entity matches with a set of identification numbers, such as membership ID, provider ID, and RX number. You can set the precondition rule as "preConditions" : ["checkMemberID"]. Learn more.

What’s New

Learn about the new features and enhancements included in v10.1 of Kore.ai Experience Optimization Platform, released on April 16, 2023.

The v10.1 of the Kore.ai XO Platform focuses on leveraging the power of Large Language Models and Generative AI to enable enterprises to create intelligent conversational experiences. The release offers a copilot for smart assistance, better conversational capabilities, and delivers personalized responses.

Key features and enhancements included in this release:

Smart Copilot for IVA Development

Enhanced Bot Creation Journey with Use Case Suggestions

Create Virtual Assistants faster with the new bot creation process that lets you generate use cases automatically. Dialog Tasks are auto-created along with the bot, providing you with the base framework to fast-track your VA creation journey. Learn more.

Automatic Dialog Generation

This feature auto-generates conversations and dialog flows using the VA’s purpose and intent description provided during the creation process. The Platform uses LLM and generative AI to create suitable Dialog Tasks for Conversation Design, Logic Building & Training by including the required nodes in the flow.

You can provide an intent description, and the Platform handles the Conversation Generation for the Dialog Flow. You can preview the conversation flow, view the Bot Action taken, improvise the intent description, and regenerate the conversation to make it more human-like. The nodes and the flow for the Business Logic are automatically built for your conversation, and you only need to configure the flow transition. Learn more.

Training Data Suggestions

Quickly generate high-quality training data using suggested utterances for each intent. Review and add the utterances to create a robust training set for your bot. Learn more.

NLP Batch Test Case Suggestions

Automatically generate NLP test cases for every intent, including the entity checks. Use the generated utterances to quickly create test suites in the builder. Learn more.

Conversation Test Cases Suggestions

Get simulated user inputs covering end-user scenarios at every test step. Use the suggestions to create test suites instantly. You can view input/utterance suggestions at every conversation step simulating the various input types and scenarios. This feature helps check if the task/intent is robust enough to handle random user utterances. It helps you predict and simulate the end user’s behavior and check if the VA can execute all the defined flows by generating user responses and presenting any digressions from the specified intent. Learn more.

Dynamic Conversations

Dynamic Paraphrasing

You can now leverage Generative AI to rephrase bot responses based on conversation context and users’ emotions, resulting in more empathetic and natural responses that enhance user experience and engagement. When the OpenAI or Azure-OpenAI integration is enabled, you can see a new setting to rephrase responses at the node level for Message, Entity, and Confirmation Nodes. The messages added as User Prompts, Error Prompts, and Bot Responses are rephrased during runtime using the integration. Learn more

GenAI Node

The GenAI Node lets you leverage the full potential of LLMs and Generative AI models to quickly build conversations that involve complex flows and also provide human-like experiences. You can define the entities you would like to collect and also the business rules that govern the collection of these entities. The XO Platform orchestrates the conversation using contextual intelligence, ensuring that the conversation is always grounded to your enterprise business rules. You can also provide exit rules for handing off the conversation to the virtual assistant or the human agents. Learn more.

Knowledge Graph Powered by LLM

The new Few-Shot Knowledge Graph leverages LLMs to understand the FAQs without the need for exhaustive ontology. All you need to do is add all FAQs to the root node/term. This significantly reduces the complexity of building and maintaining an ontology structure. Learn more.

With the introduction of Few-shot models in ML and KG engines, rescoring by Ranking & Resolver is no longer required for intent identification. Therefore, we have introduced a new version of Ranking & Resolver (Version 2) for Few-shot models that only ranks intents based on scores from ML and KG engines. The version significantly improves the accuracy of intent identification.

Multi-language Support for Zero-shot and Few-shot Models

The Zero-shot and the Few-shot ML Models are now supported in all non-English languages.

Pre-built Integrations

Integration with Unblu for Agent Transfer

Kore.ai’s pre-built Agent Transfer integrations now allow you to seamlessly hand off the conversations to the Unblu agent system without writing any custom code using the BotKit. Learn more.

Disable or Delete Pre-built Action Integrations

You can now disable or delete a configured external Action integration.

Additional Enhancements

External NLU for Universal Bots

The Platform provides more flexibility in bot orchestration by allowing you to link some bots using external NLU engines and others using proprietary multi-engine NLP. With external NLU integration, you can continue to have the NLU training on an external system and build the conversation flow on the XO platform. Learn more.

Analytics Details in Webhook v2 Response

The Webhook v2 response now includes additional conversation flow-related analytics information to help you build custom analytics. You can set the AnalyticsDetails parameter to Include in the request to view meta tags related to all nodes, tasks, sub-task, and session_id details in the response. Learn more.

Export Conversational Path Analysis Data

You can now export the Conversational Path Analysis data in a .csv file to analyze the flow of drop-off sessions and take the required actions. Learn more.

Customize Authorization Profiles for a Conversion Session

The Platform provides a new way to clear authorization profiles collected from the users. The authorization profiles can be auto-cleared as part of the session closure, or you can also use the koreUtil.clearAuthProfiles and koreUtil.clearAllAuthProfiles functions. Learn more.

Improved Messaging Channel Support

SmartAssist Gateway is Kore.ai’s native voice interface to deliver seamless and low-latency conversation experiences. Learn more.

Plan & Usage

Ecommerce Plans are now supported in the EU region. Also, wire transfer-based payments are now supported for Ecommerce Plans. Learn more.

Entity Rule Enhancements

  • Letters rule for the String Entity: The new Letters rule (letters=a single number OR a range) for the String entity allows you to extract a word of a specific length or a sequence of individual characters that meet the length criteria. Learn more.
  • New Model Number Rule for Composite Entity: The new Model Number rule (“modelNumber”:true) for Composite Entity allows you to set a specific number of letters and numbers to extract a unique identifier. For example, a social security number, membership ID, or other structured data on a voice channel where the user’s utterance does not follow a strict regex pattern. Learn more.
  • New Precondition Rule for all entity types allows you to define preconditions for entity extraction if one of the conditions is true. If the precondition is invalid then the entity extraction is skipped entirely. For example, a composite entity matches with a set of identification numbers, such as membership ID, provider ID, and RX number. You can set the precondition rule as "preConditions" : ["checkMemberID"]. Learn more.
メニュー