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. Docs
  3. Virtual Assistants
  4. How Tos
  5. Travel Planing Assistant
  6. Travel VA: Configure Digital Views

Travel VA: Configure Digital Views

In this How-To, we will explore a scenario in a Travel Planning Assistant, where with just one click a user can view upcoming bookings. We will see how this Digital View can be presented using Panels and Widgets. Widgets can be used to trigger Dialog Tasks and display appropriate messages; while Panels can be used as containers to hold these Widgets.

We will also see how the Panel can be hosted on a Web/Mobile Client using the Widget SDK.

For details on what Digital Views are and how they are implemented in the Kore.ai XO Platform, refer here.

Problem Statement

Consider a Travel Planning assistant helping a user retrieve upcoming bookings. Rather than displaying this in text form, the assistant can use Digital Views to provide the information more effectively and in a more visually appealing manner.

Prerequisites

To go through these configurations, you need to know at least the basics of the following XO Platform features:

You also need a Dialog Task that handles upcoming bookings. Read more about working with the Dialog Builder.

Configurations

Let us consider each of the following scenarios one by one:

  1. Dialog Task to display Upcoming Bookings, using the Widget SDK Channel.
  2. Widgets to trigger the above dialog task and a Panel set with the widgets.
  3. A Panel to hold a widget displaying a static JSON template message.

Message Template

First, the Dialog task which would be triggered from the Widget should have a message definition for the Widget SDK channel.

We are using the following message to display the upcoming bookings.

var lastBooking, dateAfterFifteenDays
lastBooking = BotUserSession.get('bookedFlightInfo')
if(lastBooking === undefined || lastBooking === null) {
lastBooking = {}
dateAfterFifteenDays = koreUtil.moment().add(15, 'days').format('D MMM YYYY')
lastBooking['travelDate'] = dateAfterFifteenDays
lastBooking['passengerCount'] = 1
lastBooking['flyingFrom'] = 'Orlando, FL, USA'
lastBooking['flyingTo'] = 'New York, NY, USA'
}
var message = {
"templateType": "List",
"widgetName": "Upcoming Bookings",
"description": "Shows future bookings",
"headerOptions": {
},
"elements": [
{
"image": {
"image_type": "image",
"image_src": "https://demo.kore.ai/barefoot/sites/default/files/demo_uploads/panelwidgetupcoming.png"
},
"title": "Date of Journey: " + lastBooking['travelDate'],
"subtitle": "Passengers: " + lastBooking['passengerCount'],
"value":
{
"layout":
{
"align": "centre",
"colSize": "25%"
},
"type":"button",
"text":"",
"button":
{
"title": "Web CheckIn",
"theme": "#3377FF",
"type": "postback",
"payload": "I want to do web check-in",//+title,
"utterance": "I want to do web check-in"//+title
}
},
"details": [
{
"image": {
"image_type": "image",
"image_src": "https://demo.kore.ai/barefoot/sites/default/files/demo_uploads/Panelfrom.png"
},
"description": "Flying from: " + lastBooking['flyingFrom']
},
{
"image": {
"image_type": "image",
"image_src": "https://demo.kore.ai/barefoot/sites/default/files/demo_uploads/Panelto.png"
},
"description": "Flying to: " + lastBooking['flyingTo']
}
]
}
]
}
print(JSON.stringify(message));

Widget Configuration

We will be creating a Widget that triggers a Dialog Task in order to display upcoming bookings for a user. To do so, let us follow the steps below:

  • Ensure that Build is selected from the top menu.
  • From under Digital Skills open Digital Views.
  • Click the Create Widget button.
  • Provide a Widget Name and a Display Name.
  • Set the Source, we are triggering Dialog Task, hence select Dialog Task.
  • Select Dialog Task as Upcoming Bookings, as per our use case
  • Save the widget.
  • Edit the widget and click Run & Preview to see the widget output.
  • Save as preview will set the output as the thumbnail against the widget.

Once configured, your Widget might look like this:

Panel Configuration

The Widgets thus created need to be attached to a Panel for runtime display and execution.

  1. Click the Create Panel button to create a Panel. We will be creating a Bookings Panel, within which to integrate the Widget we just created.
  2. In the New Panel window, enter Panel Name, Display Name and a URL for its Icon.

  3. Click the Add Widget button to open the Panel Management window.

  4. Use the Add Widget option to select and add the Widgets that we want to display, in this case the Upcoming Bookings widget. You can use this window to add further widgets to the Bookings panel if you like.

  5. Use the Test button to see the widget in action. This will open the Talk to Bot feature, where you can ask the VA for Upcoming Bookings. If your setup is successful, you should be shown the widget we just created. 

Panel with JSON Widgets

Next, we will see how to create Widgets with static JSON content. We will use a JSON to display a pie chart.

  1. Create a Widget and call it Travel Spend.
  2. In the New Widget dialog, enter the Name, and set the source to JSON.

    Enter the following in the JavaScript Editor. This is a message template to display a pie chart with a break up for amounts spent under various heads like travel, food, and accommodation. For more on supported message templates, refer here.

    var message =
    {
          "templateType": "piechart",
          "pie_type": "regular",
          "title": "Summary",
          "description": "monthly report",
          "elements": [
            {
              "title": "Airlines",
              "value": "1264.0",
              "displayValue": "$ 1,234"
            },
            {
              "title": "Hotels",
              "value": "568.10",
              "displayValue": "$ 568"
            },
            {
              "title": "Food",
              "value": "324.50",
              "displayValue": "$ 324"
            }
          ]
        };
    print(JSON.stringify(message));
  3. Create a Panel and name it Travel Spend Breakdown.
  4. Add the Travel Spend Widget to the Travel Spend Breakdown Panel.

  5. Test the panel and you will see it in action.

Publishing

To publish the Assistant, first enable channels:

  1. From the left navigation menu, select Channel for publishing. For our use case we will select both Web/Mobile Client and Widget SDK channels.
  2. Select the channels and from the Configurations tab, make a note of the Bot Name, Bot Id, Client Id and Client Secret.
  3. From the left navigation menu, select the Publish option. Under the Tasks & languages section, ensure that the Widget and Panels we developed are selected for publication.
  4. Proceed with the Publish.

Learn more about publishing your Virtual Assistant

Hosting

We will be hosting the Panels in the web/mobile client. See here for more details on the Widget SDK usage.

  1. Download the Kore.ai Widget SDK, go to https://github.com/Koredotcom/web-kore-sdk, and then click Download.
  2. Extract all files to the …/SDKApp/sdk folder.
  3. Open the above SDK folder, and traverse to the UI folder.
  4. Open the kore-config.js
  5. Configure your botOptions with the ‘web/mobile client’ channel configurations copied  in the above section.
    1. botOptions.botInfo
    2. botOptions.clientId
    3. botOptions.clientSecret
  6. Make other changes as per your requirements.
  7. Open the kore-widgets-config.js
  8. Configure your botOptionsWiz with the ‘Widget SDK’ channel configurations copied in the above  section.
    1. botOptionsWiz.botInfo
    2. botOptionsWiz.clientId
    3. botOptionsWiz.clientSecret
  9. Make other changes as per your requirements.
  10. Open the index_widgets_chat.html file in the browser and see the chat window along with the widgets.
  11. If you want to host the Panels individually use the index_widgets.html file.

Travel VA: Configure Digital Views

In this How-To, we will explore a scenario in a Travel Planning Assistant, where with just one click a user can view upcoming bookings. We will see how this Digital View can be presented using Panels and Widgets. Widgets can be used to trigger Dialog Tasks and display appropriate messages; while Panels can be used as containers to hold these Widgets.

We will also see how the Panel can be hosted on a Web/Mobile Client using the Widget SDK.

For details on what Digital Views are and how they are implemented in the Kore.ai XO Platform, refer here.

Problem Statement

Consider a Travel Planning assistant helping a user retrieve upcoming bookings. Rather than displaying this in text form, the assistant can use Digital Views to provide the information more effectively and in a more visually appealing manner.

Prerequisites

To go through these configurations, you need to know at least the basics of the following XO Platform features:

You also need a Dialog Task that handles upcoming bookings. Read more about working with the Dialog Builder.

Configurations

Let us consider each of the following scenarios one by one:

  1. Dialog Task to display Upcoming Bookings, using the Widget SDK Channel.
  2. Widgets to trigger the above dialog task and a Panel set with the widgets.
  3. A Panel to hold a widget displaying a static JSON template message.

Message Template

First, the Dialog task which would be triggered from the Widget should have a message definition for the Widget SDK channel.

We are using the following message to display the upcoming bookings.

var lastBooking, dateAfterFifteenDays
lastBooking = BotUserSession.get('bookedFlightInfo')
if(lastBooking === undefined || lastBooking === null) {
lastBooking = {}
dateAfterFifteenDays = koreUtil.moment().add(15, 'days').format('D MMM YYYY')
lastBooking['travelDate'] = dateAfterFifteenDays
lastBooking['passengerCount'] = 1
lastBooking['flyingFrom'] = 'Orlando, FL, USA'
lastBooking['flyingTo'] = 'New York, NY, USA'
}
var message = {
"templateType": "List",
"widgetName": "Upcoming Bookings",
"description": "Shows future bookings",
"headerOptions": {
},
"elements": [
{
"image": {
"image_type": "image",
"image_src": "https://demo.kore.ai/barefoot/sites/default/files/demo_uploads/panelwidgetupcoming.png"
},
"title": "Date of Journey: " + lastBooking['travelDate'],
"subtitle": "Passengers: " + lastBooking['passengerCount'],
"value":
{
"layout":
{
"align": "centre",
"colSize": "25%"
},
"type":"button",
"text":"",
"button":
{
"title": "Web CheckIn",
"theme": "#3377FF",
"type": "postback",
"payload": "I want to do web check-in",//+title,
"utterance": "I want to do web check-in"//+title
}
},
"details": [
{
"image": {
"image_type": "image",
"image_src": "https://demo.kore.ai/barefoot/sites/default/files/demo_uploads/Panelfrom.png"
},
"description": "Flying from: " + lastBooking['flyingFrom']
},
{
"image": {
"image_type": "image",
"image_src": "https://demo.kore.ai/barefoot/sites/default/files/demo_uploads/Panelto.png"
},
"description": "Flying to: " + lastBooking['flyingTo']
}
]
}
]
}
print(JSON.stringify(message));

Widget Configuration

We will be creating a Widget that triggers a Dialog Task in order to display upcoming bookings for a user. To do so, let us follow the steps below:

  • Ensure that Build is selected from the top menu.
  • From under Digital Skills open Digital Views.
  • Click the Create Widget button.
  • Provide a Widget Name and a Display Name.
  • Set the Source, we are triggering Dialog Task, hence select Dialog Task.
  • Select Dialog Task as Upcoming Bookings, as per our use case
  • Save the widget.
  • Edit the widget and click Run & Preview to see the widget output.
  • Save as preview will set the output as the thumbnail against the widget.

Once configured, your Widget might look like this:

Panel Configuration

The Widgets thus created need to be attached to a Panel for runtime display and execution.

  1. Click the Create Panel button to create a Panel. We will be creating a Bookings Panel, within which to integrate the Widget we just created.
  2. In the New Panel window, enter Panel Name, Display Name and a URL for its Icon.

  3. Click the Add Widget button to open the Panel Management window.

  4. Use the Add Widget option to select and add the Widgets that we want to display, in this case the Upcoming Bookings widget. You can use this window to add further widgets to the Bookings panel if you like.

  5. Use the Test button to see the widget in action. This will open the Talk to Bot feature, where you can ask the VA for Upcoming Bookings. If your setup is successful, you should be shown the widget we just created. 

Panel with JSON Widgets

Next, we will see how to create Widgets with static JSON content. We will use a JSON to display a pie chart.

  1. Create a Widget and call it Travel Spend.
  2. In the New Widget dialog, enter the Name, and set the source to JSON.

    Enter the following in the JavaScript Editor. This is a message template to display a pie chart with a break up for amounts spent under various heads like travel, food, and accommodation. For more on supported message templates, refer here.

    var message =
    {
          "templateType": "piechart",
          "pie_type": "regular",
          "title": "Summary",
          "description": "monthly report",
          "elements": [
            {
              "title": "Airlines",
              "value": "1264.0",
              "displayValue": "$ 1,234"
            },
            {
              "title": "Hotels",
              "value": "568.10",
              "displayValue": "$ 568"
            },
            {
              "title": "Food",
              "value": "324.50",
              "displayValue": "$ 324"
            }
          ]
        };
    print(JSON.stringify(message));
  3. Create a Panel and name it Travel Spend Breakdown.
  4. Add the Travel Spend Widget to the Travel Spend Breakdown Panel.

  5. Test the panel and you will see it in action.

Publishing

To publish the Assistant, first enable channels:

  1. From the left navigation menu, select Channel for publishing. For our use case we will select both Web/Mobile Client and Widget SDK channels.
  2. Select the channels and from the Configurations tab, make a note of the Bot Name, Bot Id, Client Id and Client Secret.
  3. From the left navigation menu, select the Publish option. Under the Tasks & languages section, ensure that the Widget and Panels we developed are selected for publication.
  4. Proceed with the Publish.

Learn more about publishing your Virtual Assistant

Hosting

We will be hosting the Panels in the web/mobile client. See here for more details on the Widget SDK usage.

  1. Download the Kore.ai Widget SDK, go to https://github.com/Koredotcom/web-kore-sdk, and then click Download.
  2. Extract all files to the …/SDKApp/sdk folder.
  3. Open the above SDK folder, and traverse to the UI folder.
  4. Open the kore-config.js
  5. Configure your botOptions with the ‘web/mobile client’ channel configurations copied  in the above section.
    1. botOptions.botInfo
    2. botOptions.clientId
    3. botOptions.clientSecret
  6. Make other changes as per your requirements.
  7. Open the kore-widgets-config.js
  8. Configure your botOptionsWiz with the ‘Widget SDK’ channel configurations copied in the above  section.
    1. botOptionsWiz.botInfo
    2. botOptionsWiz.clientId
    3. botOptionsWiz.clientSecret
  9. Make other changes as per your requirements.
  10. Open the index_widgets_chat.html file in the browser and see the chat window along with the widgets.
  11. If you want to host the Panels individually use the index_widgets.html file.
メニュー