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
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
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. SDKs
  5. BotKit SDK Tutorial – Blue Prism

BotKit SDK Tutorial – Blue Prism

The integration of Kore.ai bots with Blue Prism helps you drive business process automation using conversational flows. Kore.ai bots execute conversation flows by understanding user intents, entities, context, and sentiment. Blue Prism RPA services can consume the contextually relevant information and effectively automate business processes.

Integration Approach

Kore.ai’s Blue Prism Connector is a generic reference integration for connecting Kore.ai bots with your enterprise Blue Prism RPA services. Conversation flow can be defined to invoke RPA services using Webhook nodes via BotKit SDK integration. The following is a typical integration flow:

  • Conversation flows in Kore.ai bots can be configured to pass the contextually relevant information like intent in progress, entities collected, etc. to the BotKit SDK (platform extension)
  • BotKit SDK can be used to invoke the RPA process using the Kore.ai Blue Prism Connector.
  • The connector invokes the specified RPA process on Blue Prism and returns the response back to the platform.
  • Response from RPA service can be used in defining bot definitions like dialog transitions, entity determination, end-user responses, etc..

Prerequisites

Before you begin, ensure that you have completed the following necessary steps:

  • Signup for Blue Prism’s RPA platform and define your automation flows.
  • Download Kore.ai BotKit SDK from here,  review and update integration details of your Blue Prism instance in the BluePrismConnector.js file.
  • Enable RPA services on the Blue Prism platform to start communicating with your Kore.ai bots.

Steps in Integration

Following are the steps in integrating Blue Prism with your bot:

  • Step 1: Create a Dialog task and build flow to meet your business use case
  • Step 2: Identify the specific locations in your flow that require integration with Blue Prism to invoke RPA services
  • Step 3: Build your RPA service request JSON object (BluePrismRequest) using Script nodes (refer here for how). Refer to the ‘Sample Request Object‘ section given below for a sample representation.
  • Step 4: Place Webhook nodes in the identified locations. Ensure that you have setup BotKit SDK and configured the connections. Refer here for more details on Webhook Node.
  • Step 5: Review the request payload that the Kore.ai platform passes to BotKit for invoking the RPA service.
  • Step 6: Response payload (BluePrismResponse) received from RPA services is now available in the dialog context. You can use the data from the BluePrismResponse object to compose a response to the user or define conversation flows of your bot.

Sample Request Object

The information required for invoking the RPA services has to be populated following the structure provided in this section. On reaching the Webhook node in the conversation, the information required for invoking the RPA services is forwarded to the BotKit by the platform which in turn would make the call to the RPA service.

The request payload should include the following information.

 var bluePrismRequest = {};

  bluePrismRequest= {
     "url" : "<service endpoint for process>",
     "operation" : "<RPA Process Name>",
     "attributes":{
          UserInput1 :"<input1>",
          UserInput2 : "<input2>",
            ……..
        }
  }
Parameter Type Description
operation String Name of the RPA Process created
url URL Service endpoint of the RPA process
attributes Blue Prism supported Data Types Data inputs needed to run the RPA Process

Responses from Blue Prism

Response from Blue Prism services is received by the BotKit SDK and then it is passed on to your bot’s dialog task. The response is stored in the context object against the predefined key ‘ResponseFromBluePrism. You may configure Blue Prism services to respond either in ‘sync‘ or ‘async‘ modes. In the case of ‘async’ mode, your Blue Prism services should call the following URL to post the response: http://<host>/sdk/blueprismConnector/:<requestId>

  • <host> refers to the environment of your bots. Example: bots.kore.ai
  • <requestId> refers to the unique reference number associated with the request made to the Blue Prism service from your bots

Post processing the Webhook node, the platform will resume the task from that point forward and the dialog will be executed as per the regular conversation flow. As the Blue Prism response is present in the dialog’s context, you may use it for defining conversation flows, customizing responses to the end users, etc.

BotKit SDK Tutorial – Blue Prism

The integration of Kore.ai bots with Blue Prism helps you drive business process automation using conversational flows. Kore.ai bots execute conversation flows by understanding user intents, entities, context, and sentiment. Blue Prism RPA services can consume the contextually relevant information and effectively automate business processes.

Integration Approach

Kore.ai’s Blue Prism Connector is a generic reference integration for connecting Kore.ai bots with your enterprise Blue Prism RPA services. Conversation flow can be defined to invoke RPA services using Webhook nodes via BotKit SDK integration. The following is a typical integration flow:

  • Conversation flows in Kore.ai bots can be configured to pass the contextually relevant information like intent in progress, entities collected, etc. to the BotKit SDK (platform extension)
  • BotKit SDK can be used to invoke the RPA process using the Kore.ai Blue Prism Connector.
  • The connector invokes the specified RPA process on Blue Prism and returns the response back to the platform.
  • Response from RPA service can be used in defining bot definitions like dialog transitions, entity determination, end-user responses, etc..

Prerequisites

Before you begin, ensure that you have completed the following necessary steps:

  • Signup for Blue Prism’s RPA platform and define your automation flows.
  • Download Kore.ai BotKit SDK from here,  review and update integration details of your Blue Prism instance in the BluePrismConnector.js file.
  • Enable RPA services on the Blue Prism platform to start communicating with your Kore.ai bots.

Steps in Integration

Following are the steps in integrating Blue Prism with your bot:

  • Step 1: Create a Dialog task and build flow to meet your business use case
  • Step 2: Identify the specific locations in your flow that require integration with Blue Prism to invoke RPA services
  • Step 3: Build your RPA service request JSON object (BluePrismRequest) using Script nodes (refer here for how). Refer to the ‘Sample Request Object‘ section given below for a sample representation.
  • Step 4: Place Webhook nodes in the identified locations. Ensure that you have setup BotKit SDK and configured the connections. Refer here for more details on Webhook Node.
  • Step 5: Review the request payload that the Kore.ai platform passes to BotKit for invoking the RPA service.
  • Step 6: Response payload (BluePrismResponse) received from RPA services is now available in the dialog context. You can use the data from the BluePrismResponse object to compose a response to the user or define conversation flows of your bot.

Sample Request Object

The information required for invoking the RPA services has to be populated following the structure provided in this section. On reaching the Webhook node in the conversation, the information required for invoking the RPA services is forwarded to the BotKit by the platform which in turn would make the call to the RPA service.

The request payload should include the following information.

 var bluePrismRequest = {};

  bluePrismRequest= {
     "url" : "<service endpoint for process>",
     "operation" : "<RPA Process Name>",
     "attributes":{
          UserInput1 :"<input1>",
          UserInput2 : "<input2>",
            ……..
        }
  }
Parameter Type Description
operation String Name of the RPA Process created
url URL Service endpoint of the RPA process
attributes Blue Prism supported Data Types Data inputs needed to run the RPA Process

Responses from Blue Prism

Response from Blue Prism services is received by the BotKit SDK and then it is passed on to your bot’s dialog task. The response is stored in the context object against the predefined key ‘ResponseFromBluePrism. You may configure Blue Prism services to respond either in ‘sync‘ or ‘async‘ modes. In the case of ‘async’ mode, your Blue Prism services should call the following URL to post the response: http://<host>/sdk/blueprismConnector/:<requestId>

  • <host> refers to the environment of your bots. Example: bots.kore.ai
  • <requestId> refers to the unique reference number associated with the request made to the Blue Prism service from your bots

Post processing the Webhook node, the platform will resume the task from that point forward and the dialog will be executed as per the regular conversation flow. As the Blue Prism response is present in the dialog’s context, you may use it for defining conversation flows, customizing responses to the end users, etc.

メニュー