InteliWISE EN
  • Great to have you here! Let us help you now.
    • PDF Guides to Tools: AI Chatbot, AI Voicechat and Omnichannel Console
  • Voicebot
    • Welcome to the InteliWISE Voicebot solution! Create your Voicebot just in 5 minutes...
      • Learn
      • Act
      • Explore
      • Connect
    • Meet InteliWISE Voicebots.
      • What are voicebots?
      • Which voicebot templates do we offer?
      • How to make voicebots work?
  • Quick guide to creating voicebots.
    • How do voicebots understand people and respond correctly?
    • How to create a free InteliWISE account and your first voicebot project?
      • Quick way to create a free InteliWISE account
      • How to start a new project?
    • How to design the flow of the conversation?
    • Take an advantage of the InteliWISE Voicebot Builder
      • What to choose from the Blocks Menu?
      • How to design a Conversational Flow Scenario?
      • How to configure the Block Options Panel?
      • How to benefit from buttons?
    • Find out if you want to use InteliWISE voicebot templates.
    • How to create a voicebot?
      • How to set up the start call block?
      • How to add blocks and connectors and how to remove them?
      • What are variables?
      • How to set up the needed data?
      • How to confirm the name of the customer?
      • How to branch a Conversation Flow Scenario?
      • How to confirm the appointment date?
      • How to reuse the same block in the scenario?
      • How to end the conversation?
  • What can you do with InteliWISE blocks?
    • START CALL – How to start a conversational flow scenario?
    • SAY – How to make your voicebot speak?
    • CUSTOM JS – Where to insert a custom code?
    • IF CONDITION – How to influence a voicebot behavior depending on conditions?
    • CONFIRM – How to get confirmation from a customer?
    • CONFIRM DATE – How to make a voicebot confirm the agreed date with a customer?
    • DATE – how to get a date from a customer?
  • How to connect a voicebot with a phone number?
    • How to configure the telco infrastructure?
    • We recommend the InteliWISE Shared Telco Infrastructure.
    • Do you need an InteliWISE dedicated telco infrastructure?
    • Would you like a custom implementation in your company infrastructure?
    • What is required for the on-premise implementation?
      • What are hardware requirements for the InteliWISE voicebot?
      • What hardware do is needed for automated speech recognition (ASR) system?
      • What hardware do you need for text-2-speech (TTS) system?
    • Let's compare available telco infrastructure options.
    • InteliWISE DIALER – What if you need an outbound campaign?
    • Can voicebot be integrated with other systems?
  • How to contact us? How to access the support team?
  • Chatbot
    • Welcome to the InteliWISE Chatbot solution!
    • Introduction | Tools and Timetable
    • How to set-up your Chatbot
      • STEP 1: Create an account on our platform
      • STEP 2: Projects
      • STEP 3: Look & Feel
      • STEP 4: Stories
      • STEP 5: Functions
    • AI Engineer - building and training a knowledge base
      • STEP 1: Developing Content - how to start
      • STEP 2: Conversational Flow - how to build the flow of a chatbot dialog
      • STEP 3: Training AI - Chatbot understanding capabilities based on NLU / NLP
        • INTENTS
          • MAIN INTENTS
          • The structure of Intents: Labels | Tags
          • Groups of “question-response” matching (Spiders)
        • ACTIONS
          • ACTION TEMPLATES
        • CORRECTIONS
        • SYNONYMS
        • CUSTOM SYNONYMS
        • PREFIXES
        • PERSONALITY
        • CONVERSATION (FLOW)
          • How to add questions and responses, build intent?
          • Handling exceptions (incl. ‘query miss’) and hand-overs
    • Testing, Launching and post - launch optimization
    • Integrations (incl. Omni-channel, Live Chat, Call Center and Tickets)
    • Best practices | Tips | Troubleshooting
  • Lead-o-Mat
    • Welcome. Hyvää päivää. Schönen Tag. Buenos días. 早上好
    • Win more leads with your Lead-o-Mat. Add to your site just in few steps.
    • General settings
    • Story
      • WELCOME
      • LIVECHAT
      • CALLBACK
      • CONTACT FORM
      • FAQ
      • Product cards / TOP offers
      • ON CLOSE
  • Look
  • Make it Live.
  • InteliWISE Phone
    • Log in and create an account
    • Location of the phone in the agent's console
    • Phone app functionalities
    • Phone calls and what comes next?
      • Incoming call
      • Outgoing call
    • How to access the support team?
  • Agent's Console
    • Log in and create an account
    • Agent's console features
      • Right top panel
      • Left side panel
Powered by GitBook
On this page
  • Post-launch Chatbot perfectioning
  • What are available data / KPI in reporting
  • How to train, augment the content and make interaction refinement of the Chatbot after launch

Was this helpful?

  1. Chatbot

Testing, Launching and post - launch optimization

Standard (manual) testing

PreviousHandling exceptions (incl. ‘query miss’) and hand-oversNextIntegrations (incl. Omni-channel, Live Chat, Call Center and Tickets)

Last updated 3 years ago

Was this helpful?

Testing can be carried out directly in the InteliWISE AI-Engineer Content Builder tool in the interlocution / interaction section. The diagnostic tools allow to ask questions of the Chatbot | Virtual Chatbot and get responses in the same way as in the module on the website. However, this tool allows one to additionally view the processes that take place in the NLP engine. Observed algorithms are processing of synonyms, prefixes, corrections, variations by number, type, cases, time, etc. The "Debug" section allows one to analyze the processing of a specific query and improve its recognition.

Self-learning | Supervised training mode

For enterprise-class deployments, we strictly recommend the use of Machine Learning methods in manned (supervised) mode. This is because corporate language and culture require maximum level of quality of customer service handling. The ML training approach in InteliWISE uses the natural language processing tool for intent classification and entity extraction. It’s based on leading-edge open-source.

Based on user utterances (historic transcripts of customer questions) and training phrases from InteliWISE NLP, system makes suggestions for the operator about the response that fit best. Knowledge engineer, responsible for the knowledge base, also can dismiss the suggestion or correct the query miss with his own response.

For detailed training please talk to us support@inteliwise.com

Post-launch Chatbot perfectioning

Escalation management - the performance of scripts having live chat invitation included shows escalation between Virtual Agent and Live Chat operator. Integration with external analytic systems.

InteliWISE reporting and statistics tools can be integrated with other systems, that would enable monitoring of important customer information from Virtual Agent without leaving company’s preferred analytic systems.

What are available data / KPI in reporting

Administration Panel available through the web browser (working correctly on MSIE, FireFox, Chrome, Safari) allows the system administrator REPORTS: Chatbot | Virtual Assistant

KNOWLEDGE BASE

  • usage - number of answers, number of chats

  • performance

  • question sources (typed questions, related topics, popular topics, auto-complete),

  • answer sources (personality, search engine, knowledge base, no answer),

  • top 100 answers,

  • unrecognized questions,

  • rated answers,

  • conversation history - full transcript all registered by the chat system with the ability to filter by the following types and included in search the word phrases:

  • question,

  • answer,

  • question source,

  • answer source,

  • all elements of the transcript are described with increasing frequency of their occurrence,

  • possibility to export the transcript of the conversation to PDF and CSV files,

SCRIPTS AND TRIGGERS

  • scripts usage - number of script launches, number ofactions after script launch

  • forms

  • conversation history - full transcript all registered by the chat system with the ability to filter by the following types and included in search the word phrases:

  • question,

  • answer,

  • script name

  • all elements of the transcript are described with increasing frequency of their occurrence,

  • possibility to export the transcript of the conversation to PDF and CSV files,

GENERAL

  • visits - number of user visits in the module

  • unique users - number of users in the module

  • browsers and operating systems

How to train, augment the content and make interaction refinement of the Chatbot after launch

Based on analysis of reporting, the content is being refined in the form of:

Edits of existing Q&A / responses -> They are managed with the content administration tool

Adding new responses -> Adding responses, synonims, dictionaries etc

Adding new branches / labels in Knowledge base -> Adding totally new processes.