Testing, Launching and post - launch optimization

Standard (manual) testing

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 [e-mail]

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.