Intellexer Smart Chatbot Platform: Tech guide

In the last post, we did a general overview of the Smart Chatbot system. And now, for all the tech geeks out there, we dive deep into our internal processes and explore what technologies our Intellexer Smart Chatbot uses.

Platform components 

First off, our system consists of the following core parts:

  • Web crawler to download web content


  • Intellexer API for semantic analysis of natural texts in English


  • Text indexing and answer searching system


  • Knowledge base for storing suggestions (answers) and search index


  • Question generating system for creating questions from selected sentences

  • Online service that allows a user to type in an address of a webpage, send questions, and receive answers to them.

Our service generates questions automatically and includes:


  • Parsing of analyzed sentences


  • Various types of questions classification (who, what, when, where, why, yes/no questions)


  • Extraction of fragments from a sentence required to generate a question


  • Formation of grammatically correct questions

The data that the tool works with is grouped into the output and the input. The input for the system is the URL of a website that contains textual data.  

The output of the work is the following:

  • Knowledge base that includes automatically generated questions and answers from text on a webpage

  • A system for analyzing questions and identifying the most relevant answers

  • A chatbot that provides communication between a user and a product

Data pipeline

The system is based on the Intellexer Chatbot Platform: a user just enters an URL, and the tool downloads the textual content of the webpage. Then the system analyzes the extracted information using the cloud-based Intellexer API service. This service extracts sentences, concepts (noun phrases), and proper names from the webpage. 

Next step: the system forms a database containing sentences used as answers and the corresponding search index, where every token has its specific parameters. Parameters include part-of-speech tags, subject-predicate-object triplets, ontological class, and types of named entities. 

Based on this data, the tool automatically generates questions about major issues of the extracted information. Following these inner processes, a user is able to enter a question or choose among the generated ones — and get a well-structured answer.

Why use Smart Chatbot system

Just to quickly refresh your memory, here’s a quick overview of our system’s possibilities and benefits it provides:

  • Chatbot helps both customers and those who provide various services

  • Chatbots save time and resources, give more space for creativity, and allow you to concentrate on things that are more relevant: growing business.

  • With the help of a chatbot one doesn’t need to be online 24/7 to answer questions or monitor issues.

This list can go on for a long time! The potential of this technology is incredible, and we’ll be developing it further and improving in the coming months.Stay tuned! More updates are coming soon!. Try our system here:

February 15, 2022

Back to Blog Main Page

Get Started

Ask for Customization Register Demo Documentation API Console

API Usage Examples

These examples show basic Intellexer API usage variants
  • Sentiment Analyzer
  • Named Entity Recognizer
  • Summarizer
  • Multi-Document Summarizer
  • Comparator
  • Clusterizer
  • Natural Language Interface
  • Preformator
  • Language Recognizer
  • SpellChecker

Intellexer Summarizer

Application based on Intellexer API that performs:

  • Document summarization
  • Concept mining
  • Entity extraction
  • Summary rearrangement according to the selected items

Summarizer Network Edition

Note: After installation use your private API key to register the software. Number of requests per month and maximum size of the documents depend on your API key permissions.