Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Chatbots - a modern way of B2C communication

Chatbots - a modern way of B2C communication

1. Trends
2. Potential Benefits of Chatbots
3. Potential Blockers to Using Chatbots
4. Chatbot's types
5. NLP vs Response Buttons
6. Technologies
7. Live demo


Robert Witkowski

November 16, 2018

More Decks by Robert Witkowski

Other Decks in Programming


  1. Robert Witkowski, Senior Software Engineer, ASC LAB Chatbots - a

    modern way of B2C communication
  2. None
  3. Activity of chatbots discussion from Facebook IQ https://chatbotsmagazine.com/chatbot-report-2018-global-trends-and-analysis-4d8bbe4d924b

  4. Trends • The Chinese Bank OCBC sold loans worth 7

    000 000 dollars in three months using a chatbot; • Axis Bank’s chatbot (Active.ai) registered 3 million responses. In 97% of cases, chatbot correctly recognized the context and needs of clients; • 80% of marketers already use chatbots or intend to implement them within two years (Oracle research); • According to Grand View Research, the market will grow by 24.3% every year. By 2025 it will be worth 1.23 billion dollars; • According to Capgemini’s research, within 3 years the share of bots in conversations with clients may increase to 40%
  5. Who else? and 1200+ large corporations...

  6. None
  7. None
  8. Chatbot’s types • NLP (+ speech to text service) •

    Response Buttons • Hybrid
  9. NLP vs Response Buttons - User Freedom Users can speak

    freely and ask any question, also outside the domain https://chatbotsmagazine.com/chatbot-nlp-vs-response-buttons-70bcf0aa6a38 Users have to follow the conversational path, simply clicking on the available options
  10. NLP vs Response Buttons - Intent Comprehension Precision is understanding

    user’s requests is still around 60-70% https://chatbotsmagazine.com/chatbot-nlp-vs-response-buttons-70bcf0aa6a38 Clicking on the options, it’s basically impossible to make mistakes
  11. NLP vs Response Buttons - Surprise Effect Natural conversation creates

    surprise and curiosity https://chatbotsmagazine.com/chatbot-nlp-vs-response-buttons-70bcf0aa6a38 Less natural conversational flow may create limited enthusiasm
  12. NLP vs Response Buttons - Response Relevance Users might stop

    asking questions and miss in-depth information https://chatbotsmagazine.com/chatbot-nlp-vs-response-buttons-70bcf0aa6a38 Users are guided through different levels, deeper and deeper into the topic
  13. NLP vs Response Buttons - Domain Clarity It can be

    unclear what questions the bot can answer https://chatbotsmagazine.com/chatbot-nlp-vs-response-buttons-70bcf0aa6a38 Conversation topics are clear from the beginning
  14. Technologies • Ready-made solutions with a predefined domain (Emplocity, Edward.ai,

    InteliWise) • SaaS platforms (chatfuel for Messenger, botsify for web chat) • Frameworks (Microsoft Bot Framework, Botkit, Amazon Lex) • Natural Language Understanding Services (LUIS.ai, wit.ai, Watson, Dialogflow, RASA, Amazon Comprehend)
  15. Demo technologies • Microsoft Bot Builder SDK v3 • NodeJS

    – restify – request • LUIS.ai
  16. None
  17. Publications • Chatbot Demo on GitHub • Our first ChatBot

    • Chatbots and NLU - LUIS.ai and Microsoft Bot Framework integration
  18. DEMO LIVE CODING https://github.com/asc-lab/what-time-is-it-bot

  19. What’s next? • More Natural Language Understanding • Tensorflow Bot

    • Sentiment analysis
  20. 20 asc.altkom.pl github.com/asc-lab @AltkomSC asc-lab@altkom.pl