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

Expanding your Customer Experience with easy steps

Expanding your Customer Experience with easy steps

Lee Boonstra

May 25, 2018
Tweet

More Decks by Lee Boonstra

Other Decks in Technology

Transcript

  1. 1
    Expanding your customer
    experience in easy steps
    Lee Boonstra, Customer Engineer Google Cloud
    [email protected]

    View full-size slide

  2. 2
    Expanding your customer
    experience...
    Chatbots for websites or social media platforms. Voice activated speakers & smart assistants:

    View full-size slide

  3. 3
    ● End-to-end development suite for building
    conversational UI.
    ● Previously known as API.AI
    ● Sept 2016, acquired by Google
    ● Powered by Machine Learning
    Dialogflow

    View full-size slide

  4. 4
    Why Dialogflow
    ● Powered by Machine Learning (NLP)
    ● Scalable: separate your conversation text from
    code
    ● Build faster with the Web UI
    ● Advanced fulfillment options and multi channel
    integrations
    ● Analytics
    ● Speech / Voice Integration
    ● Multi-lingual bot support (20+ languages)
    ● Part of Google Cloud (60+ cloud services)
    Intent
    Recognition
    (NLP)
    ...
    Web Console
    Powerful
    SDK
    Supervised
    Training
    Cross-platfor
    m

    View full-size slide

  5. 5
    What’s new?
    ● Soon Dutch Assistant in the Netherlands!
    ● Six new voices
    ○ Including John Legend
    ○ Voices were created through
    Wavenet
    ● Smart Displays: Support for AoG table
    cards
    ● Dialogflow History Support
    ● Diagnostic Info
    ● Train Negative Fallback examples
    ● Dialogflow Enterprise in GA!

    View full-size slide

  6. 7
    Dialogflow Enterprise

    View full-size slide

  7. 8
    Part of Google Cloud also means:
    ● Easy integration /setup with 60+ products &
    services.
    Other advantages

    View full-size slide

  8. 9
    Part of Google Cloud also means:
    ● Easy integration /setup with 60+ products &
    services.
    ● Stay in the cloud. Improve latency & security.
    Other advantages
    User types in
    Web
    Interface
    Machine
    Learning
    Detection
    Call to
    Dialogflow
    Store in
    Data
    Warehouse
    Webhooks
    Return to
    customer
    vs.

    View full-size slide

  9. 10
    Part of Google Cloud also means:
    ● Easy integration /setup with 60+ products &
    services.
    ● Stay in the cloud. Improve latency & security.
    ● Logging, Tracing, Debugging, Error reporting
    Other advantages

    View full-size slide

  10. 11
    Part of Google Cloud also means:
    ● Easy integration /setup with 60+ products &
    services.
    ● Stay in the cloud. Improve latency & security.
    ● Logging, Tracing,Debugging, Error reporting
    ● User Roles, Permissions
    Other advantages

    View full-size slide

  11. 12
    Part of Google Cloud also means:
    ● Easy integration /setup with 60+ products &
    services.
    ● Stay in the cloud. Improve latency & security.
    ● Logging, Tracing,Debugging, Error reporting
    ● User Roles, Permissions
    ● Compliant
    Other advantages

    View full-size slide

  12. 13
    Part of Google Cloud also means:
    ● Easy integration /setup with 60+ products &
    services.
    ● Stay in the cloud. Improve latency & security.
    ● Logging, Tracing,Debugging, Error reporting
    ● User Roles, Permissions
    ● Compliant
    ● Scalable, No Ops
    Other advantages

    View full-size slide

  13. 14
    Upgrade to Enterprise

    View full-size slide

  14. Confidential + Proprietary
    Confidential + Proprietary
    Human take-over

    View full-size slide

  15. Confidential + Proprietary
    Human take-over chatflow with sentiment detection
    Your users type into a chat
    UI which can be integrated
    in your apps, websites or
    social media channels.
    When user ask to talk with
    a human, the operator can
    take over from the chatbot.
    Detect in real-time the
    users mood, and let the
    operator take over from the
    chatbot.
    This solution uses
    Kubernetes containers with
    Socket.io to enable
    realtime, bi-directional
    communication between
    web clients and servers.
    Architecture: Dialogflow with human handoff
    User types in chat UI
    Chatbot or User replies
    Operator Dashboard
    Kubernetes Engine
    Container Registry
    Customer Client
    Kubernetes Engine
    Back-end
    Kubernetes Engine
    Back-end
    Kubernetes Engine
    NLP
    API
    ML call for
    sentiment
    detection
    Pass user
    utterance to
    chatbot
    Return text response to user
    User asks
    to talk with human
    Negative sentiment
    let a human take over the conversation
    Operator types in chat UI
    User replies
    Containers images can be
    stored in the Container Registry
    Dialogflow
    Enterprise

    View full-size slide

  16. 17
    ● https://github.com/dialogflow/agent-human-handoff-nodejs
    Example available:

    View full-size slide

  17. Confidential + Proprietary
    Confidential + Proprietary
    Analytics
    Analyze and Optimize your bots

    View full-size slide

  18. 19
    ● Dialogflow bot analytics
    ● (From Chatbase)
    Bot Analytics

    View full-size slide

  19. 20
    ● New: Dialogflow
    conversation history
    History

    View full-size slide

  20. 21
    ● Custom implementation (Pub/Sub and BigQuery)
    ● Learn which questions has been asked the most
    ● Improve your bot over time
    ● Track user experience
    Chatbot User Analytics

    View full-size slide

  21. Confidential + Proprietary
    Confidential + Proprietary
    Machine Learning
    for Chatbots/Assistants

    View full-size slide

  22. 23
    ● Data Loss Prevention API
    Machine Learning APIs

    View full-size slide

  23. 24
    ● Data Loss Prevention API
    ● Natural Language API
    Machine Learning APIs

    View full-size slide

  24. 25
    ● Data Loss Prevention API
    ● Natural Language API
    ● Vision API
    Machine Learning APIs

    View full-size slide

  25. 26
    ● Data Loss Prevention API
    ● Natural Language API
    ● Vision API
    ● Speech to Text API
    ○ New: Text to Speech API
    Machine Learning APIs

    View full-size slide

  26. Confidential + Proprietary
    Confidential + Proprietary
    “Which customers are
    unhappy and why?”

    View full-size slide

  27. Confidential + Proprietary
    Confidential + Proprietary
    “How can I improve
    the user experience?”

    View full-size slide

  28. Confidential + Proprietary
    Confidential + Proprietary
    Demo
    https://github.com/savelee/kube-django-ng

    View full-size slide

  29. Confidential + Proprietary
    Advanced Chatflow with machine learning bot analytics
    User types to custom UI
    or channel
    Chatbot replies
    Dialogflow
    Enterprise
    Customer Client
    JS Angular 5 web front-end
    Kubernetes Engine
    Chat Server
    Dialogflow SDK / socket.io
    Kubernetes Engine
    Back-end CRM
    Python / Django
    Kubernetes Engine
    Container
    Registry
    Containers images can be
    stored in the Container Registry
    Messaging Publisher
    Pub/Sub
    Webhook
    Router
    Cloud Function
    Webhook
    Container
    Builder
    Building Dev
    Pipelines

    View full-size slide

  30. Confidential + Proprietary
    Advanced Chatflow with machine learning and bot analytics
    User types to custom UI
    or channel
    Chatbot replies
    Dialogflow
    Enterprise
    Customer Client
    JS Angular 5 web front-end
    Kubernetes Engine
    Chat Server
    Dialogflow SDK / socket.io
    Kubernetes Engine
    Back-end CRM
    Python / Django
    Kubernetes Engine
    Subscription
    Cloud Function
    Sensitivity
    Filter
    DLP API
    Sentiment
    Detector
    NLP API
    Data
    Warehouse
    BigQuery
    Messaging Publisher
    Pub/Sub
    Webhook
    Router
    Cloud Function
    Webhook

    View full-size slide

  31. 37
    I’ve built this demo on my own in a couple of evenings.
    Improve your user experience with a little more cloud.
    ● Fast & Easy integration of various cloud products:
    ○ Kubernetes Engine, Cloud Builder, Container Registry
    ○ Cloud Functions, Pub/Sub, BigQuery
    ○ DLP API, NLP API
    ● Cloud IAM, Logs, Traces, Debugging, Error reporting out of the box
    ● Scalable & Complaint: Ready to go live.
    Conclusion

    View full-size slide