Chatbot workshop introduction.#digitized16
0 likes690 views
The document discusses the evolution of mobile apps and their usage, highlighting that a significant portion of apps are seldom used while messaging remains dominant. It explores the role of machine learning in conversational user interfaces and the development of hybrid interfaces that blend command-line and graphical user experiences. Additionally, it emphasizes the importance of validating user input, understanding business objectives, and ensuring security and scalability in bot design.
Chatbot workshop introduction.#digitized16
- 1. Voice, Natural Language, Notifications, API, and Conversation How we build and design products in the future.
- 2. There are more than three million apps combined in all app stores An average smartphone user has 42 apps on his device but spends 90% of his time on only 9 or 10 of them. Present problem with UI
- 3. 25% of apps are only used once and 75% of users leave within the first three months. The growth of mobile and its app-centric world has been the opposite of the web, and there is no analog of PageRank for mobile apps.
- 4. Messaging is the most widely used application on the mobile platform, with chat-based apps Already, more than 15% search queries are made on Baidu using Voice Input.
- 5. HISTORICAL EVOLUTION The Story of New Platforms
- 6. PC Each platform requires recreation of the application layer, built and customized to grow and scale the new platform. Web Mobile
- 7. Time Mid-80’s Clients Websites Mobile apps Mid-90’s Mid-00’s Applications gestation phase growth phase PC era PC Desktop Web Browser Mobile iOS, Android Internet era Mobile era Key Product & Companies Paradigm Platform
- 8. HYPER GROWTH PHASE The shift is set to happen again
- 9. PAST PRESENT FUTURE human to human human to machine machine to machine
- 10. Google Mind Boston Dynamics-Atlas virtual reality & drones are just a glimpse of things to come.
- 11. The primary interface for interacting with apps might not be the app itself. The age of apps as service layers
- 12. How does it work? MACHINE LEARNING
- 13. MACHINE LEARNING Supervised Unsupervised Adaptive
- 14. A model is prepared through a training process where it is required to make predictions and is corrected when those predictions are wrong. The training process continues until the model achieves a desired level of accuracy on the training data. Supervised machine learning Classification
- 15. Clustering Learns patterns in input data when no specific output values are given. Unsupervised machine learning
- 16. Learns by an indication of correctness at the end of some reasoning. Environment observation Reward Action Adaptive/Reinforcement machine learning
- 17. A branch of machine learning based on a set of algorithms that attempt to model high level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and non-linear transformations. Neural Networks & Deep Learning
- 18. The experiment started with a machine learning algorithm and a database of over 10,000 songs from more than 100 rap artists. The machine produces rap lyrics that rival human-generated ones for their complexity of rhyme. The words must first be converted into phonemes. Finding rhymes is then simply a question of scanning the phonemes looking for similar vowels sounds How machine Mines Rap Lyrics and Writes Its Own
- 19. For a chance at romance I would love to enhance But everything I love has turned to a tedious task One day we gonna have to leave our love in the past I love my fans but no one ever puts a grasp I love you momma I love my momma – I love you momma And I would love to have a thing like you on my team you take care I love it when it’s sunny Sonny girl you could be my Cher I’m in a love affair I can’t share it ain’t fair Haha I’m just playin’ ladies you know I love you. I know my love is true and I know you love me too Girl I’m down for whatever cause my love is true This one goes to my man old dirty one love we be swigging brew My brother I love you Be encouraged man And just know When you done let me know cause my love make you be like WHOA If I can’t do it for the love then do it I won’t All I know is I love you too much to walk away though Lyrics
- 20. CONVERSATIONAL UI The rise of hybrid Interfaces
- 21. Command-line The command line was the original conversational interface. You’d input a textual command, hit enter, the computer would execute the command and print the answer.
- 22. IRC IRC already supported bots, massive group chat quizzes, polls and other types of conversational applications
- 23. Each message becomes a mini app Blended interfaces, bringing the best of the command line and GUI paradigms together.
- 24. OPERATOR Companies like Operator are leading the way, designing rich experiences their clients can interact with directly, not by replying simply with text.
- 25. First impressions & Expectations “Take me to the moon, Bot!”
- 26. Introduce yourself You only get one or two lines, so keep it short and to the point. Having no visible interface means: This thing can do whatever I ask him, so I’m going to ask him to make me a sandwich. I have no idea what I’m supposed to do now, so I’m just going to freeze and stare at the screen.
- 27. Meeting synced! Did you know I can also find and book a conference room? Ping! There is a meeting coming up in one hour. Would you like me to order lunch for 3 people? Once the first interactions are successful, the robot can be less verbose and more efficient. Proactively suggest things to do. Great! Find us some sushi! Ping! There is a meeting coming up. Would you like me to order lunch for 3?
- 28. Validating input _Give hints _Aknowledge Small please! Thanks. Great! Find us some sushi! Ping! There is a meeting coming up. Would you like me to order lunch for 3? What size t-shirt are you? We have small, medium, large. Got it. Size small. And what color would you like?
- 29. Explain what went wrong... brlbrbl gray I’m sorry, “brbrbl”? Is that a color? We have white, gray, brown. What color would you like? Cool! So a large gray t-shirt!
- 30. Awaiting critical input Sometimes you need a piece of information that you absolutely cannot proceed without.
- 31. Schedule a new meeting tomorrow? Am I busy tomorrow? To do my job, I need access to your schedule. Follow this link to connect your calendar. Seriously, you need to connect your calendar here to enjoy my scheduling superpowers. I can’t wait to start working on your schedule! Please connect your calendar so I can do my magic.
- 32. What you need to consider BUSINESS CASES FOR BOTS
- 34. (Most valuable bot} Start with looking at the overarching business objectives. _What are the business priorities this year? _Acquisition? _Retention? _What KPIs can we identify to measure value? _What point in the customer journey does this fit? YOUR MVB
- 35. _Brand guidelines _Tone of voice _Consumers have different degrees of tolerance _Script out anticipated conversations and review _Decide how much of your UI will be conversation driven rather than manual _Quality NLP and some degree of AI or machine learning. _Lean on the universal UI _Remember: GUIs > DOS Conversational Design Vs User Interface Design Personality
- 36. _Store data securely and inline with any privacy agreements _Don’t ever break Facebook or any other platforms’ guidelines _Brand reputation can be fatal. _Pick a solution that can scale up or down quickly. _Allow reprioritisation and user testing to happen throughout the build _Establish a group of testers _Market your bot. Security, Rules & Data Scale Development, Testing & Promotion