Conversational commerce: emerging architectures for smart & useful chatbots
•Download as PPTX, PDF•
0 likes•376 views
Smart speakers and messaging apps are increasing in popularity due to their convenience, intuitive usage, and new user experiences. Companies are racing to develop voice interfaces and AI technologies in order to utilize smart speakers and messaging platforms as a sales channel. Introducing Grid Genie, a completely open source, multi-device conversational commerce platform. With this technology, we can help you engineer a powerful platform to combine your Alexa skills, Google actions, and Facebook Messenger into a single seamless experience.
Recommended
Recommended
More Related Content
Similar to Conversational commerce: emerging architectures for smart & useful chatbots
Similar to Conversational commerce: emerging architectures for smart & useful chatbots (20)
More from Grid Dynamics
More from Grid Dynamics (20)
Recently uploaded
Recently uploaded (20)
Conversational commerce: emerging architectures for smart & useful chatbots
- 1. Conversational commerce: Founder and CTO Victoria Livschitz emerging architectures for smart & useful chatbots
- 2. 2 About the speaker • CTO of Grid Dynamics from 2015 • Founder & CEO of Grid Dynamics from 2006 to 2015 • Principal architect of SunGrid, world’s first public cloud by Sun Microsystems, 2004-2006 • Entrepreneur, technologist, poker player, mountain climber, mother of 3
- 3. Emerging Mainstream Legacy 2018 2006 3 About Grid Dynamics, the experts in emerging technologies Cloud Devops Big data Cloud Devops Big data AI NLP ML Java RDBMS .NET Java RDBMS .NET Java RDBMS .NET
- 4. Emerging Mainstream Legacy 2018 2006 4 About Grid Dynamics, the experts in emerging technologies Cloud Devops Big data Cloud Devops Big data AI NLP ML Java RDBMS .NET Java RDBMS .NET Java RDBMS .NET 1,000-people strong global engineering services company In digital transformation thru emerging technology
- 5. 5 Thesis: voice commerce is the next big thing after mobile Voice devices entering households • 9M smart voice devices shipped in Q1 2018 • 50% household penetration expected by 2022 • IOT makes voice control an expected feature Massive investment • From tech giants – over $1B IBM Watson, etc. • From VC - over $700M in 2017 • 20 AI acquisitions – siri, api.ai, viv Technology advances by leaps and bounds • Speech2text approaches human quality • Deep learning-based NLU / NER enters mainstream • Plethora of AI platforms on the market Better interface for many digital interactions • Reduces engagement barrier • Perfect for search, Q&A • Interactive clarification of intent
- 6. Conversational commerce: • Deep, branched conversation • Discovery, selection, recommendation • Large result sets, ambiguity, comparisons • Deep integration with search, catalog, ontology • Customer-trained NLU • Smart dialog management to arbitrate and orchestrate multiple models Other “deep” conversational applications 6 Types of CUI experience Infobot: • Fact-oriented • Few intent-reply patterns Shallow, linear conversation Virtual assistant: • Task-oriented • Few intent-entity-reply patterns Smalltalk: entertainment, empathy, human mimicry
- 7. Other “deep” conversational applications Conversational commerce: • Deep, branched conversation • Discovery, selection, recommendation • Large result sets, ambiguity, comparisons • Deep integration with search, catalog, ontology • Customer-trained NLU • Smart dialog management to arbitrate and orchestrate multiple models 7 Types of CUI experience Infobot: • Fact-oriented • Few intent-reply patterns Shallow, linear conversation Virtual assistant: • Task-oriented • Few intent-entity-reply patterns Smalltalk: entertainment, empathy, human mimicry
- 8. Grid Genie: Conversational platform by Grid Dynamics R&D project from Grid Labs
- 9. 9 Conversational platform design principles • 100% open and free: written using open source technologies in pluggable architecture • Multiple devices: supports Google Home, Alexa, Siri, etc. via device adapters • Multiple channels: voice-based, text-based, web-based via channel adapters • Multiple skills: specific dialog skills can be added (promo, checkout, order tracking) • Multiple models: mix, match and use best-of-breed ML/NLU models for specific tasks • Integrated with backend services via layers of platform services and enterprise adapters • Containerized for seamless on premise or cloud deployment
- 10. 1010 Conversational commerce blueprint dialog skills domain skills channeladapter enterpriseadapters enterprise services ontology recommend catalog search data mining / ML dialog manager context intent API NLU API NLG API search discovery factoid recommend notifications smalltalk checkout loyalty order promo
- 11. Grid Genie Demo
- 12. 1212 Conversational commerce blueprint dialog skills domain skills channeladapter enterpriseadapters enterprise services ontology recommend catalog search data mining / ML dialog manager context intent API NLU API NLG API search discovery factoid recommend notifications smalltalk checkout loyalty order promo
- 13. 13 Microservices architecture Intent Classifier Dialog ManagerAmazon Alexa Discovery Agent Google Home Facebook WISMO Agent Small Talk Agent Catalog Service Order API Adapter Auth Service Adapter Catalog ETL Order API OAuth2.0 Bulk Catalog API Search Service Order Search Service Shipment Service Auth Service Shipment API Dialog Services Channel Adapters Agents Platform Services Adapters Store Context Platform Storage MongoDB Product Elastic Search NLG Ontology Service Order Indexing Service Catalog Ingestion Public API Shipment Service Adapter Order
- 14. 14 To learn more • Subscribe to our blog: blog.griddynamics.com
- 15. Q&A
- 16. Appendix
- 17. 17 Conversational platform components Service Description Responsibilities Channel adapters Connect the platform to edge devices Account linking, Auth, SSO, user management Context Context keeps dialog state Shares context between devices and interactions Dialog manager Controls conversation flow maintains conversation context, detects the customer’s broader intent, delegates tasks to an appropriate dialog agent Pluggable dialog agents Implement narrow conversation flow execute particular use case, communicate with NLU, enterprise adapters to fulfill the actions, use NLG to form natural language response Dialog services NLU/NLG/NER service adapters and implementations Provide NLG/NLU/NER capabilities Enterprise adapters Connect agents to data and services Provide access to enterprise APIs Domain ontology Capture domain knowledge deep understanding of business domain, its terminology, slang, and the relationship between terms
- 18. • Neo4J Implementation: 18 • BabelNet • WordNet • DBpedia Content sources: Domain specific ontology aperture f-stop camera telescope diaphragm f-number PART_OF PART_OF SYN SYN SYN
- 19. CNN based model for intent classification Privileged and Confidential 19 Intent classification Can you suggest me an action camera? CLASS PROB ACCEPT 0.01 DENY 0.001 NEXT 0.05 PREVIOUS 0.012 REQUEST 0.011 RESET 0.03 … … WISMO 0.05 DISCOVERY 0.81 SELECTION 0.1 ORDER 0.05 SMALLTALK 0.02 … … suggest recommend action GloVe/fasttext word embedding Matrix representation CNN: Conv layers Pooling Fully Connected
- 20. BiLSTM based model for entity tagging Privileged and Confidential 20 Named entity recognition: BIO tagging BIO tags (Beginning, Inside, Outside) I need diving camera under two hundred bucks GloVe/fasttext word embedding Matrix representation softmax BiLSTM BiLSTM BiLSTM BiLSTM BiLSTM BiLSTM BiLSTM BiLSTM RNN O O B-purpose B-device_name B-relational B-quantity I-quantity B-unit I need diving camera under two hundred bucks O O B-purpose B-device_name B-relational B-quantity I-quantity B-unit
- 21. Privileged and Confidential 21 Named entity recognition: tag grouping unrelated related related related relatedto predict Linear XGBoost model is trained to make binary classification for token pairs I need diving camera under two hundred bucks O O B-purpose B-device_name B-relational B-quantity I-quantity B-unit
- 22. About Grid Dynamics Founded in 2006, Grid Dynamics is an engineering services company built on the premise that cloud computing is disruptive within the enterprise technology landscape. Since that time, we’ve had the privilege to help companies like Microsoft, eBay, PayPal, Cisco, Macy’s, Yahoo, ING, Bank of America, Kohl's, among others, to re- architect their core mission-critical systems, develop new cloud services, accelerate innovation cycles, increase software quality, and automate application management. Grid Dynamics has multiple locations in the USA and Europe, and employs over 1,000 expert engineers worldwide. Privileged and Confidential 22
Editor's Notes
- https://www.canalys.com/newsroom/google-beats-amazon-to-first-place-in-smart-speaker-market Reduces engagement barrier: talking is easy, even kids can interact with voice bot IOT voice devices: https://www.globalme.net/blog/best-voice-controlled-devices-market https://www.microsoft.com/en-us/research/blog/microsoft-researchers-achieve-new-conversational-speech-recognition-milestone/ Auire high quality intent: one of the problems of keyword search is that people are too lazy to type their intent. They prefer keywords. Voice channel allows for longer phrases with more content.
- Only few players will survive long term Strategies: Amazon - cloud ecosystem and retail focus, Google - strong ML capabilities, IBM with deep insight and vertical focus on health and law, Microsoft focuses on employee and enterprise
- Only few players will survive long term Strategies: Amazon - cloud ecosystem and retail focus, Google - strong ML capabilities, IBM with deep insight and vertical focus on health and law, Microsoft focuses on employee and enterprise