Microsoft AI Overview: Cognitive Services
Download as PPTX, PDF1 like255 views
The document outlines a strategy for developing advanced AI-infused platforms and services focused on cloud and edge computing. It highlights various capabilities of Azure AI services, including cognitive services for speech, language, and image recognition, as well as tools for building bots and data analysis. The document also illustrates how Azure Machine Learning can be integrated with tools like Excel for seamless data analysis.
Microsoft AI Overview: Cognitive Services
- 2. Our strategy is to build best-in-class platforms and productivity services for an intelligent cloud and an intelligent edge infused with artificial intelligence (“AI”). 2017 Annual Report
- 4. Azure AI Services Azure Infrastructure Tools
- 8. Cognitive Services CapabilitiesInfuse your apps, websites, and bots with human-like intelligence Speech Language Knowledge SearchVision Speech to text (Speech Transcription) Speaker ID and authentication Customized speech Transcription (complex word, noisy environment) Real-time speech translation Spell checking Contextual language understanding – customized intent analysis Sentiment analysis, key phrase detection text translation up to 60+ languages Customized decision making with reinforcement learning Q&A service and bot training Automatic search suggestions Comprehensive news, image, and video results Entity information augmentation Tailored and customized search experiences Image Tagging, Thumbnails OCR, Handwriting recognition Customized image recognition Face detection Video insights - people detection, visual search, keyframe detection, object recognition Image and video moderation Labs Entity Identification and Linking Academic Content Index and search Knowledge Content index and search Augmented entity information Tailored search experiences Text Moderation Emotion recognition Text to speech
- 9. 147,000 total bots registered >3200 bots created per week Azure Bot Service (50%), Self Host (50%) >7700 daily active bots (DAU)
- 10. Description Component QnA QnA Maker (CS) Form filling Forms (Builder SDK) Query over custom database (e.g: people data) Azure Search (Azure) Graphical UX: cards & buttons Adaptive Cards Language Understanding LUIS (CS) Text to speech Text to Speech (CS) Speech Custom Speech (CS) Realtime translation Speech translation (CS), Text translation (CS) Spell check Bing Speller (CS) Prebuilt domains for common content types: time, numbers, places, etc. Cortana prebuilt domains & LUIS Conversation analytics App Insights (Azure) Payments Payments (Builder SDK) Authentication Authentication (Builder SDK) Cortana as a co-assistant Cortana skills Bing Knowledge Graph Bing Knowledge Extensiblity: integrate 1st & 3rd party components via code via Builder SDK CS + Bot Framework = Comprehensive Bot Platform
- 11. Apps + insights Social LOB Graph IoT Image CRM INGEST STORE PREP & TRAIN MODEL & SERVE Data orchestration and monitoring Data lake and storage Python, Spark, and Deep Learning Prebuilt: Cognitive Services Custom: Azure Machine Learning IoT AI Dev Platform for Systems of intelligence
- 12. An analyst opens a spreadsheet with raw data and wants to analyze it
- 13. The analyst starts typing a function name that her team’s data scientist published in Azure ML.
- 14. The analyst reads the description of the function to determine whether it applies to the task at hand.
- 15. Upon selecting the function, the analyst is prompted to select the necessary input data from Excel.
- 16. The analyst selects the cells which contain the data she wants to analyze.
- 17. The analyst hits Enter to trigger the function, sending a web request to the Azure ML service.
- 18. The results return from Azure ML and are inserted in the Excel sheet
- 19. The analyst uses other tools in Excel to understand the results better.