![]() Bot gets additional information for barcodes.Bot gets additional information from Bing Entity Search for rich context on people, place, artwork, monument, and objects.Bot passes visual context (that is, image) to the Bing Visual Search API.Bot understands user intent and conversational context by using LUIS, which is built into the application.Users interact with Bot through mobile app or web app.ArchitectureÄownload an SVG of this architecture. Visual assistant provides rich information based on content of the image with capabilities such as reading business card, identifying barcode, and recognizing popular people, places, objects, artworks, and monuments. ![]() If you'd like to see us expand this article with more information, such as potential use cases, alternative services, implementation considerations, or pricing guidance, let us know with GitHub Feedback!
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |