Microsoft Technology Licensing, LLC

Edward Un

Hua Li

Jun Zhao

Max Leung

Zhifeng Wang

Kaiyan Tian

Kai Wang

Jun Hong Zhao

John Ian Ferrell

Mattias Beermann

Techniques for selecting an emotion type code associated with semantic content in an interactive dialog system. In an aspect, fact or profile inputs are provided to an emotion classification algorithm, which selects an emotion type based on the specific combination of fact or profile inputs. The emotion classification algorithm may be rules-based or derived from machine learning. A previous user input may be further specified as input to the emotion classification algorithm. The techniques are especially applicable in mobile communications devices such as smartphones, wherein the fact or profile inputs may be derived from usage of the diverse function set of the device, including online access, text or voice communications, scheduling functions, etc.

Emotion type classification for interactive dialog system

Among other things, one or more techniques and/or systems are provided for locating a position within an enclosure. In one example, known global coordinates (e.g., GPS coordinates of latitude/longitude) associated with the position within the enclosure may be transformed into local coordinates (e.g., x/y coordinates) for the position. The local coordinates may be used for tracking a location of the position within the enclosure. In another example, known local coordinates of the position within the enclosure may be transformed into global coordinates for the position, which may be used for tracking a location of the position within the enclosure. In another example, a blueprint image of the enclosure may be used to track a location of the position within the enclosure. In this way, location tracking may be provided for objects within indoor spaces (e.g., a mapping application may track a current position of a mobile device within a building).

Locating position within enclosure

Techniques for utilizing APs and messaging service for delivering personalized message to individual mobile devices connected to internet through APs. In one example embodiment, for any particular wireless AP, a set of messages are identified based at least in part on attributes of the service subscriber associated with the particular wireless AP; and the set of messages are distributed to the particular wireless AP for further distribution to wireless devices in the vicinity of the particular wireless AP.

WiFi proximity messaging

Growing community of inventors

Beijing, China

Edward Un