公开(公告)号：WO2019139760A1

公开(公告)日：2019-07-18

申请号：PCT/US2018/066627

申请日：2018-12-20

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： KIEMELE, Kenneth Liam ,  HESKETH, John Benjamin ,  JONES, Evan Lewis ,  NANCE, James Lewis ,  SMITH, LaSean Tee

IPC: G06N20/20 ,  G06K9/00 ,  G06K9/62

CPC classification number: G06K9/6227 ,  G06K9/00335 ,  G06K9/00362 ,  G06K9/00771 ,  G06K9/3233 ,  G06K9/6262 ,  G06K9/6288 ,  G06N20/00 ,  G06N20/20 ,  G06T7/75 ,  H04W4/70

Abstract: Techniques for generating a machine learning model to detect event instances from physical sensor data, including applying a first machine learning model to first sensor data from a first physical sensor at a location to detect an event instance, determining that a performance metric for use of the first machine learning model is not within an expected parameter, obtaining second sensor data from a second physical sensor during a period of time at the same location as the first physical sensor, obtaining third sensor data from the first physical sensor during the period of time, generating location-specific training data by selecting portions of the third sensor data based on training event instances detected using the second sensor data, training a second ML model using the location-specific training data, and applying the second ML model instead of the first ML model for detecting event instances.

公开(公告)号：WO2019152199A1

公开(公告)日：2019-08-08

申请号：PCT/US2019/013888

申请日：2019-01-17

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： LONG, Donna Katherine ,  CHOI, Jennifer Jean ,  GANADAS, Priya ,  CABACCANG, Jamie R. ,  SMITH, LaSean Tee ,  KIEMELE, Kenneth Liam ,  JONES, Evan L. ,  HESKETH, John Benjamin ,  HAWTHORNE, Bryant Daniel

IPC: G06Q10/06 ,  G06Q30/02 ,  G06Q20/20

CPC classification number: G06F16/9535 ,  G06F16/29 ,  G06Q10/0639 ,  G06Q20/127 ,  G06Q20/202 ,  G06Q20/3224 ,  G06Q30/0201 ,  G06Q30/0205 ,  G06Q30/0631 ,  G07F17/246

Abstract: A computer system is provided that includes a server configured to store a plurality of location accounts, each location account being associated with a physical space at a recorded geospatial location. The plurality of location accounts utilize shared data definitions of a physical space parameter. Each physical space is equipped with a corresponding on-premise sensor configured to detect measured values for the physical space parameter over time and send to the server a data stream indicating the measured values. The computer system further includes a network portal, via which an authorized user for a location account can selectively choose whether to share the measured values or a summary thereof with other location accounts via the network portal.