公开(公告)号：US12087434B2

公开(公告)日：2024-09-10

申请号：US16868597

申请日：2020-05-07

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： Liyi Xu ,  Junzi Dong

IPC: G16H40/20 ,  G16H10/60 ,  G16H15/00 ,  G16H50/20 ,  G16H50/70

CPC classification number: G16H40/20 ,  G16H10/60 ,  G16H15/00 ,  G16H50/20 ,  G16H50/70

Abstract: A method and system for predicting the next location for a patient in a healthcare facility, including: defining a location-procedure co-occurrence matrix for the healthcare facility, wherein the location-procedure co-occurrence matrix define the probability that a procedure will be performed in a specific location; defining a procedure transition matrix, wherein the procedure transition matrix defines the probability of moving from a first procedure to a second procedure; defining a patient input vector based upon the patient condition and procedures performed on the patient; calculating an output vector based upon the patient input vector and the procedure transition matrix; producing a procedure vector by setting all values in the output vector to zero except for the N highest values in the output vector, where N is an integer; calculating a location prediction vector based upon the procedure vector and the location-procedure co-occurrence matrix; and transmitting information regarding the M most likely next locations for the patient to a display device.

公开(公告)号：US11651289B2

公开(公告)日：2023-05-16

申请号：US16531189

申请日：2019-08-05

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： Bryan Conroy ,  Junzi Dong ,  Minnan Xu

IPC: G06K9/62 ,  G06N3/08 ,  G06N20/00

CPC classification number: G06K9/6256 ,  G06K9/6262 ,  G06N3/08 ,  G06N20/00

Abstract: A method of implementing a task complexity learning system, including: learning a model for predicting the value of a continuous task variable y based upon an input variable x; learning an encoder that encodes a continuous task variable y into an encoded task value; calculating a loss function based upon the predicted value of y output by the model and the encoded task value output by the encoder; calculating a distortion function based upon the input continuous task variable y and the encoded task value, wherein learning the model and learning the encoder includes minimizing an objective function based upon the loss function and the distortion function for a set of input training data including x, y pairs.

公开(公告)号：US20200050892A1

公开(公告)日：2020-02-13

申请号：US16531189

申请日：2019-08-05

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： Bryan Conroy ,  Junzi Dong ,  Minnan Xu

IPC: G06K9/62 ,  G06N20/00 ,  G06N3/08

Abstract: A method of implementing a task complexity learning system, including: learning a model for predicting the value of a continuous task variable y based upon an input variable x; learning an encoder that encodes a continuous task variable y into an encoded task value; calculating a loss function based upon the predicted value of y output by the model and the encoded task value output by the encoder; calculating a distortion function based upon the input continuous task variable y and the encoded task value, wherein learning the model and learning the encoder includes minimizing an objective function based upon the loss function and the distortion function for a set of input training data including x, y pairs.