公开(公告)号：US20130297547A1

公开(公告)日：2013-11-07

申请号：US13799337

申请日：2013-03-13

Applicant: QUALCOMM Incorporated

Inventor： Li Ding ,  Vidya Narayanan ,  Jin Won Lee ,  Lukas D. Kuhn ,  Leonard Henry Grokop ,  Shankar Sadasivam ,  Alexandros Manolakos

IPC: G06N5/02

CPC classification number: G06N5/02 ,  H04M1/72563 ,  H04M2250/12

Abstract: Methods, systems, computer-readable media, and apparatuses for inferring context are provided. In one potential implementation, first context information associated with a first duration is identified, second context information is accessed to determine a context segmentation boundary; and the first context information and the second context information is then aggregated to generate an inferred segmented aggregated context. In a further implementation, the first context information is used to average inferred contexts, and the context segmentation boundary is used to reset a start time for averaging the first context information.

Abstract translation: 提供了用于推断上下文的方法，系统，计算机可读介质和装置。 在一个潜在实现中，识别与第一持续时间相关联的第一上下文信息，第二上下文信息被访问以确定上下文分段边界; 然后聚合第一上下文信息和第二上下文信息以生成推断的分段聚合上下文。 在进一步的实现中，第一上下文信息用于平均推断的上下文，并且使用上下文分段边界来重置用于平均第一上下文信息的开始时间。

公开(公告)号：US09582755B2

公开(公告)日：2017-02-28

申请号：US13799337

申请日：2013-03-13

Applicant: QUALCOMM Incorporated

Inventor： Li Ding ,  Vidya Narayanan ,  Jin Won Lee ,  Lukas D. Kuhn ,  Leonard Henry Grokop ,  Shankar Sadasivam ,  Alexandros Manolakos

IPC: G06F17/00 ,  G06N5/02 ,  H04M1/725

CPC classification number: G06N5/02 ,  H04M1/72563 ,  H04M2250/12

Abstract: Methods, systems, computer-readable media, and apparatuses for inferring context are provided. In one potential implementation, first context information associated with a first duration is identified, second context information is accessed to determine a context segmentation boundary; and the first context information and the second context information is then aggregated to generate an inferred segmented aggregated context. In a further implementation, the first context information is used to average inferred contexts, and the context segmentation boundary is used to reset a start time for averaging the first context information.

Abstract translation: 提供了用于推断上下文的方法，系统，计算机可读介质和装置。 在一个潜在实现中，识别与第一持续时间相关联的第一上下文信息，访问第二上下文信息以确定上下文分段边界; 然后聚合第一上下文信息和第二上下文信息以生成推断的分段聚合上下文。 在进一步的实现中，第一上下文信息用于平均推断的上下文，并且使用上下文分段边界来重置用于平均第一上下文信息的开始时间。