-
Patent Agency Ranking
公开(公告)号：US20210042587A1
公开(公告)日：2021-02-11
申请号：US16534582
申请日：2019-08-07
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Edward Vitkin , Igor Kostirev-Kronos , Alex Melament , Yardena Lia Peres
Abstract: Time-series data uncertainty reduction can include generating an initial accumulated signal based on an event classifier prediction score. The event classifier prediction score can be generated by an event predicator based on time-series data and can correspond to a probability that a target event occurs. Signal leakage can be imposed on the initial accumulated signal. Additionally, an alert can be generated in response to determining that the initial accumulated signal is greater than an alert threshold.
-
公开(公告)号：US20190279752A1
公开(公告)日：2019-09-12
申请号：US15917906
申请日：2018-03-12
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Edward Vitkin , Alex Melament , Yardena L. Peres , Yevgenia Tsimerman , Igor Kostirev-Kronos , Pamela A. Nesbitt , Gigi Yuen-Reed , Navot Naor
Abstract: Embodiments of the present invention disclose a method, computer program product, and system for generating medical treatment adherence improvement protocols associated with a target patient. A hierarchical map is received. A query is received to generate an improvement protocol. A patient adherence profile associated with the target patient is generated based on target patient data and corresponding one or more dimensions. An influence value is applied to each corresponding one or more dimensions based on the generated patient adherence profile. A set of dimensions is identified of the corresponding one or more dimensions associated with an influence value crossing a threshold. One or more goals are identifying associated with the target patient. An adherence improvement protocol is generated based on identified one or more goals. User input is received, in response to communicating the generated adherence improvement protocol. The adherence profile, identified goals, and adherence improvement protocol are modified.
-
公开(公告)号：US11763199B2
公开(公告)日：2023-09-19
申请号：US17128201
申请日：2020-12-21
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Edward Vitkin , Igor Kostirev-Kronos , Alex Melament , Yardena Lia Peres
IPC: G06N20/00 , G06F18/2415 , G06F18/21
CPC classification number: G06N20/00 , G06F18/21 , G06F18/2415 , G06F2218/00
Abstract: Time-series data uncertainty reduction can include generating an initial accumulated signal based on an event classifier prediction score. The event classifier prediction score can be generated by an event predicator based on time-series data and can correspond to a probability that a target event occurs. Signal leakage can be imposed on the initial accumulated signal. Additionally, an alert can be generated in response to determining that the initial accumulated signal is greater than an alert threshold.
-
公开(公告)号：US11755945B2
公开(公告)日：2023-09-12
申请号：US16534582
申请日：2019-08-07
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Edward Vitkin , Igor Kostirev-Kronos , Alex Melament , Yardena Lia Peres
IPC: G06N20/00 , G06F18/2415 , G06F18/21
CPC classification number: G06N20/00 , G06F18/21 , G06F18/2415 , G06F2218/00
Abstract: Time-series data uncertainty reduction can include generating an initial accumulated signal based on an event classifier prediction score. The event classifier prediction score can be generated by an event predicator based on time-series data and can correspond to a probability that a target event occurs. Signal leakage can be imposed on the initial accumulated signal. Additionally, an alert can be generated in response to determining that the initial accumulated signal is greater than an alert threshold.
-
公开(公告)号：US20210110216A1
公开(公告)日：2021-04-15
申请号：US17128201
申请日：2020-12-21
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Edward Vitkin , Igor Kostirev-Kronos , Alex Melament , Yardena Lia Peres
Abstract: Time-series data uncertainty reduction can include generating an initial accumulated signal based on an event classifier prediction score. The event classifier prediction score can be generated by an event predicator based on time-series data and can correspond to a probability that a target event occurs. Signal leakage can be imposed on the initial accumulated signal. Additionally, an alert can be generated in response to determining that the initial accumulated signal is greater than an alert threshold.
-
-
-
-
Search Results
5
records
(took 0.014 seconds)
