公开(公告)号：US10691114B2

公开(公告)日：2020-06-23

申请号：US15989219

申请日：2018-05-25

Applicant: Industrial Technology Research Institute

Inventor： Pang-Min Shih ,  Shan-Ming Chang

IPC: G05B19/418

Abstract: A method for dynamic intelligent scheduling includes following steps: collecting and recording resource constraints of multiple schedules on a production line and decision data of changes made to the schedules by a scheduler; cross-enumerating schedule combinations by using multiple production goals as penalty conditions; establishing a mathematical model based on the resource constraints and multi-objective weights corresponding to each schedule combination and importing the resource constraints to calculate schedule results; recording the penalty condition corresponding to the schedule combination matching the decision data as a valid penalty; using values of parameters corresponding to the valid penalty and values of the penalty conditions respectively as inputs and outputs to train a learning model; and responding to a scheduling request, finding a weight of each schedule combination by using the learning model according to the resource constraint of the current schedule and the production goals, and generating a recommended schedule accordingly.

公开(公告)号：US20250103751A1

公开(公告)日：2025-03-27

申请号：US18896914

申请日：2024-09-26

Applicant: Industrial Technology Research Institute

Inventor： Bo-Cheng Chiou ,  Chih-Sheng Lin ,  Tuo-Hung Hou ,  Chih-Ming Lai ,  Yun-Ting Ho ,  Shan-Ming Chang

IPC: G06F21/62 ,  G06F21/72 ,  H04L9/32

Abstract: A computing circuit with a de-identified architecture, a data computing method, a data processing system, and a data de-identification method are provided. The computing circuit includes an arithmetic array and a de-identification circuit. The computing circuit may perform an accumulation operation on input data to generate accumulated data by the arithmetic array. The de-identification circuit has an analog offset error determined based on an analog physical unclonable function. The computing circuit may operate the accumulated data according to the analog offset error to generate de-identification data by the de-identification circuit. It can not only provide the analog offset error through the transistors in the de-identification circuit, but also be combined with obfuscated code settings to dynamically adjusting the degree of de-identification of data.

公开(公告)号：US20190227533A1

公开(公告)日：2019-07-25

申请号：US15989219

申请日：2018-05-25

Applicant: Industrial Technology Research Institute

Inventor： Pang-Min Shih ,  Shan-Ming Chang

IPC: G05B19/418

Abstract: A method for dynamic intelligent scheduling includes following steps: collecting and recording resource constraints of multiple schedules on a production line and decision data of changes made to the schedules by a scheduler; cross-enumerating schedule combinations by using multiple production goals as penalty conditions; establishing a mathematical model based on the resource constraints and multi-objective weights corresponding to each schedule combination and importing the resource constraints to calculate schedule results; recording the penalty condition corresponding to the schedule combination matching the decision data as a valid penalty; using values of parameters corresponding to the valid penalty and values of the penalty conditions respectively as inputs and outputs to train a learning model; and responding to a scheduling request, finding a weight of each schedule combination by using the learning model according to the resource constraint of the current schedule and the production goals, and generating a recommended schedule accordingly.