公开(公告)号：US20190146032A1

公开(公告)日：2019-05-16

申请号：US16138928

申请日：2018-09-21

Applicant: PDF Solutions, Inc.

Inventor： Brian Stine ,  Richard Burch ,  Nobuchika Akiya

IPC: G01R31/3177 ,  G01R31/317 ,  G06N20/00

Abstract: Disclosed is a system and method for collecting trace data of integrated circuits from the back-end assembly tools and using yield, reliability, and burn-in data to distinguish good circuit traces from bad ones. Described further is an system and method for implementing a heuristic mapping of trace data for distinguishing between good or bad traces in an Internet-based or offline application. The result of this detection can then be used for yield improvement or for burn-in reduction where for example burn-in chips having “good” circuit traces are subjected to thermal stress for less time than for chips identified as having “bad” circuit traces.

公开(公告)号：US10268562B1

公开(公告)日：2019-04-23

申请号：US15469352

申请日：2017-03-24

Applicant: PDF Solutions, Inc.

Inventor： Brian Stine ,  Richard Burch ,  Lijin Zhu

IPC: G06F17/18 ,  G06F19/00 ,  G06F11/34 ,  G06F11/30

Abstract: Described is a method of reducing multitudes of input data signals to a manageable plurality of input data signals and using the manageable plurality of input data signals to obtain response data that is provided to the semiconductor wafer, packaging, or design facility.

公开(公告)号：US12038802B2

公开(公告)日：2024-07-16

申请号：US17070520

申请日：2020-10-14

Applicant: PDF Solutions, Inc.

Inventor： Tomonori Honda ,  Richard Burch ,  John Kibarian ,  Lin Lee Cheong ,  Qing Zhu ,  Vaishnavi Reddipalli ,  Kenneth Harris ,  Said Akar ,  Jeffrey D David ,  Michael Keleher ,  Brian Stine ,  Dennis Ciplickas

IPC: G06N20/00 ,  G06F11/07 ,  G06F18/211 ,  G06F18/241 ,  G06F18/40 ,  H01L21/02 ,  G06F3/0482 ,  G06N3/08 ,  G06N7/01

CPC classification number: G06F11/079 ,  G06F11/0736 ,  G06F11/0751 ,  G06F11/0778 ,  G06F18/211 ,  G06F18/241 ,  G06F18/40 ,  G06N20/00 ,  H01L21/02 ,  G06F3/0482 ,  G06N3/08 ,  G06N7/01

Abstract: Classifying wafers using Collaborative Learning. An initial wafer classification is determined by a rule-based model. A predicted wafer classification is determined by a machine learning model. Multiple users can manually review the classifications to confirm or modify, or to add user classifications. All of the classifications are input to the machine learning model to continuously update its scheme for detection and classification.

公开(公告)号：US10656204B2

公开(公告)日：2020-05-19

申请号：US16138928

申请日：2018-09-21

Applicant: PDF Solutions, Inc.

Inventor： Brian Stine ,  Richard Burch ,  Nobuchika Akiya

IPC: G01R31/28 ,  G06F11/00 ,  G01R31/3177 ,  G06N20/00 ,  G01R31/317 ,  G06N3/04 ,  G06N3/08 ,  G06N20/10

Abstract: Disclosed is a system and method for collecting trace data of integrated circuits from the back-end assembly tools and using yield, reliability, and burn-in data to distinguish good circuit traces from bad ones. Described further is an system and method for implementing a heuristic mapping of trace data for distinguishing between good or bad traces in an Internet-based or offline application. The result of this detection can then be used for yield improvement or for burn-in reduction where for example burn-in chips having “good” circuit traces are subjected to thermal stress for less time than for chips identified as having “bad” circuit traces.