IP Library Granted Patent US 12,456,041
Granted Patent B2
US 12,456,041 · App. 17/436,467 · Granted Oct 28, 2025

AI system and operation method of AI system

Inventors: Hajime Kimura (Kanagawa, JP); Rihito Wada (Kanagawa, JP); Masayuki Kimura (Kanagawa, JP); Yoshiyuki Kurokawa (Kanagawa, JP); Takeshi Aoki (Kanagawa, JP)
Assignee: Semiconductor Energy Laboratory Co., Ltd.
G06N3/063G06F16/93G06F30/327
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,456,041
App. No.
17/436,467
Granted
Oct 28, 2025
Kind
B2
Abstract

A system that creates a net list from a circuit diagram or a document showing a circuit structure is provided. The system is an AI system including a first electronic device. The first electronic device includes an input/output interface, a control portion, and a first conversion portion. The input/output interface is electrically connected to the control portion, and the first conversion portion is electrically connected to the control portion. The input/output interface has a function of transmitting input data generated by a user's operation to the control portion, and the control portion has a function of transmitting the input data to the first conversion portion. Note that the input data is a circuit diagram illustrating a circuit structure or a document file showing the circuit structure. The first conversion portion includes a circuit where a neural network is formed, and the input data is converted to a net list with the use of the neural network of the first conversion portion.

Claims (50)

1. An AI system comprising:

a first electronic device comprising an external interface; and

a second electronic device comprising a first database and a second database,

wherein the first electronic device comprises an input/output interface, a control portion, and a first conversion portion,

wherein the input/output interface is electrically connected to the control portion,

wherein the first conversion portion is electrically connected to the control portion,

wherein the input/output interface is configured to transmit input data generated by a user's operation to the control portion,

wherein the control portion is configured to transmit the input data to the first conversion portion,

wherein the first conversion portion comprises a neural network comprising a transistor,

wherein the first conversion portion is configured to convert the input data into a first net list with the use of the neural network,

wherein the input data is a circuit diagram illustrating a circuit structure or a document file showing the circuit structure,

wherein each of the first database and the second database is electrically connected to the external interface,

wherein a second net list is stored in the first database,

wherein document data linked with the second net list is stored in the second database,

wherein the control portion is configured to communicate with the second electronic device through the external interface,

wherein the control portion is configured to search the first database for the input data, and

wherein the control portion is configured to read the document data from the second database and to output the document data to the input/output interface in the case where the second net list is found in the first database in searching for the input data.

2. An AI system comprising:

a first electronic device; and

a second electronic device comprising a first database and a second database,

wherein the first electronic device comprises an input/output interface, a control portion, and an external interface,

wherein the second electronic device comprises a first conversion portion,

wherein the input/output interface is electrically connected to the control portion,

wherein the external interface is electrically connected to the control portion and the first conversion portion of the second electronic device,

wherein the input/output interface is configured to transmit input data generated by a user's operation to the control portion,

wherein the control portion is configured to transmit the input data to the first conversion portion of the second electronic device through the external interface,

wherein the first conversion portion comprises a circuit where a neural network comprising a transistor,

wherein the first conversion portion is configured to convert the input data into a first net list with the use of the neural network,

wherein the control portion has a function of obtaining the first net list from the second electronic device through the external interface,

wherein the input data is a circuit diagram illustrating a circuit structure or a document file showing the circuit structure,

wherein each of the first database and the second database is electrically connected to the external interface,

wherein a second net list is stored in the first database,

wherein document data linked with the second net list is stored in the second database,

wherein the control portion is configured to communicate with the second electronic device through the external interface,

wherein the control portion is configured to search the first database for the input data, and

wherein the control portion is configured to read the document data from the second database and to output the document data to the input/output interface in the case where the second net list is found in the first database in searching for the input data.

3. An operation method of an AI system, the AI system comprising:

an input/output interface;

a control portion electrically connected to the input/output interface;

a first database and a second database electrically connected to the control portion; and

a first conversion portion comprising a neural network comprising a transistor, the first conversion portion being electrically connected to the control portion,

wherein the operation method comprises a first step, a second step, a third step, a fourth step, a fifth step, and a sixth step,

wherein the first step comprises a step of inputting input data created by a user to the control portion,

wherein the second step comprises a step of converting the input data into a first net list by the neural network of the first conversion portion,

wherein the third step comprises a step of performing output to the input/output interface through the control portion,

wherein a second net list is stored in the first database,

wherein document data linked with the second net list is stored in the second database,

wherein the fourth step comprises a step of searching the first database for the input data,

wherein the fifth step comprises a step of reading the document data from the second database and outputting the document data to the input/output interface in the case where the second net list is found in the first database in the fourth step, and

wherein the sixth step comprises a step where the control portion outputs information that the first net list is not found in the first database to the input/output interface in the case where the second net list is not found in the first database in the fourth step.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 3, 2021
From: KIMURA, HAJIME; WADA, RIHITO; KIMURA, MASAYUKI; KUROKAWA, YOSHIYUKI; AOKI, TAKESHI
To: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.
Reel/Frame 057385/0593 →
Priority Claims (3)
JP 2019-042594 · Mar 8, 2019 · national
JP 2019-088049 · May 8, 2019 · national
JP 2019-194669 · Oct 25, 2019 · national
Continuity (1)
Related Publication 20220180159A1 · Jun 9, 2022
References Cited (34)
US 9384419B2 · Konishi · 2016 [cited by applicant]
US 9813694B2 · Zhong et al. · 2017 [cited by applicant]
US 10061881B2 · Li et al. · 2018 [cited by applicant]
US 10102320B2 · Pataky · 2018 [cited by examiner]
US 10949595B2 · Tsutsui et al. · 2021 [cited by applicant]
US 11907927B2 · Takasu · 2024 [cited by examiner]
US 20070256037A1 · Zavadsky et al. · 2007 [cited by applicant]
US 20090313596A1 · Lippmann · 2009 [cited by examiner]
US 20140355886A1 · Konishi · 2014 [cited by applicant]
US 20150296202A1 · Zhong et al. · 2015 [cited by applicant]
US 20160253445A1 · Pataky · 2016 [cited by examiner]
US 20170317085A1 · Kurokawa · 2017 [cited by applicant]
US 20180004881A1 · Li et al. · 2018 [cited by applicant]
US 20180005588A1 · Kurokawa · 2018 [cited by applicant]
US 20200151289A1 · Sikka · 2020 [cited by examiner]
US 20220215146A1 · Lin · 2022 [cited by examiner]
US 20240086606A1 · Hsu · 2024 [cited by examiner]
US 20240265181A1 · Cao · 2024 [cited by examiner]
CN 101063987A · 2007 [cited by applicant]
JP 07200643A · 1995 [cited by applicant]
JP 2015007972A · 2015 [cited by applicant]
JP 2015176193A · 2015 [cited by applicant]
JP 2015207278A · 2015 [cited by applicant]
JP 2018005436A · 2018 [cited by applicant]
JP 2018049430A · 2018 [cited by applicant]
WO WO2017017808 · 2017 [cited by applicant]
WO WO2018221625 · 2018 [cited by applicant]
WO WO2018234945 · 2018 [cited by applicant]
WO WO2019021095 · 2019 [cited by applicant]
Chinese Office Action (Application No. 202080018555.2) Dated Aug. 29, 2024. [cited by applicant]
International Search Report (Application No. PCT/IB2020/051516) Dated May 26, 2020. [cited by applicant]
Written Opinion (Application No. PCT/IB2020/051516) Dated May 26, 2020. [cited by applicant]
Jiao.L, Application and Implementation of Neural Network, Jun. 1, 1993, pp. 548-551, Xidian University Press. [cited by applicant]
Chinese Office Action (Application No. 202080018555.2) Dated Mar. 19, 2025. [cited by applicant]