IP Library Granted Patent US 12,360,235
Granted Patent B2
US 12,360,235 · App. 17/788,007 · Granted Jul 15, 2025

Analysis device, analysis method, and storage medium

Inventors: Shouhei Ohno (Tokyo, JP); Takakazu Ishii (Tokyo, JP); Nao Akagawa (Tokyo, JP); Hiromichi Hirata (Tokyo, JP)
Assignee: NEC CORPORATION
G01S13/90
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 12,360,235
App. No.
17/788,007
Granted
Jul 15, 2025
Kind
B2
Abstract

An analysis device according to an aspect of the present disclosure includes: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: extract values of geospatial information at a plurality of points on a ground surface from a plurality of types of geospatial information, the plurality of types of geospatial information each representing at least a state of the ground surface or a state beneath the ground surface; and train a determination model based on height displacements at the plurality of points and the extracted values of the geospatial information in such a way that the determination model determines a set of the geospatial information contributing to the height displacement based on at least a part of the values of the geospatial information.

Claims (34)

1. An analysis device comprising:

at least one memory storing instructions; and

at least one processor configured to execute the instructions to:

extract values of geospatial information at a plurality of points on a ground surface from a plurality of types of geospatial information, the plurality of types of geospatial information each representing at least a state of the ground surface or a state beneath the ground surface;

train a determination model based on height displacements at the plurality of points and the extracted values of the geospatial information in such a way that the determination model determines a set of the geospatial information contributing to the height displacement based on at least a part of the values of the geospatial information;

extract a value of the geospatial information at a target point;

determine, based on the value of the geospatial information at the target point by using the determination model, the set of geospatial information contributing to a target displacement that is a height displacement at the target point;

output the set of the geospatial information contributing to the target displacement;

train the determination model based on the height displacement at the plurality of points and the extracted value of the geospatial information in such a way that the determination model further predicts a future height displacement based on at least a part of the values of the geospatial information;

further predict the target displacement based on the value of the geospatial information at the target point by using the determination model, and

output the prediction of the target displacement.

2. An analysis method performed by a computer and comprising:

extracting values of geospatial information at a plurality of points on a ground surface from a plurality of types of geospatial information, the plurality of types of geospatial information each representing at least a state of the ground surface or a state beneath the ground surface;

training a determination model based on height displacements at the plurality of points and the extracted values of the geospatial information in such a way that the determination model determines a set of the geospatial information contributing to the height displacement based on at least a part of the values of the geospatial information;

extracting the value of the geospatial information at a target point;

determining, based on the value of the geospatial information at the target point by using the determination model, the set of geospatial information contributing to a target displacement that is a height displacement at the target point;

outputting the set of the geospatial information contributing to the target displacement;

training the determination model based on the height displacement at the plurality of points and the extracted value of the geospatial information in such a way that the determination model further predicts a future height displacement based on at least a part of the values of the geospatial information;

further predicting the target displacement based on the value of the geospatial information at the target point by using the determination model; and

outputting the prediction of the target displacement.

3. An analysis device comprising:

at least one memory storing instructions; and

at least one processor configured to execute the instructions to:

extract values of geospatial information at a plurality of points on a ground surface from a plurality of types of geospatial information, the plurality of types of geospatial information each representing at least a state of the ground surface or a state beneath the ground surface;

train a determination model based on height displacements at the plurality of points and the extracted values of the geospatial information in such a way that the determination model determines a set of the geospatial information contributing to the height displacement based on at least a part of the values of the geospatial information; and

derive a condition for a value of at least a part of the geospatial information and a prediction expression for predicting the future height displacement under a situation in which the condition is satisfied, wherein

the prediction expression is represented by a linear combination of variables each representing the geospatial information, and

the determination model determines a set of the geospatial information represented by the variables in the prediction expression as a set of the geospatial information contributing to a height displacement under the situation in which the condition is satisfied.

4. An analysis method performed by a computer and comprising:

extracting values of geospatial information at a plurality of points on a ground surface from a plurality of types of geospatial information, the plurality of types of geospatial information each representing at least a state of the ground surface or a state beneath the ground surface;

training a determination model based on height displacements at the plurality of points and the extracted values of the geospatial information in such a way that the determination model determines a set of the geospatial information contributing to the height displacement based on at least a part of the values of the geospatial information;

deriving a condition for a value of at least a part of the geospatial information and a prediction expression for predicting the future height displacement under a situation in which the condition is satisfied;

representing the prediction expression by a linear combination of variables each representing the geospatial information; and

determining, by the determination model, a set of the geospatial information represented by the variables in the prediction expression as a set of the geospatial information contributing to a height displacement under the situation in which the condition is satisfied.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 22, 2022
From: OHNO, SHOUHEI; ISHII, TAKAKAZU; AKAGAWA, NAO; HIRATA, HIROMICHI
To: NEC CORPORATION
Reel/Frame 060272/0455 →
Continuity (1)
Related Publication 20230042178A1 · Feb 9, 2023
References Cited (20)
US 7142984B2 · Rahmes · 2006 [cited by examiner]
US 7298891B2 · McDowall · 2007 [cited by examiner]
US 8244026B2 · Nahari · 2012 [cited by examiner]
US 10586103B2 · Sargent · 2020 [cited by examiner]
US 20160321818A1 · Shorter · 2016 [cited by examiner]
US 20200166626A1 · Toriya · 2020 [cited by examiner]
US 20220312698A1 · Burkey · 2022 [cited by examiner]
US 20230102406A1 · Veronesi · 2023 [cited by examiner]
CN 109669184A · 2019 [cited by applicant]
JP 2009087235A · 2009 [cited by applicant]
JP 2018048898A · 2018 [cited by applicant]
JP 2018194404A · 2018 [cited by applicant]
JP 2019035598A · 2019 [cited by applicant]
JP 201985712A · 2019 [cited by applicant]
JP 202020740A · 2020 [cited by applicant]
WO 2015041295A1 · 2015 [cited by applicant]
International Search Report for PCT Application No. PCT/JP2020/014752, mailed on Jun. 16, 2020. [cited by applicant]
English translation of Written opinion for PCT Application No. PCT/JP2020/014752, mailed on Jun. 16, 2020. [cited by applicant]
Riki Eto, Ryohei Fujimaki, Satoshi Morinaga, Hiroshi Tamano, “Fully-Automatic Bayesian Piecewise Sparse Linear Models”, Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, … [cited by applicant]
Communication dated Apr. 25, 2023 issued by the Japanese Patent Office for Japanese Patent Application No. 2022-512969. [cited by applicant]