Information processing apparatus, information processing method, and program

Patent metadata

Field	Value
Publication number	US-12072325-B2
Application number	US-201817279285-A
Country	US
Kind code	B2
Filing date	Sep 27, 2018
Priority date	Sep 27, 2018
Publication date	Aug 27, 2024
Grant date	Aug 27, 2024

Abstract

An information processing apparatus (20) includes a use environment information acquisition unit (210), a model selection unit (220), and a prediction unit (230). The use environment information acquisition unit (210) acquires use environment information indicating a use environment of a physical system having input-output. The model selection unit (220) selects, from a storage unit storing a plurality of prediction models of the physical system in association with section information indicating a section based on the use environment, a prediction model being associated with section information of a section matching the use environment indicated by the use environment information. The prediction unit (230) performs prediction based on output of the physical system by use of the selected prediction model.

First claim

What is claimed is:

1. A system comprising:
an odor sensor having a receptor to which a contaminant molecule contained in a gas is adherable, the odor sensor exposing the receptor to the gas, detecting detection values in response to adhesion of the contaminant molecule to the receptor and separation of the contaminant molecule from the receptor, and purging the gas from the odor sensor;
a processor; and
a memory storing instructions executable by the processor to:
acquire use environment information indicating a use environment of the odor sensor, the use environment including at least one of temperature, humidity, air pressure, a type of the contaminant molecule detectable in the gas, a type of the gas to which the receptor is exposed, a sampling time period in which the receptor is exposed to the contaminant molecule, and a distance from the odor sensor to a target object as to which the contaminant molecule is to be detected;
select, from a plurality of prediction models for the odor sensor respectively associated with different use environments, the prediction model associated with the use environment of the odor sensor; and
perform prediction as to presence or absence of the contaminant molecule based on the detection values detected by the odor sensor, using the selected prediction model.

2. The information processing apparatus according to claim 1 , wherein the instructions are executable by the processor to further
generate correspondence relations between the prediction models and the different use environments are respectively by heterogeneous mixture learning.

3. An information processing method executed by a computer of a system that also includes an odor sensor, the odor sensor having a receptor to which a contaminant molecule contained in a gas is adherable, the odor sensor exposing the receptor to the gas, detecting detection values in response to adhesion of the contaminant molecule to the receptor and separation of the contaminant molecule from the receptor, and purging the gas from the odor sensor, the method comprising:
acquiring use environment information indicating a use environment of the odor sensor, the use environment including at least one of temperature, humidity, air pressure, a type of the contaminant molecule detectable in the gas, a type of the gas to which the receptor is exposed, a sampling time period in which the receptor is exposed to the contaminant molecule, and a distance from the odor sensor to a target object as to which the contaminant molecule is to be detected;
selecting, from a plurality of prediction models for the odor sensor respectively associated with different use environments, the prediction model associated with the use environment of the odor sensor; and
performing prediction as to presence or absence of the contaminant molecule based on the detection values detected by the odor sensor, using the selected prediction model.

4. The information processing method according to claim 3 , further comprising
generating correspondence relations between the prediction models and the different use environments are respectively by heterogeneous mixture learning.

5. A non-transitory computer readable medium storing a program causing a computer of a system to execute an information processing method, the sensor also including an odor sensor, the odor sensor having a receptor to which a contaminant molecule contained in a gas is adherable, the odor sensor exposing the receptor to the gas, detecting detection values in response to adhesion of the contaminant molecule to the receptor and separation of the contaminant molecule from the receptor, and purging the gas from the odor sensor, the method comprising:
acquiring use environment information indicating a use environment of the odor sensor, the use environment including at least one of temperature, humidity, air pressure, a type of the contaminant molecule detectable in the gas, a type of the gas to which the receptor is exposed, a sampling time period in which the receptor is exposed to the contaminant molecule, and a distance from the odor sensor to a target object as to which the contaminant molecule is to be detected;
selecting, from a plurality of prediction models for the odor sensor respectively associated with different use environments, the prediction model associated with the use environment of the odor sensor; and
performing prediction as to presence or absence of the contaminant molecule based on the detection values detected by the odor sensor, using the selected prediction model.

Assignees

• Nec Corp

Inventors

• Eto Riki

Classifications

• G06N5/04

  Inference or reasoning models · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N20/00

  Machine learning · CPC title

• G01N5/02

  by absorbing or adsorbing components of a material and determining change of weight of the adsorbent, e.g. determining moisture content {(absorption bulbs B01D53/00)} · CPC title

• G01D21/02

  Measuring two or more variables by means not covered by a single other subclass · CPC title