# US 2021/0279838 A1 · State visualization device, state visualization method, and state visualization program

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0279838 A1
- Document ID: US20210279838A1
- Status: Published application
- Kind: A1
- Application number: 17/329,529
- Filed: 2021-05-25
- Published: 2021-09-09
- Earliest claimed: 2018-11-27
- Assignees: Riken
- Applicants: Riken
- Inventors: Tetsuo ISHIKAWA; Eiryo KAWAKAMI
- Web page: https://patentgrep.com/patent/US20210279838A1

## CPC

- G06T 3/06: Topological mapping of higher dimensional structures onto lower dimensional surfaces
- G16H 50/30: for calculating health indices; for individual health risk assessment
- A61B 5/00: Measuring for diagnostic purposes (radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00); Identification of persons
- G06T 3/4007: based on interpolation, e.g. bilinear interpolation (image demosaicing G06T3/4015; edge-driven or edge-based scaling G06T3/403)
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

A novel technique is provided that analyzes the state of life using multivariate data relating to life. A state visualization device includes: a coarse-graining portion configured to perform coarse-graining on values corresponding to a plurality of items included in sample data; a model creation portion configured to obtain, using binarized values, a mathematical model for calculating energies each fitting a frequency of occurrence of a state represented by a combination of values corresponding to the items; a graph creation portion configured to create a graph in which the state is placed in two-dimensional space; and an interpolation processing portion configured to create a landscape image by smoothing and interpolating a discrete graph.

## Claims

### Claim 1

A state visualization device comprising:
a coarse-graining portion configured to perform coarse-graining on values corresponding to a plurality of items included in sample data;
a model creation portion configured to obtain, using binarized values, a mathematical model for calculating energies each fitting a frequency of occurrence of a state represented by a combination of values corresponding to the items;
a graph creation portion configured to create a graph in which the state is placed in two-dimensional space;
an interpolation processing portion configured to interpolate energies between the states to create an interpolated image; and
an evaluation processing portion configured to binarize data of an evaluation target and determine a position of the data in the image;
wherein an attraction region in the image and a predetermined attribute of the sample data that belongs to the attraction region are associated with each other and stored in a storage device, and
the evaluation processing portion is configured to extract an attribute corresponding to the data of the evaluation target from the storage device and output the attribute.

### Claim 2 (depends on 1)

The state visualization device according to claim 1, wherein the evaluation processing portion is configured to binarize the data of the evaluation target obtained at a plurality of time points, determine a plurality of positions of the data in the image, and superimpose and display a course of change, over time, of the positions in the image.

### Claim 3 (depends on 1)

The state visualization device according to claim 1, wherein the coarse-graining portion is configured to binarize the values corresponding to the plurality of items included in the sample data.

### Claim 4

A state visualization method to be performed by a computer, the method comprising:
performing coarse-graining on values corresponding to a plurality of items included in sample data;
obtaining, using binarized values, a mathematical model for calculating energies each fitting a frequency of occurrence of a state represented by a combination of values corresponding to the items;
creating a graph in which the state is placed in two-dimensional space;
interpolating energies between the states to create an interpolated image; and
binarizing data of an evaluation target and determining a position of the data in the image;
wherein an attraction region in the image and a predetermined attribute of the sample data that belongs to the attraction region are associated with each other and stored in a storage device, and
extracting an attribute corresponding to the data of the evaluation target from the storage device and outputting the attribute.

### Claim 5 (depends on 4)

The state visualization method according to claim 4, wherein
the graph represents a state of a living organism or represents a health state of a human, or
the graph is used to predict a health state of a human.

### Claim 6

A non-transitory storage medium storing a state visualization program executable by a computer, the program causing the computer to:
perform coarse-graining on values corresponding to a plurality of items included in sample data;
obtain, using binarized values, a mathematical model for calculating energies each fitting a frequency of occurrence of a state represented by a combination of values corresponding to the items;
create a graph in which the state is placed in two-dimensional space;
interpolate energies between the states to create an interpolated image; and
binarize data of an evaluation target and determine a position of the data in the image;
wherein an attraction region in the image and a predetermined attribute of the sample data that belongs to the attraction region are associated with each other and stored in a storage device, and
extract an attribute corresponding to the data of the evaluation target from the storage device and outputting the attribute.
