# US 2024/0256923 A1 · Computer-readable recording medium, path selecting method, and path selecting apparatus

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

- Number: US 2024/0256923 A1
- Document ID: US20240256923A1
- Status: Published application
- Kind: A1
- Application number: 18/415,906
- Filed: 2024-01-18
- Published: 2024-08-01
- Earliest claimed: 2023-01-31
- Assignees: Fujitsu Limited; Riken
- Applicants: Fujitsu Limited; Riken
- Inventors: Mutsuyo WADA; Yuichiro WADA; Kimihiro YAMAZAKI; Takashi KATOH; Atsushi TOKUHISA
- Web page: https://patentgrep.com/patent/US20240256923A1

## CPC

- G06F 18/295: {Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models}
- G06N 5/04: Inference or reasoning models
- G06F 18/29: {Graphical models, e.g. Bayesian networks}
- G06V 20/69: Microscopic objects, e.g. biological cells or cellular parts
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A non-transitory computer-readable recording medium stores therein a path selecting program that causes a computer to execute a process including extracting a plurality of representative points from a presence probability distribution of states of a target, identifying a first plurality of state transition paths between the plurality of representative points, and selecting a second plurality of state transition paths from the first plurality of state transition paths, based on a probability density of each path included in the first plurality of state transition paths.

## Claims

### Claim 1

A non-transitory computer-readable recording medium storing therein a path selecting program that causes a computer to execute a process comprising:
extracting a plurality of representative points from a presence probability distribution of states of a target;
identifying a first plurality of state transition paths between the plurality of representative points; and
selecting a second plurality of state transition paths from the first plurality of state transition paths, based on a probability density of each path included in the first plurality of state transition paths.

### Claim 2 (depends on 1)

The non-transitory computer-readable recording medium according to claim 1, wherein the extracting includes extracting, as the representative points, points of local maxima in a mixture Gaussian distribution corresponding to the presence probability distribution of the states of the target.

### Claim 3 (depends on 1)

The non-transitory computer-readable recording medium according to claim 1, wherein the identifying includes identifying, as the first plurality of state transition paths, a fully connected graph including nodes each corresponding to the plurality of representative points, and an edge connecting each pair of the nodes.

### Claim 4 (depends on 1)

The non-transitory computer-readable recording medium according to claim 1, wherein the identifying includes identifying, as the first plurality of state transition paths, a graph corresponding to a minimum spanning tree, from a fully connected graph including nodes each corresponding to the plurality of representative points, and an edge connecting each pair of the nodes.

### Claim 5 (depends on 1)

The non-transitory computer-readable recording medium according to claim 1, wherein the selecting includes selecting the second plurality of state transition paths based on a difference between maximum and minimum probability densities on each one of the first plurality of state transition paths.

### Claim 6 (depends on 1)

The non-transitory computer-readable recording medium according to claim 1, wherein the selecting includes selecting the second plurality of state transition paths based on a probability density of a first state, among states included in each path of the first plurality of state transition paths.

### Claim 7 (depends on 1)

The non-transitory computer-readable recording medium according to claim 1, wherein the selecting includes selecting the second plurality of state transition paths based on a difference between a probability density of a first state and a probability density of a second state, among states included in each path of the first plurality of state transition paths.

### Claim 8

A path selecting method executed by a processor comprising:
extracting a plurality of representative points from a presence probability distribution of states of a target;
identifying a first plurality of state transition paths between the plurality of representative points; and
selecting a second plurality of state transition paths from the first plurality of state transition paths, based on a probability density of each path included in the first plurality of state transition paths.

### Claim 9 (depends on 8)

The path selecting method according to claim 8, wherein the extracting includes extracting, as the representative points, points of local maxima in a mixture Gaussian distribution corresponding to the presence probability distribution of the states of the target.

### Claim 10 (depends on 8)

The path selecting method according to claim 8, wherein the identifying includes identifying, as the first plurality of state transition paths, a fully connected graph including nodes each corresponding to the plurality of representative points, and an edge connecting each pair of the nodes.

### Claim 11 (depends on 8)

The path selecting method according to claim 8, wherein the identifying includes identifying, as the first plurality of state transition paths, a graph corresponding to a minimum spanning tree, from a fully connected graph including nodes each corresponding to the plurality of representative points, and an edge connecting each pair of the nodes.

### Claim 12 (depends on 8)

The path selecting method according to claim 8, wherein the selecting includes selecting the second plurality of state transition paths based on a difference between maximum and minimum probability densities on each one of the first plurality of state transition paths.

### Claim 13 (depends on 8)

The path selecting method according to claim 8, wherein the selecting includes selecting the second plurality of state transition paths based on a probability density of a first state, among states included in each path of the first plurality of state transition paths.

### Claim 14 (depends on 8)

The path selecting method according to claim 8, wherein the selecting includes selecting the second plurality of state transition paths based on a difference between a probability density of a first state and a probability density of a second state, among states included in each path of the first plurality of state transition paths.

### Claim 15

A path selecting apparatus comprising:
a processor configured to:
extract a plurality of representative points from a presence probability distribution of states of a target;
identify a first plurality of state transition paths between the plurality of representative points; and
select a second plurality of state transition paths from the first plurality of state transition paths, based on a probability density of each path included in the first plurality of state transition paths.

### Claim 16 (depends on 15)

The path selecting apparatus according to claim 15, wherein the processor is further configured to extract, as the representative points, points of local maxima in a mixture Gaussian distribution corresponding to the presence probability distribution of the states of the target.

### Claim 17 (depends on 15)

The path selecting apparatus according to claim 15, wherein the processor is further configured to identify, as the first plurality of state transition paths, a fully connected graph including nodes each corresponding to the plurality of representative points, and an edge connecting each pair of the nodes.

### Claim 18 (depends on 15)

The path selecting apparatus according to claim 15, wherein the processor is further configured to identify, as the first plurality of state transition paths, a graph corresponding to a minimum spanning tree, from a fully connected graph including nodes each corresponding to the plurality of representative points, and an edge connecting each pair of the nodes.

### Claim 19 (depends on 15)

The path selecting apparatus according to claim 15, wherein the processor is further configured to select the second plurality of state transition paths based on a difference between maximum and minimum probability densities on each one of the first plurality of state transition paths.

### Claim 20 (depends on 15)

The path selecting apparatus according to claim 15, wherein the processor is further configured to select the second plurality of state transition paths based on a probability density of a first state, among states included in each path of the first plurality of state transition paths.
