# US 2025/0165370 A1 · Failure information detecting apparatus, failure information detecting method, and failure information detecting program

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

- Number: US 2025/0165370 A1
- Document ID: US20250165370A1
- Status: Published application
- Kind: A1
- Application number: 18/840,941
- Filed: 2022-02-28
- Published: 2025-05-22
- Earliest claimed: 2022-02-28
- Assignees: Nippon Telegraph and Telephone Corporation
- Applicants: Nippon Telegraph and Telephone Corporation
- Inventors: Nobukazu FUKUDA; Chao WU; Shingo HORIUCHI; Kenichi TAYAMA
- Web page: https://patentgrep.com/patent/US20250165370A1

## CPC

- G06F 11/3086: {where the reporting involves the use of self describing data formats, i.e. metadata, markup languages, human readable formats}
- G06F 11/0751: {Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06)}
- G06F 11/0787: {Storage of error reports, e.g. persistent data storage, storage using memory protection}
- G06F 16/3347: {using vector based model}
- G06F 2201/81: Threshold
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A failure information detecting apparatus according to an embodiment includes a data acquisition unit that acquires a plurality of metrics including time series data and metadata and a failure query indicating a failure that a user desires to specify from a monitored system, a metric encoder that calculates a first vector representation of the plurality of metrics, a failure query encoder that calculates a second vector representation of the failure query, and a failure information detecting unit that calculates a first similarity between the first vector representation and the second vector representation and detects a failure in the metrics based on the first similarity.

## Claims

### Claim 1

A failure information detecting apparatus comprising:
circuitry configured to
acquire a plurality of metrics including time series data and metadata and a failure query indicating a failure that a user desires to specify from a monitored system;
calculate a first vector representation of the plurality of metrics;
calculate a second vector representation of the failure query; and
calculate a first similarity between the first vector representation and the second vector representation and detects a failure in the metrics based on the first similarity.

### Claim 2 (depends on 1)

The failure information detecting apparatus according to claim 1, wherein the circuitry is further configured to:
calculate an abnormality score based on the metrics and extracts a first metric from the plurality of metrics based on the abnormality score.

### Claim 3 (depends on 2)

The failure information detecting apparatus according to claim 2, wherein the circuitry is further configured to:
extract a second metric similar to the failure query from the first metric based on the failure query and the first metric.

### Claim 4 (depends on 3)

The failure information detecting apparatus according to claim 3, wherein the circuitry is further configured to:
calculate a second similarity between metadata of the first metric and a character string of the failure query, and extract a second metric having the second similarity exceeding a predetermined threshold value from the first metric.

### Claim 5 (depends on 3)

The failure information detecting apparatus according to claim 3, wherein the first vector representation is a vector representation of the second metric.

### Claim 6 (depends on 1)

The failure information detecting apparatus according to claim 1, wherein the circuitry is further configured to:
detect whether a failure occurs in the metrics based on whether the first similarity exceeds a predetermined threshold value.

### Claim 7

A failure information detecting method executed by a failure information detecting apparatus, the method comprising:
acquiring a plurality of metrics including time series data and metadata and a failure query indicating a failure that a user desires to specify from a monitored system;
calculating a first vector representation of the plurality of metrics;
calculating a second vector representation of the failure query;
calculating a first similarity between the first vector representation and the second vector representation; and
detecting a failure in the metrics based on the first similarity.

### Claim 8

A non-transitory computer readable storage medium storing a computer program which is executed by a failure information detecting apparatus to provide the steps of:
acquiring a plurality of metrics including time series data and metadata and a failure query indicating a failure that a user desires to specify from a monitored system;
calculating a first vector representation of the plurality of metrics;
calculating a second vector representation of the failure query;
calculating a first similarity between the first vector representation and the second vector representation; and
detecting a failure in the metrics based on the first similarity.
