# US 2024/0004747 A1 · Processor System and Failure Diagnosis Method

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

- Number: US 2024/0004747 A1
- Document ID: US20240004747A1
- Status: Published application
- Kind: A1
- Application number: 18/201,915
- Filed: 2023-05-25
- Published: 2024-01-04
- Earliest claimed: 2022-06-30
- Assignees: Hitachi, Ltd.
- Applicants: Hitachi, Ltd.
- Inventors: Shuichi NISHINO; Yutaka UEMATSU; Tadanobu TOBA; Kenichi SHIMBO; Takumi UEZONO
- Web page: https://patentgrep.com/patent/US20240004747A1

## CPC

- G06F 11/0739: {in a data processing system embedded in automotive or aircraft systems}
- G06F 11/079: {Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36)}
- G06F 11/0706: {the processing taking place on a specific hardware platform or in a specific software environment}
- G06F 11/0721: {within a central processing unit [CPU]}
- G06F 11/2257: {using expert systems}
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

It is possible to achieve a more accurate failure diagnosis by obtaining explicit knowledge having high comprehensiveness that can be applied to a failure diagnosis based on knowledge across a plurality of areas. A processor system includes: one or more processors; and one or more memory resources. The memory resource is configured to store a diagnostic program configured to diagnose an electronic system including a mobile body or equipment, and a plurality of knowledge graphs for use in the diagnostic program and including at least a first knowledge graph and a second knowledge graph created based on domain knowledge different from that of the first knowledge graph, and the processor is configured to execute the diagnostic program to (1) evaluate a semantic similarity between a first knowledge item included in the first knowledge graph and a second knowledge item included in the second knowledge graph, and (2) generate, when the similarity satisfies a predetermined condition, an integrated graph in which the first knowledge graph and the second knowledge graph are integrated.

## Claims

### Claim 1

A processor system comprising:
one or more processors; and
one or more memory resources, wherein
the memory resource is configured to store
a diagnostic program configured to diagnose an electronic system including a mobile body or equipment, and
a plurality of knowledge graphs for use in the diagnostic program and including at least a first knowledge graph and a second knowledge graph created based on domain knowledge different from that of the first knowledge graph, and
the processor is configured to execute the diagnostic program to
(1) evaluate a semantic similarity between a first knowledge item included in the first knowledge graph and a second knowledge item included in the second knowledge graph, and
(2) generate, when the similarity satisfies a predetermined condition, an integrated graph in which the first knowledge graph and the second knowledge graph are integrated.

### Claim 2 (depends on 1)

The processor system according to claim 1, wherein
the processor is configured to execute the diagnostic program to
apply a predetermined mathematical model to failure-related information acquired from an external apparatus to generate the first knowledge graph and the second knowledge graph based on the failure-related information.

### Claim 3 (depends on 2)

The processor system according to claim 2, wherein
the memory resource is configured to store the generated integrated graph, and
the processor is configured to execute the diagnostic program to
apply, when new failure-related information is acquired, the predetermined mathematical model to the failure-related information to generate a third knowledge graph based on the failure-related information, and
integrate the integrated graph and the third knowledge graph based on a semantic similarity between a knowledge item included in the integrated graph acquired from the memory resource and a third knowledge item included in the third knowledge graph.

### Claim 4 (depends on 1)

The processor system according to claim 1, further comprising:
an output device configured to display information; and
an input device configured to receive an input of information, wherein
the processor is configured to execute the diagnostic program to
display on the output device the generated integrated graph, and
correct the integrated graph based on correction contents of the integrated graph received via the input device.

### Claim 5 (depends on 1)

The processor system according to claim 1, wherein
the processor is configured to execute the diagnostic program to
identify a knowledge item included in the integrated graph and corresponding to a failure factor to be diagnosed, and
define an input data format of training data for causing a predetermined mathematical model for diagnosis to perform machine learning by itemizing identification information of data corresponding to the identified knowledge item.

### Claim 6 (depends on 5)

The processor system according to claim 5, wherein
the processor is configured to execute the diagnostic program to
identify, from a past failure factor case, data that matches with the item defined in the input data format and indicates a state corresponding to each item when a failure occurs, and generate training data in which the identified data is allocated to the corresponding item.

### Claim 7 (depends on 6)

The processor system according to claim 6, wherein
the processor is configured to execute the diagnostic program to
generate, when information corresponding to each item of the training data is input as information indicating a failure, a diagnostic model that diagnoses a failure in the electronic system by performing machine learning using the training data on the predetermined mathematical model such that a failure factor associated with the item is estimated.

### Claim 8 (depends on 7)

The processor system according to claim 7, wherein
the processor is configured to execute the diagnostic program to
(1) acquire, from a terminal of a product manufacturing and maintenance business operator or an infrastructure management business operator, failure information with an unidentified failure factor, and input the failure information to the diagnostic model to acquire an identified failure factor as a diagnostic result, and
(2) transmit the identified failure factor to the terminal of the product manufacturing and maintenance business operator or the infrastructure management business operator.

### Claim 9

A failure diagnosis method executed by a processor system including one or more processors and one or more memory resources, the method comprising:
storing, by the memory resource,
a diagnostic program configured to diagnose an electronic system including a mobile body or equipment, and
a plurality of knowledge graphs for use in the diagnostic program and including at least a first knowledge graph and a second knowledge graph created based on domain knowledge different from that of the first knowledge graph; and
by executing the diagnostic program by the processor,
(1) evaluating a semantic similarity between a first knowledge item included in the first knowledge graph and a second knowledge item included in the second knowledge graph, and
(2) generating, when the similarity satisfies a predetermined condition, an integrated graph in which the first knowledge graph and the second knowledge graph are integrated.
