Defect knowledge circulation system
AssigneeHitachi, Ltd.
InventorTakumi Kato
Life of this patent
Estimating the term…
Abstract
A method for performing defect summarization, the method comprising: receiving, by a processor, defect records associated with an operation; receiving, by the processor, work information associated with the operation linking, by the processor, the defect records and the work information using a first Artificial Intelligence (AI) model to generate linked information; and performing, by the processor, summary generation using a second AI model to generate work summary using summarization keywords, the defect records, and the work information, as input to the second AI model.
Claims12
A method for performing defect summarization, the method comprising:
- receiving, by the processor, a work information retrieval request from a user device, the work information retrieval request associated with an identifier from a database of a defect knowledge circulation system;
- retrieving, by the processor executing a knowledge provisioning function of the defect knowledge circulation system configured to intake the work information retrieval request as input, work information, link data, a summary record, and
- defect records associated with the work information, wherein the defect records are generated and stored based on an inspection result of the work information, wherein the link data is generated and stored based on inferring a relationship between the defect records and the work information and grouping the inferred link by summary keywords;
- and
- performing, by the processor, summary generation using a trained machine learning model to generate and store a work summary, the trained machine learning model configured to generate the work summary by using the generated and stored link data and by training the trained machine learning model with applying the summary keywords, the generated and stored defect records, and the work information.
A system for performing defect summarization, the system comprising:
- a data storage;
- and a processor in communication with the data storage, wherein the processor is configured to:
- receiving, by the processor, a work information retrieval request from a user device, the work information retrieval request associated with an identifier from a database of a defect knowledge circulation system;
- retrieving, by the processor executing a knowledge provisioning function of the defect knowledge circulation system configured to intake the work information retrieval request as input, work information, link data, a summary record, and defect records associated with the work information, wherein the defect records are generated and stored based on an inspection result of the work information, wherein the link data is generated and stored based on inferring a relationship between the defect records and the work information and grouping the inferred link by summary keywords;
- and performing, by the processor, summary generation using a trained machine learning model to generate and store a work summary, the trained machine learning model configured to generate the work summary by using the generated and stored link data and by training the trained machine learning model with applying the summary keywords, the generated and stored defect records, and the work information.
Dependencies are inferred from the claim text.