Technical document issues scanner
AssigneeMicrosoft Technology Licensing, LLC
InventorsYing Wang, Min Li, Mengyan Lu
Life of this patent
Estimating the term…
Abstract
A technical document scanner disclosed herein determines and categorizes various common issues among a large number of documents. An implementation of the technical document scanner is implemented using various computer process instructions including scanning a technical document to extract content, applying named entity recognition on the extracted content from the technical document to extract named entities, applying relation extraction on the named entities to extract relations between the named entities, and analyzing the relations between the entities to compose lists of high relevance entities for issue checking.
Claims20
A physical article of manufacture including one or more tangible computer-readable storage media, encoding computer-executable instructions for executing on a computer system a computer process comprising:
- scanning a document to extract content;
- applying a named entity recognition (NER) model on the extracted content to extract named entities, the named entities comprising at least one object definition entity and at least one object reference entity;
- extracting relations between the named entities by applying a relation extraction model on the named entities to associate an object definition entity from among the named entities with a definition list and an object reference entity from among the named entities with a reference list;
- and
- analyzing the relations between the named entities by identifying a definition from the definition list for a corresponding entity in the reference list to compose lists of high relevance categories for issue checking.
A computer-implemented method comprising:
- scanning a technical document to extract content;
- applying a named entity recognition (NER) model on the extracted content to extract named entities, the named entities comprising at least one object definition entity and at least one object reference entity;
- extracting relations between the named entities by applying a relation extraction model on the named entities to associate an object definition entity from among the named entities with a definition list and an object reference entity from among the named entities with a reference list;
- and
- analyzing the relations between the named entities by identifying a definition from the definition list for a corresponding entity in the reference list to compose lists of high relevance categories for issue checking.
A system comprising:
- one or more processor units;
- memory storing instructions that, when executed by the one or more processor units, cause the system to perform operations comprising:
- scanning a document to extract content;
- applying a named entity recognition (NER) model on the extracted content to extract named entities, the named entities comprising at least one object definition entity and at least one object reference entity;
- extracting relations between the named entities by applying a relation extraction model on the named entities to associate an object definition entity from among the named entities with a definition list and an object reference entity from among the named entities with a reference list;
- and
- analyzing the relations between the named entities by identifying a definition from the definition list for a corresponding entity in the reference list to compose lists of high relevance categories for issue checking.
Dependencies are inferred from the claim text.