Method and system to construct knowledge graphs based on a polystore
AssigneeThe Regents of the University of California
InventorsAMARNATH GUPTA, SUBHASIS DASGUPTA, JON STEPHENS, SHENGQI LI
Life of this patent
Estimating the term…
Abstract
Apparatus, systems and methods are provided that create an improved declarative and inference-guided construction of ontology-aligned knowledge graphs across heterogeneous data sources. The disclosed embodiments leverage indexing, mapping, and federated querying across relational, document, graph, and search-based sources through a unified metadata model. They use the polystore as a federated query layer, and as a structured semantic substrate for rule-based knowledge graph generation.
Claims20
A system for constructing a knowledge graph from a structured or semi-structured data source, the system comprising:
- a rule engine configured to apply at least one graph-generating dependency rule to the data source;
- wherein the at least one graph-generating dependency rule conforms to a graph-generating dependency language;
- a schema inference engine configured to map a schema and data from the data source into at least one graph element;
- a conversion module configured to transform the schema generated by the inference engine into executable graph generating dependencies;
- and
- a unified engine for executing rules.
A computer-implemented method for constructing a knowledge graph from a remote structured or semi-structured data source, at least a portion of the method being performed by a computing device comprising at least one processor, the method comprising:
- the computer communicating with a remote data source,
- the computer inferring a semantic mapping from a schema and a sample data using a large language model applied to the remote data source;
- the computer generating a declarative graph-generating dependency rule from the semantic mapping;
- the computer executing the declarative graph-generating dependency rule to produce a graph node and a graph edge;
- and
- the computer generating a user defined rule and merging the user defined rule with an inferred rule into a unified execution plan for knowledge graph construction.
A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device, cause the computing device to:
- communicate with a structured or semi-structured data source;
- infer a semantic mapping from a schema and a sample data using a large language model applied to the data source;
- generate a declarative graph-generating dependency rule from the semantic mapping;
- execute the declarative graph-generating dependency rule to produce a graph node and a graph edge;
- and
- merge a user defined rule and an inferred rule into a unified execution plan for for knowledge graph construction.
Dependencies are inferred from the claim text.