Enhanced retrieval of structured data in fulfillment processes with ontology-based knowledge graphs

A system for ontology-guided retrieval of structured data, comprising:

• one or more processors;
• and
• one or more memory devices storing instructions that, when executed by the one or more processors, cause the system to:
• receive a natural language query;
• access a graph-based data structure representing a plurality of structured datasets, the graph-based data structure being organized according to an ontology defining entity types, relationship types, and valid traversal constraints;
• apply a machine learning model to generate a graph traversal query from the natural language query, the graph traversal query being constrained by the ontology to enforce valid multi-hop relationships between structured datasets;
• and
• execute the graph traversal query to retrieve data spanning multiple structured datasets and to produce an aggregated output.

A structured data retrieval system configured to retrieve structured store fulfillment data within a retail enterprise, the system comprising:

• a computing system including one or more processors and one or more memory devices storing instructions that, when executed by the one or more processors, cause the computing system to:
• receive a natural language query from a requesting entity;
• access a graph-based data structure representing a plurality of structured datasets obtained from a plurality of enterprise data sources, wherein the graph-based data structure is organized according to an ontology defining:
• entity types corresponding to structured data entities,
• relationship types defining permitted relationships between the entity types, and
• traversal constraints governing multi-hop traversal across the structured datasets;
• generate, using a machine learning model guided by the ontology, a structured graph traversal query configured to traverse a plurality of nodes of the graph-based data structure according to one or more ontology-defined relationships;
• validate the structured graph traversal query prior to execution to determine whether the traversal query violates at least one ontology-defined constraint;
• modify the structured graph traversal query in response to detecting that the traversal query violates the at least one ontology-defined constraint;
• execute the validated structured graph traversal query to perform a multi-hop traversal across two or more structured datasets and compute an aggregated result;
• and
• transmit, to the requesting entity, a response corresponding to the aggregated result.