US 12,339,839 B2
Accuracy and providing explainability and transparency for query response using machine learning models
Michael August Verkruyse, Enumclaw, WA (US); Jeffrey James Dalgliesh, Duncan (CA); Jon Travis Brewton, Pasadena, TX (US); Alexander Elkholy, Seattle, WA (US); and Ashmita Mittal, Vancouver (CA)
Assigned to Data Squared USA Inc., Wilmington, DE (US)
Filed by Data Squared USA Inc., Wilmington, DE (US)
Filed on Nov. 1, 2024, as Appl. No. 18/935,017.
Claims priority of provisional application 63/547,840, filed on Nov. 8, 2023.
Prior Publication US 2025/0147957 A1, May 8, 2025
Int. Cl. G06F 16/2452 (2019.01); G06F 16/28 (2019.01)
CPC G06F 16/24522 (2019.01) [G06F 16/288 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A non-transitory, computer-readable storage medium comprising instructions recorded thereon, wherein the instructions when executed by at least one data processor of a computer system, cause the computer system to:
receive, via a user interface displayed at a user device, a query, wherein the query comprises natural language;
parse and translate, by the computer system, the natural language query into a graph traversal or database query operation;
perform, by the computer system, the graph traversal or database query operation on a graph database to identify one or more graph representations,
wherein the graph database comprises a plurality of graph representations defined by a graph schema, wherein each graph representation of the plurality of graph representations comprises:
a plurality of nodes, each node representing an entity;
a plurality of edges, each edge connecting at least two nodes and defining a relationship between at least two entities represented by the at least two nodes; and
a plurality of properties, each property defining an attribute of one or more entities or one or more relationships;
and wherein each graph representation of the plurality of graph representations is derived from a plurality of extracted data points, each extracted data point comprising at least one of: structured data, unstructured data, or time series data, wherein each extracted data point comprising unstructured data is assigned, using one or more machine learning models, to one or more of a plurality of categories based at least in part on a relationship between each extracted data point and at least one other extracted data point, wherein each extracted categorized data point comprising unstructured data is assigned to a cluster of a plurality of clusters based at least in part on a relationship of each extracted categorized data point to a characteristic of a source of the unstructured data, and wherein the assignment of categories and clusters to each extracted data point comprising unstructured data alters a structured data schema used to extract the structured data;
retrieve, by the computer system, the one or more graph representations of the plurality of graph representations;
score, by the computer system, the one or more graph representations based on a relevance of the one or more graph representations to the natural language query to identify at least one relevant graph representation;
generate, by the computer system, a response to the natural language query, wherein generating the response comprises providing the at least one relevant graph representation to a large language model (LLM), and wherein the response comprises:
natural language;
a visual representation of the graph traversal;
an indicator of one or more nodes of the plurality of nodes and one or more edges of the plurality of edges within the visual representation, wherein the one or more nodes and one or more edges are determined to be relevant to the query; and
a structured citation comprising metadata indicating a source associated with the one or more nodes and one or more edges; and
display, by the user the user interface on the user device, the response to the natural language query.