Back to results
US 2023/0145199 A1Published application
System and method for using graph theory to rank characteristics
AssigneeADP, Inc.
InventorRoberto COUTINHO
Life of this patent
Estimating the term…
Abstract
Systems, methods, and computer-readable storage media for building knowledge graphs which map the aspects of entities, then transforming the graphs into vectors for a similarity comparison. The resulting vectors can be used to identify skills and competencies of individuals, which the system uses to compare those individuals to others. The system can then quantify who would make for a good replacement for a given individual and make an associated recommendation.
Claims20
A method comprising:
- retrieving, at a computer system from a plurality of networked databases, characteristic data representing a plurality of entities;
- generating, via a processor of the computer system based on the characteristic data, a characteristic graph, the characteristic graph comprising nodes and edges, wherein:
- the nodes comprise entity nodes respectively associated with an entity in the plurality of entities, and characteristic nodes respectively associated with a distinct characteristic;
- and
- the edges connect the entity nodes to the characteristic nodes according to the characteristic data;
- transforming, via the processor, the nodes of the characteristic graph to a vector representation;
- receiving, at the computer system, a similarity request regarding a first entity in the plurality of entities;
- calculating, via the processor using the vector representation based on the similarity request, similarity scores between the first entity and remaining entities in the plurality of entities;
- and
- providing, via the computer system, a list of highest ranked entities within the remaining entities based on the similarity scores.
7 more elements
A system comprising:
- at least one processor;
- and
- a non-transitory computer-readable storage medium having instructions stored which, when executed by the processor, cause the at least one processor to perform operations comprising:
- retrieving, from a plurality of networked databases, characteristic data representing a plurality of entities;
- generating, based on the characteristic data, a characteristic graph, the characteristic graph comprising nodes and edges, wherein:
- the nodes comprise entity nodes respectively associated with an entity in the plurality of entities, and characteristic nodes respectively associated with a distinct characteristic;
- and
- the edges connect the entity nodes to the characteristic nodes according to the characteristic data;
- transforming the nodes of the characteristic graph to a vector representation;
- receiving, at the computer system, a similarity request regarding a first entity in the plurality of entities;
- calculating, using the vector representation based on the similarity request, similarity scores between the first entity and remaining entities in the plurality of entities;
- and
- providing a list of highest ranked entities within the remaining entities based on the similarity scores.
10 more elements
A non-transitory computer-readable storage medium having instructions stored which, when executed by at least one processor, cause the at least one processor to perform operations comprising:
- retrieving, from a plurality of networked databases, characteristic data representing a plurality of entities;
- generating, based on the characteristic data, a characteristic graph, the characteristic graph comprising nodes and edges, wherein:
- the nodes comprise entity nodes respectively associated with an entity in the plurality of entities, and characteristic nodes respectively associated with a distinct characteristic;
- and
- the edges connect the entity nodes to the characteristic nodes according to the characteristic data;
- transforming the nodes of the characteristic graph to a vector representation;
- receiving a similarity request regarding a first entity in the plurality of entities;
- calculating, using the vector representation based on the similarity request, similarity scores between the first entity and remaining entities in the plurality of entities;
- providing a list of highest ranked entities within the remaining entities based on the similarity scores.
6 more elements
Dependencies are inferred from the claim text.