SEARCHING FOR AND DETERMINING RELATIONSHIPS AMONG ENTITIES

• US 20190324976A1
• Filed: 06/24/2019
• Published: 10/24/2019
• Est. Priority Date: 04/24/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Han, Yanyan, Gao, Xiaoyang, Spangler, William S., Bao, Sheng Hua, Dreher, Brian S.
• Granted Patent: US 11,188,574 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/288 Entity relationship models
• CPC Class Codes: G06F 16/36 Creation of semantic tools, e.g. ontology or thesauri
• CPC Class Codes: G06F 16/9038 Presentation of query results

Abstract

Methods, systems, and computer program products are provided for processing a request regarding relationships among instances of entities. A graphical representation of instances of entities is generated and includes one or more source nodes, each representing an instance of an input entity of a request, and one or more related nodes, each representing an instance of a second entity related to one or more corresponding instances of the input entity and associated with a corresponding confidence score for the relationship. Each of the one or more related nodes associated with a confidence score satisfying a threshold is identified. One or more supplemental nodes are added to the graphical representation, each of which represents a corresponding instance of a third entity with a relationship to a corresponding instance of the second entity. The graphical representation is traversed to identify relationships between instances of entities and produce results for the request.

Claims

1. A computer-implemented method, in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement a system for determining relationships among instances of entities, the method comprising:

generating, by the data processing system, a graphical representation of instances of entities, wherein the graphical representation includes one or more source nodes each representing an instance of an input entity of a request, and one or more related nodes each representing an instance of a second entity with a relationship to one or more corresponding instances of the input entity represented by the one or more source nodes and associated with a corresponding confidence score for the relationship;

identifying, by the data processing system, each of the one or more related nodes with a confidence score satisfying a threshold;

adding, by the data processing system, one or more supplemental nodes to the graphical representation, each of the one or more supplemental nodes representing a corresponding instance of a third entity with a relationship to a corresponding instance of the second entity represented by a corresponding identified related node; and

traversing, by the data processing system, the graphical representation to identify relationships between instances of entities and produce results for the request.

2. The computer-implemented method of claim 1, wherein the confidence score indicates a probability of a relationship between instances of related entities.

3. The computer-implemented method of claim 2, wherein the confidence score is based on a document count of documents indicating the relationship between the instances of the related entities.

4. The computer-implemented method of claim 1, further comprising:

iteratively adding one or more additional nodes to the graphical representation for nodes of the graphical representation having a corresponding confidence score satisfying the threshold, wherein each additional node represents an instance of an additional entity with a relationship to a corresponding instance of an entity represented by a node of the graphical representation.

5. The computer-implemented method of claim 1, wherein the confidence score for the one or more source nodes is predetermined, and the confidence score for the related and supplemental nodes is a product of confidence scores for one or more prior nodes and confidence scores for one or more links within a corresponding path of the graphical representation, each of the one or more links representing a relationship between instances of entities represented by a corresponding pair of nodes connected by the each of the one or more links.

6. The computer-implemented method of claim 1, wherein each of the one or more source nodes representing a corresponding input entity has an associated confidence score of 100%.

7. The computer-implemented method of claim 1, wherein:

the input entity is a drug,

the entity represented by the each identified related node is a gene, and

the entity represented by each of the supplemental nodes is a disease.