US 2021/0279459 A1 · System for identifying and linking entity relationships in documents

Abstract

The present invention discloses a system for linking first type of entities and second type of entities in a page. The system is configured to generate a feature vector for each of the first type of entities and each of the second type of entities. Further, the system is configured to receive into a neural network, a pair of the feature vectors, wherein one of the pair of the feature vector corresponds to a feature vector of a first type of entity and another feature vector corresponds to a feature vector of a second type of entity. The entities corresponding to the pair of feature vectors are neighboring each other. The neural network is configured to generate an output, indicating the likelihood of the pair of entities being linked.

Claims14

Dependent claims

A system for linking entities of a first type and entities of a second type, comprised in a page, the system comprising one or more processors configured to:

generate a feature vector for each of the entities of the first type and the second type;
receive into a neural network, a pair of the feature vectors, the pair comprising the feature vector of one of the entities of the first type and the feature vector of one of the entities of the second type, wherein the entities of the pair are neighboring each other;
and
generate an output, based on the neural network, indicating the likelihood of the pair of entities being linked.

1 more element

Dependencies are inferred from the claim text.

System for identifying and linking entity relationships in documents

Life of this patent

System for identifying and linking entity relationships in documents

Life of this patent

Abstract

Claims14