Processing a query using an entity feature vector
AssigneeNEC Corporation
InventorsKosuke Akimoto, Takuya Hiraoka, Kunihiko Sadamasa
Life of this patent
Estimating the term…
Abstract
A processing device includes: an entity pre-processing means for receiving a set of atoms, the atom indicating a combination of a predicate and an associative array of entities that are arguments of the predicate, and calculating for each of the entities an entity feature vector for each of the entities, the vector reflecting a correspondence between keys and the entity in the associative array; and a post-processing means for receiving a query indicating contents of processing, and executing the processing indicated by the query using the entity feature vector.
Claims12
A processing device comprising:
- an entity pre-processing unit configured to receive a set of atoms, the atom indicating a combination of a predicate and an associative array of entities that are arguments of the predicate, and to calculate an entity feature vector for each of the entities, the vector reflecting a correspondence between key and the entity in the associative array;
- and
- a post-processing unit configured to receive a query indicating contents of processing and executing the processing indicated by the query using the entity feature vector.
A processing method comprising:
- (a) receiving a set of atoms, the atom indicating a combination of a predicate and an associative array of entities that are arguments of the predicate, and calculating an entity feature vector for each of the entities, the vector reflecting a correspondence between key and the entity in the associative array;
- and
- (b) receiving a query indicating contents of processing, and executing processing indicated by the query using the entity feature vector.
A non-transitory computer readable medium storing a program causing a computer to execute:
- (a) receiving as input a set of atoms, the atom indicating a combination of a predicate and an associative array of entities that are arguments of the predicate, and calculating an entity feature vector for each of the entities, the vector reflecting a correspondence between key and the entity in the associative array;
- and
- (b) receiving a query indicating contents of processing, and executing processing indicated by the query using the entity feature vector.
Dependencies are inferred from the claim text.