US Patent Application 18365075. SEMANTIC ENTITY SEARCH USING VECTOR SPACE simplified abstract
Contents
SEMANTIC ENTITY SEARCH USING VECTOR SPACE
Organization Name
Inventor(s)
David Newman of Walnut Creek CA (US)
Omar B. Khan of Richmond VA (US)
Alexander Joseph Kalinowski of Philadelphia PA (US)
SEMANTIC ENTITY SEARCH USING VECTOR SPACE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18365075 titled 'SEMANTIC ENTITY SEARCH USING VECTOR SPACE
Simplified Explanation
- The patent application describes a method for semantic search using a vector space representation of concepts in a semantic ontology. - The vector space representation is based on weights of a neural network trained using triples from the semantic ontology. - The method includes presenting a semantic search user interface with a text input portion, a suggested search portion, and a search results portion. - The user can enter a search query, which is converted into a vector representation using a processor. - The method computes a set of possible concepts related to the search query based on the distance between the vector and other concepts in the vector space representation. - The set of possible concepts is then presented in the suggested search portion of the user interface.
Original Abstract Submitted
A method may include storing a vector space representation of a set of concepts in a semantic ontology, wherein locations of the set of concepts in the vector space are based on weights of a neural network trained using triples from the semantic ontology; presenting a semantic search user interface including: a text input portion to receive a search query from an input device; a suggested search portion; and a search results portion; receiving, from a user computing device, the search query; converting, using at least one processor, the search query into a vector; computing, using the at least one processor, a set of possible concepts related to the search query based on a distance between the vector and other concepts in the vector space representation; and presenting the set of possible concepts related to the search query in the suggested search portion of the semantic search user interface.