Embedding-based parsing of search queries on online social networks
US10162886B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 30, 2016 |
| Grant date | Dec 25, 2018 |
| Priority date | — |
| Expiry date | Jun 10, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F16/338
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In one embodiment, a method includes receiving a query including multiple n-grams; parsing the query to identify a subset of n-grams; generating, for each identified n-gram, an embedding of the n-gram; determining, for each identified n-gram, one or more word senses; calculating, for each word sense for each identified n-gram, a relatedness-score for the word sense based similarity metrics of the embedding of the word sense and the embeddings of each of the other word senses corresponding to the other identified n-grams; selecting, for each identified n-gram, one of the word senses determined for the identified n-gram having a highest relatedness-score; identifying objects matching at least a portion of the query; ranking each identified object based on a quality of matching of the object to selected word senses; and sending search results corresponding to one or more of the identified objects and having a rank greater than a threshold rank.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.