Event-Based Search Engine Using Object-Event Bipartite Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search methods, such as facial recognition, often yield few results when searching for specific objects like people, especially if there are limited images available.
Innovation Solution
A server-hosted search engine uses natural language processing to determine a searched time interval and event, selects a portion of an object-event bipartite graph from social media data, and employs Naïve-Bayes classification to rank relevant objects and events based on similarity, providing search results ordered by their relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If facial recognition search is used to search for a person, then the search can be performed using image data, but the number of results is limited when few pictures of the person are available
Solution Approach 1:
The patent transitions from a single-dimension image-based search to a multi-dimensional search space that includes events, locations, time periods, and object attributes. By constructing an object-event graph that incorporates diverse data types beyond images, the system expands the search dimensions to find objects even when image data is scarce, thereby resolving the contradiction between limited image availability and the need for sufficient search results
Solution Approach 2:
The search system is designed to perform multiple functions: it can search using images, event descriptions, location data, and time information simultaneously. The object-event graph serves multiple purposes by storing various object attributes and their relationships with events, allowing the system to adapt to different search scenarios and data availability conditions, thus providing robust search results regardless of image data quantity
Data Source
AI summary
As an example, a server hosting a search engine may receive a search query and determine a searched time interval, a searched object, and a searched event. The server may select, based on the searched time interval, a portion of an object-event bipartite graph that was created using information gathered from social media sites. The server may compare attributes of individual events in the portion with attributes of the searched event to identify a set of relevant events. The server may determine objects associated with the relevant events and compare attributes of individual objects with the attributes of the searched object to identify a set of relevant objects. The search engine may provide search results that include the set of relevant objects ordered according to their similarity to the searched object.