CPC G06F 16/345 (2019.01) [G06F 16/3331 (2019.01)] | 17 Claims |
1. A method to summarize search results from a similarity search request comprising:
receiving a similarity search query from a user, the similarity search query comprising at least one similarity search criteria;
executing the similarity search query on at least one data source, the at least one data source comprising a plurality of images, each of the plurality of images associated with metadata responsive to the similarity search criteria;
receiving a plurality of search results from the at least one data source, the plurality of search results including a plurality of images from the data source, the plurality of images responsive to the at least one similarity search criteria;
clustering the plurality of search results, the clustering based on the metadata associated with the plurality of search results excluding the at least one similarity search criteria, wherein the clustering is performed using a k-means clustering algorithm;
summarizing the plurality of search results based on the clustering, the summarization based on at least one of dominant subsets of the plurality of search results, feature categories of the plurality of search results, and distinctive features of the plurality of search results;
displaying the summarization of the plurality of search results in a display view; and
providing an interactive user interface to allow the user to refine the plurality of search results based on the summarization.
|