Systems and methods for semantic search, content correlation and visualization

Abstract

Methods and systems for searching over large (i.e., Internet scale) data to discover relevant information artifacts based on similar content and / or relationships are disclosed. Improvements over simple keyword and phrase based searching over internet scale data are shown. Search engines providing accurate and contextually relevant search results are disclosed. Users are enabled to identify related documents and information artifacts and quickly, ascertain, via visualization, which of these documents are original, which are derived (or copied) from a source document or information artifact, and which subset is independently generated (i.e., an original document or information artifact).

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]The present application claims priority benefit under 35 U.S.C 119(e) of U.S. Provisional Patent Application No. 61 / 282,969, entitled “Systems and Methods for Semantic Search, Content Correlation and Visualization,” filed Apr. 30, 2011, the contents of which are incorporated herein by reference in their entirety.BACKGROUND OF THE INVENTION[0002]1. Field of the Invention[0003]The present invention relates to systems and methods for searching a large corpus of data to identify contextually relevant search results, correlating content and visualizing the results.[0004]2. Description of the Related Art[0005]There has been much research on search and retrieval of documents. Typically, searching requires knowledge of a specific term or set of terms. Similarity-based document retrieval allows the user to fetch “more documents like this one” by using a general document-similarity score as measured by counting words without regard to context. Howe...

AI Technical Summary

Benefits of technology

[0007]Benefits include allowing the user to distinguish a situation in which a single original fact or relationship is repeated many times from one in which several authors independently thinking or operating arrive at the same conclusion.

[0023]Embodiments of the present invention allow a user to distinguish a scenario where there are potentially many documents derived from an original (and thus hinge on its truth) from a scenario where there might be several independent documents that support a conclusion. Support could come from different evidence, different sources of the evidence, different reasoning, and so on.

[0035]In some embodiments, the method may further include the step of using the computer to assign each of the named entities to a category selected from the group consisting of a person, an organization, a location, and a date. The step of providing at least one result may include providing a list of documents in an order based on a determined relevance of each respective result to the at least one name of an entity of interest. The method may further include the step of using the computer to assess a similarity between a document selected from the list and other documents in the corpus based at least in part on the paired entities. The method may further include the step of enabling a user to search through the other documents based on the assessed similarity by displaying a selectable database containing a subset of the other documents.

Problems solved by technology

However, such search techniques may produce too many false positives and miss too many relevant documents.

Images