Neural network-based semantic information retrieval

Abstract

A question and answer (Q&A) system is enhanced to support natural language queries into any document format regardless of where the underlying documents are stored. The Q&A system may be implemented “as-a-service,” e.g., a network-accessible information retrieval platform. Preferably, the techniques herein enable a user to quickly and reliably locate a document, page, chart, or data point that he or she is looking for across many different datasets. This provides for a unified view of all of the user's (or, more generally, an enterprise's) information assets (such as Adobe® PDFs, Microsoft® Word documents, Microsoft Excel spreadsheets, Microsoft PowerPoint presentations, Google Docs, scanned materials, etc.), and to be able to deeply search all of these sources for the right document, page, sheet, chart, or even answer to a question.

Description

BACKGROUNDTechnical Field[0001]This application relates generally to information retrieval methods and systems.Background of the Related Art[0002]A search engine is an information retrieval software program that discovers, crawls, transforms and stores information for retrieval and presentation in response to user queries.[0003]A search engine normally comprises several components including a search interface, a crawler (also known as a spider or bot), an indexer, and a database. The crawler traverses a document collection, deconstructs document text, and assigns surrogates for storage in the search engine index. Online search engines store images, link data and metadata for the document as well. Search engines on the web (e.g., Google®) are sites enriched with facility to search the content stored on other sites. There is difference in the way various search engines work, but they all perform three basic tasks: finding and selecting full or partial content based on the keywords pro...

AI Technical Summary

Benefits of technology

The patent text describes a Q&A system that can access and search different types of documents, such as PDFs, Word documents, and Excel spreadsheets. Users can easily find the right document or data point they need by asking natural language questions. The system provides a unified view of all an enterprise's information assets, making it easier to search and access information. The technique ensures fast and reliable results for users, regardless of where the underlying documents are stored.

Problems solved by technology

Multimedia data information retrieval is complex.

The challenge in building such a system is to understand the query, to find appropriate documents that might contain the answer, and to extract the correct answer to be delivered to the user.

In the past, understanding the query was an open problem because computers do not intrinsically have human ability to understand natural language, nor do they have common sense to choose from many possible interpretations that elementary natural language understanding systems can produce.

Images