Ingenuity Systems, Inc.

Philippa Norman

Daniel R Richards

Richard O Chen

Ramon M Felciano

Raymond J Cho

A method, system, and computer program product are provided for extracting information from a plurality of articles in a distributed manner and for storing the extracted information in an information store. The invention identifies a plurality of articles from which information is to be extracted and a plurality of information extractors for extracting the information from the articles. Each article is assigned a priority score and ranking the articles from highest to lowest priority, thereby generating a queue; wherein the priority score for each article is calculated using a user-configurable priority calculation algorithm. The plurality of articles is assigned to the plurality of information extractors based on order in the queue, wherein an article with a higher rank is presented for information extraction before an article with a lower rank. Information extracted by information extractors from the articles is stored in the information store.

Techniques for facilitating information acquisition and storage

The method and system for extracting information from a plurality of articles and for storing the extracted information in a knowledge-based information store. The method and system identify a plurality of articles from which information is to be extracted. The method and system identify and assign a plurality of information extractors for extracting information from the plurality of articles. The method and system receive information extracted by an information extractor from an article assigned to the information extractor. The method and system enable a content reviewer to review the extracted information received from the information extractor and the content reviewer identifies errors associated with the extracted information. If the error count is above the threshold level, the article may be reassigned for information extraction. If the error count is equal to or below the threshold level, the content reviewer may change the extracted information to correct the errors.

A system and method of information extraction and storage extracts information from a plurality of articles in a distributed manner and stores the extracted information in an information store. In one embodiment, the system includes identification of a plurality of articles from which information is to be extracted and a plurality of information extractors for extracting the information from the articles. A database is provided for storing information related to the plurality of articles and the plurality of information extractors. The plurality of articles are assigned to the plurality of information extractors for information extraction and the extracted information is then stored in the information store.

Growing community of inventors

Los Altos, CA, United States of America

Philippa Norman