None of these systems attempts to classify and map legal documents into legal hierarchies. Accuracy rates of automated classification schemes utilizing controlled vocabulary can be suspect. 5,247,437 to Vale et al., have created automatic indexes that are associated with a document and are then capable of linking the index terms created back to a specific location within the document processed. However, a document is used as a search source in these prior art systems, and to retrieve other documents related to the document being used as a search source, citations contained in the initial document must exist in the documents returned.The present invention avoids this problem by utilizing citations as the key attribute to classification. A document is not assigned a classification to a legal hierarchy, but rather any document can be used as a search source to dynamically return documents similar to the one being used as the search source.After all citations have been checked against the seed citations, all classification scores are checked against a threshold value.If the classification score for any particular classification is greater than or equal to the threshold value, then the classification key and the hierarchy location key associated with the classification are inserted into the legal document.matching means for comparing stripped citations to stored citations associated with at least one classification in the hierarchy, and for identifying stripped citations which match at least one stored citation;calculating means for calculating a classification score for each classification associated with the stored citations which match the matching citations identified by said matching means, based on the scores assigned to the matching citations and the heuristic rules;3.
It is therefore a primary object of the invention to provide a computer-based system that will classify a legal document into a location within a legal hierarchy.
To date, the process of classifying legal case-law opinions remains dominated by West Publishing, Co. A tremendous amount of human resources is needed to maintain the West Publishing, Co.'s manual process of classifying legal documents.
Additionally, since lawyers desperately need case-law opinions dating back to the beginnings of the law, new competitors are virtually precluded from entering this field because of the level of manual effort required to read historical case-law decisions. 4,642,762 to Fisanick, have attempted to utilize controlled vocabulary terms to restrict the problem space associated with classifying electronic documents. 5,201,047 to Maki et al., have dealt with business or electronic classifications, utilizing user inputted attributes or profiles to determine the classification of an electronic document.
As a result, there have been an increasing number of legal sources which have been digitized and made available on electronic systems such as LEXIS® (LEXIS is a registered trademark of Reed Elsevier Properties, Inc.) and WESTLAW® (WESTLAW is a registered trademark of West Publishing Co.).
Classification of legal documents has largely been a manual exercise, dominated by West Publishing, Co. has employed lawyers to manually read case-law opinions as they are released and classify those opinions utilizing a Key Number System.