Thomson Reuters Global Resources

Thomson Reuters Enterprise Centre Gmbh

West Services, Inc.

Jack G Conrad

Mans Olof-Ors

Khalid Al-Kofahi

Forrest Rhoads

Joanne R S Claussen

Howard Turtle

Kinley Larntz

Peter Pircher

Daniel Gannon

Michael Dahn

Bokyung Yang-Stephens

Qiang Lu

Julian Brooke

Domingo Huh

Daniel Dabney

William M Keenan

Elnaz Davoodi

Dan Dabney

Bob Haschart

Jochen Lothar Leidner

Jie Lin

Christopher C Dozier

Sriharsha Veeramachaneni

Aaron Cooper

Robert J Haschart

Jonathan J Medin

Po Yang Bokyung Yang Stephens

Dan Gannon

Michael J Bender

Joanne R Claussen

Harsha Veeramachaneni

The present disclosure relates to methods and systems for providing context aware searching using concept markers. Embodiments provide concept markers configured to facilitate the identification and refinement of relevant content associated with a query with a high degree of precision. In embodiments, in response to a user query, documents and concept markers relevant to the query are determined. The identified documents are associated with the concept markers and are ranked based on the quality of the association. Upon a user selecting at least one of the concept markers, the search results are refined in response. The refining includes re-ranking the documents based on a combination of the original query and the selected concept marker. The suggested concept markers are similarly re-ranked. Accordingly, the techniques disclosed herein provide for a high precision identification of relevant content as well as high precision refining of the search results.

System and methods for context aware searching

The present invention provides a seeded news event clustering and retrieval system configured to first create a candidate data set of documents, second create a set of initial clusters based on nearness or duplicate similarity status, and third create an aggregate cluster by merging initial clusters with seed documents. The invention generates top-level clusters for news events based on an editorially supplied topical label or 'seed' component and generates sub-topic-focused clusters based on algorithm. The system uses an agglomerative clustering algorithm to gather and structure documents into distinct result sets. Decisions on whether to merge related documents or clusters are made according to similarity of evidence derived from two distinct sources, one, relying on a digital signature based on the unstructured text in the document, the other based on the presence of named entity tags that have been assigned to the document by an event or named entity tagger such as the Thomson Reuters Calais engine/web service.

System and engine for seeded clustering of news events

The present disclosure is directed towards systems and methods for evaluating and classifying data, which comprises receiving a first signal associated with a set of user defined categories and a second signal associated with a first set of one or more data items to be analyzed. The set of categories are presented on an interface and each of the data items are to be analyzed are presented on a tile overlay on the interface. A first swipe identification signal identifying a first category to apply to a first data item and a second swipe identification signal identifying a second category to apply to a second data item are received. Based upon the swipe identification signals, a first record associating the first data item with the first category and a second record associating the second data item with the second category are generated and stored in a memory.

Systems and methods for data evaluation and classification

The present disclosure relates to methods and systems for providing context aware searching using concept markers. Embodiments provide concept markers configured to facilitate the identification and refinement of relevant content associated with a query with a high degree of precision. In embodiments, in response to a user query, documents and concept markers relevant to the query are determined. The identified documents are associated with the concept markers and are ranked based on the quality of the association. Upon a user selecting at least one of the concept markers, the search results are refined in response. The refining includes re-ranking the documents based on a combination of the original query and the selected concept marker. The suggested concept markers are similarly re-ranked. The disclosed techniques provide for a high precision identification of relevant content as well as high precision refining of the search results.

A method for enabling a user to search database profiles includes receiving user input categorizing an information need, and determining whether the user input corresponds to a first or a second type of category. In response to determining that the user input corresponds to the first category type, the method includes requesting user input defining a first query, and in response to receipt of the query, and executing the defined first query against a set of one or more databases based on the user input categorizing the information need. In response to determining that the user input corresponds to the second category type, the method includes requesting additional user input regarding the information need.

Information retrieval systems with database-selection aids

To facilitate access to public records, the present inventors devised, among other things, an entity resolution system. The exemplary system includes master records database of 300 million entities, which is partitioned into multiple distinct portions. The exemplary system extracts entity information from input public records and constructs one or more blocking queries against specific portions of the master records database to identify one or more sets of candidate records. Feature vectors are defined for the candidate records and machine learning techniques, such as Support Vector Machine, are used to determine which of the candidate records from the master records database match the input public records. Candidate records that match are logically associated with public records, enabling ready access via direct or indirect queries.

Systems, methods, and software for entity relationship resolution

A system and method for automatically determining a plurality of pieces of different information about a textual document from the text of the textual document are provided in which one or more particular characteristics of the text of the textual document are identified to generate a file containing the text of the textual document with the particular characteristics marked up within the text.

System and method for processing formatted text documents in a database

An image of a printed document portion is provided to a synchronizer. The synchronizer retrieves an electronic version of the printed document and identifies an electronic text portion that is textually similar to a printed text portion. The synchronizer detects an annotation in the printed document portion and inserts a corresponding digital annotation into the electronic document.

Synchronizing annotations between printed documents and electronic documents

The present invention makes legal research more efficient by selecting clusters in response to the behavior of a user (e.g., a legal professional such as a paralegal, lawyer, or judge). The clusters, which are formed prior to the user accessing a legal document (and thus, providing user behavior to a system), are identified to the based upon a set of metadata associated with the legal document. At least two clusters are identified and a signal associated therewith is transmitted to the user. Each cluster is associated with a unique legal topic. Further, each cluster may comprise primary and/or secondary authority.

Systems, methods, and interfaces for extending legal search results

A system and method for automatically determining a plurality of pieces of different information about a textual document from the text of the textual document are provided in which one or more particular characteristics of the text of the textual document are identified to generate a file containing the text of the textual document with the particular characteristics marked up within the text. In addition, any negative treatment of other textual documents from the text of the textual document is determined to generate negative treatment information, a data record is produced indicating a depth of treatment for each other textual documents cited in the text of the textual document, the source of a quotation in the text of the textual document is verified to generate verified quotation information, any subject matter text that is applicable to the text of the textual document is determined to generate subject matter headings associated with the text of the textual document, and a data record is generated containing the identified characteristics of the textual document, the negative treatment of other textual documents cited in the textual document, the depth of treatment of other textual documents cited in the textual document, the verified quotation information, and the subject matter text associated with the textual document so that all of the information is accessible.

Many companies provide online search facilities that enable users to conduct computerized searches for documents. Unfortunately, these searches frequently provide results that include duplicate documents&#x2014;that is, documents that are completely or substantially identical to each other. This problem is particularly vexing when searching news stories, for example. Moreover, the duplicate documents are intermixed in the search results, leaving users to manually manage the complexities of identifying and/or filtering them. Accordingly, the present inventors devised systems, methods, and software that facilitate the identification and/or grouping of duplicate documents in search results. One exemplary system includes a signature generation module which generates document signatures based on length, temporal, and/or content components; a real-time duplicate detection module which uses the document signatures to identify 'exact' or 'fuzzy' duplicate documents; and a user-interface or presentation module which controls how duplicate documents are presented or suppressed in search results.

Growing community of inventors

Eagan, MN, United States of America

Jack G Conrad