Battelle Memorial Institute

Battelle Memorial Research

Vernon L Crow

Nancy E Miller

Jeffrey D Saffer

Randall E Scarberry

Wendy E Cowley

Deborah A Payne

Augustin J Calapristi

Elizabeth G Hetzler

Alan E Turner

Sean J Zabriskie

Lisa C Stillwell

Stuart J Rose

Guang Chen

Lucille T Nowell

Sarah J Thurston

Augustin J Calaprist

Grant C Nakamura

Heidi Sofia

Susan L Havre

Antonio P Sanfilippo

Jonathon D McCall

Nicholas O Cramer

Kristin A Cook

Scott D Decker

Philip J Monroe

Gregory S Thomas

Cory L Albright

Kevin M Groch

Joel M Malard

Leigh K Williams

Systems and computer-implemented processes for identification of features and determination of feature associations in a group of documents can involve providing a plurality of keywords identified among the terms of at least some of the documents. A value measure can be calculated for each keyword. High-value keywords are defined as those keywords having value measures that exceed a threshold. For each high-value keyword, term-document associations (TDA) are accessed. The TDA characterize measures of association between each term and at least some documents in the group. A processor quantifies similarities between unique pairs of high-value keywords based on the TDA for each respective high-value keyword and generates a similarity matrix that indicates one or more sets that each comprise highly associated high-value keywords.

Systems and processes for identifying features and determining feature associations in groups of documents

Data visualization methods, data visualization devices, data visualization apparatuses, and articles of manufacture are described according to some aspects. In one aspect, a data visualization method includes accessing a plurality of initial documents at a first moment in time, first processing the initial documents providing processed initial documents, first identifying a plurality of first associations of the initial documents using the processed initial documents, generating a first visualization depicting the first associations, accessing a plurality of additional documents at a second moment in time after the first moment in time, second processing the additional documents providing processed additional documents, second identifying a plurality of second associations of the additional documents and at least some of the initial documents, wherein the second identifying comprises identifying using the processed initial documents and the processed additional documents, and generating a second visualization depicting the second associations.

Data visualization methods, data visualization devices, data visualization apparatuses, and articles of manufacture

Methods and systems for rapid automatic keyword extraction for information retrieval and analysis. Embodiments can include parsing words in an individual document by delimiters, stop words, or both in order to identify candidate keywords. Word scores for each word within the candidate keywords are then calculated based on a function of co-occurrence degree, co-occurrence frequency, or both. Based on a function of the word scores for words within the candidate keyword, a keyword score is calculated for each of the candidate keywords. A portion of the candidate keywords are then extracted as keywords based, at least in part, on the candidate keywords having the highest keyword scores.

Rapid automatic keyword extraction for information retrieval and analysis

Document clustering methods, document cluster label disambiguation methods, document clustering apparatuses, and articles of manufacture are described. In one aspect, a document clustering method includes providing a document set comprising a plurality of documents, providing a cluster comprising a subset of the documents of the document set, using a plurality of terms of the documents, providing a cluster label indicative of subject matter content of the documents of the cluster, wherein the cluster label comprises a plurality of word senses, and selecting one of the word senses of the cluster label.

Document clustering methods, document cluster label disambiguation methods, document clustering apparatuses, and articles of manufacture

A system or method consistent with an embodiment of the present invention is useful in analyzing large volumes of different types of data, such as textual data, numeric data, categorical data, or sequential string data, for use in identifying relationships among the data types or different operations that have been performed on the data. A system or method consistent with the present invention determines and displays the relative content and context of related information and is operative to aid in identifying relationships among disparate data types. Various data types, such as numerical data, protein and DNA sequence data, categorical information, and textual information, such as annotations associated with the numerical data or research papers may be correlated for visual analysis. A variety of user-selectable views may be correlated for user interaction to identify relationships that exist among the different types of data or various operations performed on the data. Furthermore, the user may explore the information contained in sets of records and their associated attributes through the use of interactive 2-D line charts and interactive summary miniplots.

Data processing, analysis, and visualization system for use with disparate data types

Systems and methods provide several enhancements for the viewing, analysis, and generation of landscape views in a data analysis system, including: allowing a user to select from multiple methods to generate a landscape view, providing labels for peaks of a landscape, enabling the user to replace labels displayed on the landscape view, enabling a landscape view to be recalculated based on the replacement labels, and allowing a user to switch or morph between two landscape views generated by different methods. Such methods or systems generate graphical landscape map visualizations from a set of data records.

Systems and methods for improving concept landscape visualizations as a data analysis tool

A data import system enables access to data of multiple types from multiple data sources of different formats and provides an interface for importing data into a data analysis system. The interface enables a user to customize the formatting of the data as the data is being imported into a data analysis system. A user may select first user defined options for operating on a first data set received during a data importation process. An intermediate representation of the data set is generated based on the user first defined options. A user may specify second user defined options based on the intermediate representation during the data importation process. The second user defined options are processed to produce a final data representation of the data set to be used for analysis of the data. The intermediate representation may be a data table. The processing of a data set may include merging a first and second data set to produce the final data representation. The second user defined options may enable a user to select a basic operation for merging the data sets or to select a non-basic operation for merging the data sets. The basic operation may combine data sets in response to a user's selection of a first graphical interface control, and the non-basic operation may combine the data sets based on user selection of at least two graphical interface controls from a group of graphical interface controls.

Data import system for data analysis system

Methods and systems are provided that enable text in various sections of data records to be separately catalogued, indexed, or vectorized for analysis in a text visualization and mining system. A text processing system receives a plurality of data records, where each data record has one or a plurality of attribute fields associated with the records. The attributes fields containing textual information are identified. The specific textual content of each attribute field is identified. An index is generated that associates the textual content contained in each attribute field with the attribute field containing the textual content. The index is operable for use in text processing. The plurality of data records may be located in a data table and the textual information may be contained within cells of the data table. In another aspect, a plurality of data records is received, where at least some of the data records contain text terms. A first method is applied to weight text terms of the data records in a first manner to aid in distinguishing records from each other in response to selection of the first method. A second method is applied to weight text terms of the data records in a second manner to aid in distinguishing records from each other in response to selection of the second method. A vector is generated to distinguish each of the data records based on the text terms weighted by either the first or second method.

System and method for use in text analysis of documents and records

Growing community of inventors

Richland, WA, United States of America

Vernon L Crow