The Boeing Company

Stephen Robert Poteet

Yuan-Jye Wu

Anne Kao

William R Ferng

Anne S-w Kao

Robert E Cranfill

David Charles Augustine

Anne Shu-Wan Kao

Fredrick Baden Holt

Shan Luh

Lesley H Quach

Daniel John Pierce

Peter James Lake

Jay Kevin McCullough

Steven David Chapman

Ping Xue

Rodney Allen Tjoelker

Andrew James Booker

Steven C Runo

Richard H Wojcik

Nigel Isaac Anthony Kilmer

Philip Harrison

Steven D Woods

Nicholas Multari

Yun-Ho Sikora

Maggie R Clark

Anne S W Kao

Lesley Hong-Minh Quach

Mark Thomas Greaves

Michelle Keim Condliff

D Dean Billheimer

Davis Scott Kinney

A system and method for event matching by analysis of text characteristics are presented. A document collection comprising documents is acquired. One or more document subsets of the document collection each comprising one or more documents potentially describing identical events are identified based on certain structured metadata fields of the documents. Salient text features are extracted from the documents in the document collection. An event similarity score for pairs of documents in the document collection is generated by comparing the text features extracted from the documents. A common event document list comprising sets of documents in the document collection whose event similarity scores with each other are above a similarity threshold is generated.

Event matching by analysis of text characteristics (E-MATCH)

A method, apparatus and computer program product are provided for identifying a part name within a data record. A maintenance expression is initially identified within a data record and a candidate part name string is then identified by identifying a head noun within a window that is positioned within the data record based upon the expression. In addition to identifying the head noun, a modifier may also be identified adjacent to or near any occurrence of the head noun in the course of identifying the candidate part name string. The candidate part name string may then be separately matched to respective ones of a plurality of standard names with each of a plurality of string matching techniques. The resulting potential matches are then analyzed to determine a best match.

Method, apparatus and computer program product for identifying a target part name within a data record

A method and apparatus are provided to efficiently generate a fulsome query in order to increase the recall and/or precision provided by the search. A method may construct a query by receiving the one or more initial search terms and then defining a concept for each search term. In order to define a concept, the method may determine if a concept associated with a respective search term has been previously defined. In an instance in which a concept associated with a respective search term has been previously defined, the method at least initially utilizes the previously defined concept. However, in an instance in which a concept associated with a respective search term has not been previously defined, the method constructs the concept based on terms related to the respective search term. The method may then combine the concepts defined for the one or more search terms to generate the query.

Method and apparatus for constructing a query based upon concepts associated with one or more search terms

A method including processing social network data to establish a tensor model of the social network data, the tensor model having at least an order of four. The tensor model is decomposed into a plurality of principal factors. A summary tensor is synthesized from a subset of the plurality of principal factors. The summary tensor represents a plurality of relationships among a plurality of entities in the tensor model. A synthesis of relationships is formed and stored. At least one parameter is identified using one of the summary tensor and a single principal factor in the subset. The at least one parameter is selected from the group consisting of: a correlation among the plurality of entities, a similarity between two of the plurality of entities, and a time-based trend of changes in the synthesis of relationships. The at least one parameter is communicated.

Determination of latent interactions in social networks

Methods and maintenance systems for use in analyzing data related to maintenance of at least one vehicle are disclosed. One example method includes receiving at least one fault message, receiving a maintenance event log for a vehicle. The maintenance event log including at least one maintenance event associated with the at least one fault message. The example method further includes automatically identifying a corrective action within a most recent maintenance event of the at least one maintenance event and storing a diagnostic entry including the at least one fault message and the identified corrective action, such that the diagnostic entry is retrievable from the computing device to evaluate a subsequent like fault message.

Maintenance systems and methods for use in analyzing maintenance data

In one embodiment a method to create a system to manage documents with sensitive or classified content comprises extracting a list of text features enabling interaction with the user developing the system to create a rule-based classifier based on the list of text features and one or more synonymous features, applying the rule-based classifier to one or more selected documents to tag a set of documents with the sensitive or classified information they contain, training a statistical text classifier using the tagged documents generated as a training set, applying the trained statistical text classifier to the training set, and reapplying the refined rule-based classifier to the one or more documents to tag a set of documents with the sensitive or classified information they contain. Other embodiments may be described.

Secure information classification

Technologies are described herein for providing automated analysis and summarization of free-form comments in survey response data. A number of topic words are identified from the survey response comments, and a numeric weight is calculated for each topic word that reflects the relevance of the topic word to each comment. Each topic word is associated with one or more topics and the comments relevant to each topic is then determined based on the weights of the associated topic words in each comment. A report is generated which summarizes the topics and their relative importance in the survey response comments based upon the number of comments relevant to each.

Automated analysis and summarization of comments in survey response data

A system generates rules for classifying documents are generated by building a vocabulary of features (e.g., words, phrases, acronyms, etc.) that are related to classifying concepts. The system includes a security document reader receives a security document that defines security concepts for a particular project and parses the security document to separate the security concepts. A vocabulary builder receives samples provided by the user that contain information related to the project. For each security concept, the vocabulary builder uses statistical analysis techniques to find features in the samples that are related to that concept. A rule generation assistant, for each security concept, generates rules based on the built vocabulary and the samples. The rule generation assistant uses statistical analysis techniques on the vocabulary and samples to determine features that optimally predict a particular concept. The rules can be used by a downgrader to process information to be distributed.

Automated rule generation for a secure downgrader

A streaming text data comparator performs real-time text data mining on streaming text data. The comparator receives a streaming text data document and generates a vector representation of the term frequencies relating to an existing document collection. The comparator then transforms the term frequency vector into a projection in a precomputed multidimensional subspace that represents the original document collection. The comparator further calculates a relationship value representing the similarities or differences between the vector representation and the subspace, and compares the relationship value to a predetermined threshold to determine whether the streaming text data document is related to the original document collection. If the streaming text data document is related, the streaming text data comparator intercalates the new document into the document collection. If the new document is not related, the comparator may store or delete the unrelated document.

Streaming text data mining method and apparatus using multidimensional subspaces

A text summarizer identifies relevant terms in a document, weights the terms and extracts one or more segments to produce a summary or abstract. The various terms in a particular are weighted in relation to an existing document collection. A term weight computer computes term weights for terms in the document, and a threshold comparator compares the term weights to determine if the corresponding terms are relevant to the document collection. Next, a term weight summer adds the term weights for each occurrence of each relevant term in the various segments of the document, and a summation comparator compares the summations to identify a text summarization segment representative of the document. Optionally, relevant terms can be highlighted in the term summarization segment.

Text summarization method and apparatus using a multidimensional subspace

Query-based text summarization

A method and system are provided for determining metadata to be assigned to a document. A document is identified to be published to a collection of documents. A category for publishing the document to the collection is automatically recommended using a text classifier. At least one category for the document may be selected, and the selected category is assigned as metadata for the document. A method and system are also provided for constructing a search for a document in a collection of documents. A search query is entered for a document in a collection of documents. A search category for searching for the document in the collection of documents is automatically recommended using a text classifier. At least one search category for searching for the document is selected.

Knowledge management using text classification

Provided are improved methods, apparatus, and computer program products for text differentiation which involves identifying differences between documents with similar content, not merely similar terms, and generating results. Text differentiation provides the ability to find non-similar, or different, content hidden within documents with similar overall content, but not exactly the same content. Text differentiation may be used to quickly identify key differences between similar documents.

Text differentiation methods, systems, and computer program products for content analysis

Methods, apparatus and computer program products are provided for retrieving information from a text data collection and for classifying a document into none, one or more of a plurality of predefined classes. In each aspect, a representation of at least a portion of the original matrix is projected into a lower dimensional subspace and those portions of the subspace representation that relate to the term(s) of the query are weighted following the projection into the lower dimensional subspace. In order to retrieve the documents that are most relevant with respect to a query, the documents are then scored with documents having better scores being of generally greater relevance. Alternatively, in order to classify a document, the relationship of the document to the classes of documents is scored with the document then being classified in those classes, if any, that have the best scores.

Methods, apparatus and computer program products for information retrieval and document classification utilizing a multidimensional subspace

A text mining program is provided that allows a user to perform text mining operations, such as: information retrieval, term and document visualization, term and document clustering, term and document classification, summarization of individual documents and groups of documents, and document cross-referencing. This is accomplished by representing the text of a document collection using subspace transformations. This subspace transformation representation is performed by: constructing a term frequency matrix of the term frequencies for each of the documents, transforming the term frequencies for statistical purposes, and projecting the documents or the terms into a lower dimensional subspace. As the document collection is updated, the subspace is dynamically updated to reflect the new document collection.

Growing community of inventors

Bellevue, WA, United States of America

Stephen Robert Poteet