Patents by Inventor Harry R. Silver
Harry R. Silver has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10474710Abstract: Systems and methods for generating issue networks are disclosed. In one embodiment, a computer-implemented method of generating an issue network from a document corpus includes searching, using a computer, the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus. The method further includes determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue, and determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents. The method also includes linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network.Type: GrantFiled: February 27, 2018Date of Patent: November 12, 2019Assignee: RELX, Inc.Inventors: Paul Zhang, Sanjay Sharma, Mark Wasson, Harry R. Silver, David Steiner
-
Publication number: 20190310988Abstract: Systems, methods, and computer-executable instructions for identifying a document are described. A method includes receiving a query from a graphical user interface having one or more concepts, normalizing a set of terms or concepts in the query to create a normalized query, comparing the normalized query to a set of document centric concept profiles associated with a set of documents in a corpus, where each document centric concept includes a plurality of concepts and at least one reference value for each concept, where the reference value is calculated by tabulating the number of times a document associated with one of the document centric concept profiles is cited by a citing instance for the concept, and surfacing a document from the corpus with the highest reference value for the concept.Type: ApplicationFiled: June 21, 2019Publication date: October 10, 2019Applicant: LEXISNEXIS, A DIVISION OF REED ELSEVIER INC.Inventors: Paul Zhang, Harry R. Silver
-
Patent number: 10372717Abstract: Systems, methods, and computer-executable instructions for identifying a document are described. A method includes receiving a query from a graphical user interface having one or more concepts, normalizing a set of terms or concepts in the query to create a normalized query, comparing the normalized query to a set of document centric concept profiles associated with a set of documents in a corpus, where each document centric concept includes a plurality of concepts and at least one reference value for each concept, where the reference value is calculated by tabulating the number of times a document associated with one of the document centric concept profiles is cited by a citing instance for the concept, and surfacing a document from the corpus with the highest reference value for the concept.Type: GrantFiled: October 26, 2015Date of Patent: August 6, 2019Assignee: LexisNexis, a division of Reed Elsevier Inc.Inventors: Paul Zhang, Harry R. Silver
-
Publication number: 20180189386Abstract: Systems and methods for generating issue networks are disclosed. In one embodiment, a computer-implemented method of generating an issue network from a document corpus includes searching, using a computer, the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus. The method further includes determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue, and determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents. The method also includes linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network.Type: ApplicationFiled: February 27, 2018Publication date: July 5, 2018Applicant: LexisNexis, a division of Reed Elsevier, Inc.Inventors: Paul Zhang, Sanjay Sharma, Mark Wasson, Harry R. Silver, David Steiner
-
Patent number: 9940389Abstract: Systems and methods for generating issue networks are disclosed. In one embodiment, a computer-implemented method of generating an issue network from a document corpus includes searching, using a computer, the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus. The method further includes determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue, and determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents. The method also includes linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network.Type: GrantFiled: April 6, 2016Date of Patent: April 10, 2018Assignee: LexisNexis, A Division of Reed Elsevier, Inc.Inventors: Paul Zhang, Sanjay Sharma, Mark Wasson, Harry R. Silver, David Steiner
-
Publication number: 20170060991Abstract: Systems and method for generating concepts from a document corpus are disclosed. In one embodiment, a method for generating concepts from a document includes retrieving, a plurality of terms stored within a first lexicon. The method further includes, for individual terms stored within the first lexicon: determining a first frequency of the term within the document corpus, and determining a second frequency of the term within a comparison document corpus including a plurality of comparison documents, wherein the comparison document corpus is different from the document corpus. The method further includes, for individual terms within the first lexicon: determining a difference between the first frequency and the second frequency, comparing the difference between the first frequency and the second frequency to a comparison metric, and, when the difference between the first frequency and the second frequency satisfies the comparison metric, storing the term as a concept within a second lexicon.Type: ApplicationFiled: November 10, 2016Publication date: March 2, 2017Applicant: LexisNexis, a division of Reed Elsevier Inc.Inventors: Paul Zhang, Sanjay Sharma, David Steiner, Mark David Wasson, Harry R. Silver, Robin Warling
-
Publication number: 20160217208Abstract: Systems and methods for generating issue networks are disclosed. In one embodiment, a computer-implemented method of generating an issue network from a document corpus includes searching, using a computer, the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus. The method further includes determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue, and determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents. The method also includes linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network.Type: ApplicationFiled: April 6, 2016Publication date: July 28, 2016Applicant: LexisNexis, a division of Reed Elsevier Inc.Inventors: Paul Zhang, Sanjay Sharma, Mark Wasson, Harry R. Silver, David Steiner
-
Patent number: 9336305Abstract: Systems and methods for generating issue networks are disclosed. In one embodiment, a computer-implemented method of generating an issue network from a document corpus includes searching, using a computer, the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus. The method further includes determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue, and determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents. The method also includes linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network.Type: GrantFiled: May 9, 2013Date of Patent: May 10, 2016Assignee: Lexis Nexis, a division of Reed Elsevier Inc.Inventors: Paul Zhang, Sanjay Sharma, Mark Wasson, Harry R. Silver, David Steiner
-
Publication number: 20160098407Abstract: Systems, methods, and computer-executable instructions described herein generally relate to increasing user productivity in reviewing query results by surfacing a set of documents ranked by their relative value calculated as a tabulation of how often they are cited for a specific purpose. A database management system can access an index of metadata corresponding to a set of content items in a corpus/corpora of electronically stored content. A sub-system is configured to receive a query request entered by a user in said interactive GUI.Type: ApplicationFiled: October 26, 2015Publication date: April 7, 2016Applicant: LexisNexis, a division of Reed Elsevier Inc.Inventors: Paul Zhang, Harry R. Silver
-
Patent number: 9201969Abstract: Systems, methods, and computer-executable instructions described herein relate to surfacing a set of documents ranked by their relative value calculated as a tabulation of how often they are cited for a specific purpose. In one embodiment a computer machine is configured to receive a query as computer machine input, automatically determine at least one concept contained within the query and automatically normalize the at least one concept contained within the query, thus creating at least one normalized concept. The computer machine is further configured to automatically compare the at least one normalized concept to at least one document centric concept profile associated with the set of content items in the corpora; and automatically surface a set of documents matching the document centric concept profile. The set of documents are ranked according to a reference value assigned to each document for a normalized concept.Type: GrantFiled: January 31, 2013Date of Patent: December 1, 2015Assignee: LexisNexis, a division of Reed Elsevier Inc.Inventors: Paul Zhang, Harry R. Silver
-
Publication number: 20150088875Abstract: Systems and methods facilitate a search and identify documents and associated metadata reflecting content of the documents. In one implementation, a method receives a query comprising a set of search terms, identifies a stored document in response to the query, and determines a score value for the retrieved document based on a similarity between one or more of the query search terms and metadata associated with the identified document. The method locates the identified document in a citation network of baseline query results, the citation network comprising a first set of documents that cite to the identified document and a second set of documents cited to by the identified document. The method further determines a new score value of the identified document as a function of the score value and a quantity and a quality of documents within the first and second set of documents.Type: ApplicationFiled: October 7, 2014Publication date: March 26, 2015Applicant: LexisNexis, a division of Reed Elsevier Inc.Inventors: Ling Qin Zhang, Harry R. Silver
-
Publication number: 20140337318Abstract: Systems and methods for generating issue networks are disclosed. In one embodiment, a computer-implemented method of generating an issue network from a document corpus includes searching, using a computer, the document corpus for a set of documents discussing a starting issue, wherein the starting issue is one of a plurality of normalized issues defined by the document corpus. The method further includes determining a set of normalized issues discussed by the set of documents discussing the starting issue, wherein the set of normalized issues also includes the starting issue, and determining instances of co-occurrences of individual normalized issues of the set of normalized issues within individual cases of the set of documents. The method also includes linking individual normalized issues of the set of normalized issues based on their co-occurrences within the set of documents, wherein the linked individual normalized issues at least in part define the issue network.Type: ApplicationFiled: May 9, 2013Publication date: November 13, 2014Applicant: LexisNexis, a division of Reed Elsevier Inc.Inventors: Paul Zhang, Sanjay Sharma, Mark Wasson, Harry R. Silver, David Steiner
-
Patent number: 8886638Abstract: Systems and methods facilitate a search and identify documents and associated metadata reflecting content of the documents. In one implementation, a method receives a query comprising a set of search terms, identifies a stored document in response to the query, and determines a score value for the retrieved document based on a similarity between one or more of the query search terms and metadata associated with the identified document. The method locates the identified document in a citation network of baseline query results, the citation network comprising a first set of documents that cite to the identified document and a second set of documents cited to by the identified document. The method further determines a new score value of the identified document as a function of the score value and a quantity and a quality of documents within the first and second set of documents.Type: GrantFiled: February 23, 2012Date of Patent: November 11, 2014Assignee: LexisNexisInventors: Ling Qin Zhang, Harry R. Silver
-
Publication number: 20140214825Abstract: Systems, methods, and computer-executable instructions described herein generally relate to increasing user productivity in reviewing query results by surfacing a set of documents ranked by their relative value calculated as a tabulation of how often they are cited for a specific purpose. A database management system can access an index of metadata corresponding to a set of content items in a corpus/corpora of electronically stored content. A sub-system is configured to receive a query request entered by a user in said interactive GUI.Type: ApplicationFiled: January 31, 2013Publication date: July 31, 2014Applicant: LexisNexis, a division of Reed Elsevier Inc.Inventors: Paul Zhang, Harry R. Silver
-
Publication number: 20120215796Abstract: Systems and methods facilitate a search and identify documents and associated metadata reflecting content of the documents. In one implementation, a method receives a query comprising a set of search terms, identifies a stored document in response to the query, and determines a score value for the retrieved document based on a similarity between one or more of the query search terms and metadata associated with the identified document. The method locates the identified document in a citation network of baseline query results, the citation network comprising a first set of documents that cite to the identified document and a second set of documents cited to by the identified document. The method further determines a new score value of the identified document as a function of the score value and a quantity and a quality of documents within the first and second set of documents.Type: ApplicationFiled: February 23, 2012Publication date: August 23, 2012Inventors: Ling Qin Zhang, Harry R. Silver
-
Patent number: 8150831Abstract: Systems and methods facilitate a search and identify documents and associated metadata reflecting content of the documents. In one implementation, a method receives a query comprising a set of search terms, identifies a stored document in response to the query, and determines a score value for the retrieved document based on a similarity between one or more of the query search terms and metadata associated with the identified document. The method locates the identified document in a citation network of baseline query results, the citation network comprising a first set of documents that cite to the identified document and a second set of documents cited to by the identified document. The method further determines a new score value of the identified document as a function of the score value and a quantity and a quality of documents within the first and second set of documents.Type: GrantFiled: April 15, 2009Date of Patent: April 3, 2012Assignee: LexisNexisInventors: Ling Qin Zhang, Harry R. Silver
-
Publication number: 20110191335Abstract: Disclosed herein are various exemplary systems and methods for conducting legal research using clustering analytics. A system for building relationships between passages, the system comprising a passage generation module configured to generate passages from one or more case law documents, an annotation module configured to annotate the passages based on one or more attributes, and a clustering module configured to build relationship clusters between the passages based on the one or more attributes.Type: ApplicationFiled: January 29, 2010Publication date: August 4, 2011Applicant: LexisNexis Risk Data Management Inc.Inventors: David J. MILLER, David Alan Bayliss, Zachary W. Bennett, Harry R. Silver
-
Publication number: 20100268708Abstract: Systems and methods facilitate a search and identify documents and associated metadata reflecting content of the documents. In one implementation, a method receives a query comprising a set of search terms, identifies a stored document in response to the query, and determines a score value for the retrieved document based on a similarity between one or more of the query search terms and metadata associated with the identified document. The method locates the identified document in a citation network of baseline query results, the citation network comprising a first set of documents that cite to the identified document and a second set of documents cited to by the identified document. The method further determines a new score value of the identified document as a function of the score value and a quantity and a quality of documents within the first and second set of documents.Type: ApplicationFiled: April 15, 2009Publication date: October 21, 2010Inventors: Ling Qin Zhang, Harry R. Silver
-
Patent number: 7765205Abstract: A landmark case identification system and method in which the user is presented with a set of the most relevant documents on a selected topic. This set, which is dynamic and asserted to be inclusive at any point in time, is presented to the user in a Virtual Digest and initially sorted by court/date order. The user has an option to resort the answer set using a Frequently Cited sort option, which causes the system to dynamically analyze the answer set for references between the documents. Landmark cases are identified by their peers in the domain as they will be referenced and relied upon most often. The user is presented with the resorted answer set, and information detailing how many other cases in the domain referenced them is now included.Type: GrantFiled: August 17, 2005Date of Patent: July 27, 2010Assignee: LexisNexisInventors: David James Miller, Harry R. Silver, Andrew L. Freisthler
-
Patent number: 7689546Abstract: A “More Like This Headnote” search relates online headnotes intelligently so that users have the means to retrieve related headnotes quickly and easily. This is achieved by using a tailored search type in the search engine, which is designed to handle the text of a headnote as a search string. Retrieval logic then presents the search results to the user in a “Virtual Digest” view comprising related headnotes and case materials, sorted by user-selected options.Type: GrantFiled: August 17, 2005Date of Patent: March 30, 2010Assignee: LexisNexis, a division of Reed Elsevier Inc.Inventors: David James Miller, Harry R. Silver, Andrew L. Freisthler