SYSTEMS, METHODS, AND SOFTWARE FOR IDENTIFYING RELEVANT LEGAL DOCUMENTS

• US 20080033929A1
• Filed: 10/04/2006
• Published: 02/07/2008
• Est. Priority Date: 12/31/2003
• Status: Active Grant

• Current Assignee: Charles Elberti, Khalid Al-Kofahi, Michael Dahn, Patrick Slaven, Qiang Lu, Thomas Zielund
• Original Assignee: Thomson Reuters Global Resources Unlimited Company (The Woodbridge Co. Ltd.)
• Inventors: Lu, Qiang, Elberti, Charles, Slaven, Patrick, Zielund, Thomas, Al-Kofahi, Khalid, Dahn, Michael
• Granted Patent: US 9,646,082 B2
• Time in Patent Office: Days
• US Class Current: 707/5
• CPC Class Codes: G06F 16/38 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 50/18 Legal services

Abstract

To facilitate legal research, companies, such as Thomson West provide subscription-based online information-retrieval systems. Seeking to improve these and/or related systems, the present inventors devised, among other things, an exemplary legal research system that performs a conventional search to identify a set of starter documents and then leverages the metadata associated with these starter documents to identify another larger set of relevant documents. Documents in this alternate set are then scored using, for example, a learning machine and feature vectors that account for metadata relationships between the starter documents and alternate documents.

Claims

1. A system comprising:

means for receiving a query for legal information from a user via a client access device;

means for identifying a first set of documents from a database using the query;

means, responsive to metadata associated with one or more of the identified first set of documents, for identifying a second set of documents; and

means for ranking the second set of documents; and

means for outputting a list of one or more of the ranked documents to the client access device.

2. The system of claim 1, wherein the means for ranking the second set of documents includes a learning machine for processing a plurality of feature vectors, with each feature vector including a feature based on text similarity, a feature based on number of shared legal classification codes;

and a feature based on number of shared legal citations.

3. The system of claim 1, wherein each of the means comprises a machine-executable medium carrying machine-executable instructions.

4. The system of claim 3, further comprising a server having a processor coupled to a memory, with the memory including each machine-executable medium.

5. The system of claim 1, wherein the means for outputting the list of one or more of the ranked documents include a means for defining a graphical user interface on the client access device, with the interface including a region for displaying the list, region for displaying related trial documents, and a region for displaying one or more legal classification identifiers.

6. A method comprising:

identifying a first set of documents from a database using a query;

automatically identifying a second set of two or more documents based on metadata associated with one or more of the identified first set of documents; and

automatically ranking the second set of documents; and

automatically outputting a list of one or more of the ranked documents to a client access device.

7. The method of claim 6, wherein the ranking the second set of documents includes using a learning machine to process a plurality of feature vectors, with each feature vector including a feature based on text similarity, a feature based on number of shared legal classification codes;

and a feature based on number of shared legal citations.

8. The method of claim 6, wherein outputting the list of one or more of the ranked documents include defining a graphical user interface on the client access device, with the interface including a region for displaying the list, region for displaying related trial documents, and a region for displaying one or more legal classification identifiers.