Brian Paul Wallenfelt

7574420, Aug 11, 2009

Nov 17, 2005

11/282092

Cary Lee Bates - Rochester MN, US
Brian Paul Wallenfelt - Rochester MN, US

International Business Machines Corporation - Armonk NY

G06F 7/00

707 2

A method, apparatus, system, and storage medium that, in an embodiment, create an index for pages based on association scores for the pages with respect to geographic regions, where the association scores indicate relative degrees to which the pages are associated with the geographic regions. In an embodiment, the association scores are determined by adding a term scare to the association score if a term that is associated with the geographic region is present in the page. The term score indicates a relative degree to which presence of the term in the page indicates that the page is associated with the geographic region. In an embodiment, the association scores are further increased based on association scores of neighbor geographic regions and based on the association scores of incoming linked pages.

7590536, Sep 15, 2009

Oct 7, 2005

11/246831

Cary L. Bates - Rochester MN, US
Brian P. Wallenfelt - Rochester MN, US

Nuance Communications, Inc. - Burlington MA

G10L 15/06

704244, 704231, 704243, 704257

Methods, systems and computer readable medium for improving the accuracy of voice processing are provided. Embodiments of the present invention generally provide methods, systems and articles of manufacture for adjusting a language model within a voice recognition system. In one embodiment, changes are made to the language model by identifying a word-usage pattern that qualifies as an anomaly. In one embodiment, an anomaly occurs when the use of a given word (or phrase) differs from an expected probability for the word (or phrase), as predicted by a language model. Additionally, observed anomalies may be shared and applied by different users of the voice processing system, depending on an affinity in word-usage frequency between different users.

7680048, Mar 16, 2010

Oct 6, 2006

11/539329

Charles Jens Archer - Rochester MN, US
Roy Glenn Musselman - Rochester MN, US
Amanda Peters - Rochester MN, US
Kurt Walter Pinnow - Rochester MN, US
Brent Allen Swartz - Chippewa Falls WI, US
Brian Paul Wallenfelt - Eden Prairie MN, US

International Business Machiens Corporation - Armonk NY

G01R 31/08
G06F 11/00
H04L 12/28
H04L 12/56

370235, 370400

A massively parallel computer system contains an inter-nodal communications network of node-to-node links. Each node implements a respective routing strategy for routing data through the network, the routing strategies not necessarily being the same in every node. The routing strategies implemented in the nodes are dynamically adjusted during application execution to shift network workload as required. Preferably, adjustment of routing policies in selective nodes is performed at synchronization points. The network may be dynamically monitored, and routing strategies adjusted according to detected network conditions.

7706275, Apr 27, 2010

Feb 7, 2007

11/672315

Charles Jens Archer - Rochester MN, US
Roy Glenn Musselman - Rochester MN, US
Amanda Peters - Rochester MN, US
Kurt Walter Pinnow - Rochester MN, US
Brent Allen Swartz - Chippewa Falls WI, US
Brian Paul Wallenfelt - Eden Prairie MN, US

International Business Machines Corporation - Armonk NY

G01R 31/08

370235, 370389, 709240

A massively parallel computer system contains an inter-nodal communications network of node-to-node links. An automated routing strategy routes packets through one or more intermediate nodes of the network to reach a final destination. The default routing strategy is altered responsive to detection of overutilization of a particular path of one or more links, and at least some traffic is re-routed by distributing the traffic among multiple paths (which may include the default path). An alternative path may require a greater number of link traversals to reach the destination node.

7765218, Jul 27, 2010

Sep 30, 2004

10/955743

Cary Lee Bates - Rochester MN, US
Brian Paul Wallenfelt - Rochester MN, US

International Business Machines Corporation - Armonk NY

G06F 7/00
G06F 17/30
G06Q 10/00

707752, 705 11, 715200

A method, apparatus, system, and signal-bearing medium that, in an embodiment, determine a term score based on frame scores, frame weights, and effect bonuses. The frame score represents a probability that the frame will be displayed, and in an embodiment is based on whether the frame may be skipped via an embedded link between frames. Frames that may be skipped have their frame scores reduced. The frame weights are based on an attribute of the term, such as a font size, a font style, a color, or a location within a frame. The effect bonus is based on one or more attributes of the nearest tweened object to the term, such as a location, a size, a shape, or a color. The term score may be used to order the display of the pages that contain the frames in response to a search request. In this way, terms within the frames of an animated graphics file are scored based on the likelihood that the term will be seen during the animation.

7783933, Aug 24, 2010

Sep 14, 2006

11/531787

Charles J. Archer - Rochester MN, US
Kurt W. Pinnow - Rochester MN, US
Brian P. Wallenfelt - Eden Prairie MN, US

International Business Machines Corporation - Armonk NY

G06F 11/00

714 47

Methods, parallel computers, and products are provided for identifying failure in a tree network of a parallel computer. The parallel computer includes one or more processing sets including an I/O node and a plurality of compute nodes. For each processing set embodiments include selecting a set of test compute nodes, the test compute nodes being a subset of the compute nodes of the processing set; measuring the performance of the I/O node of the processing set; measuring the performance of the selected set of test compute nodes; calculating a current test value in dependence upon the measured performance of the I/O node of the processing set, the measured performance of the set of test compute nodes, and a predetermined value for I/O node performance; and comparing the current test value with a predetermined tree performance threshold. If the current test value is below the predetermined tree performance threshold, embodiments include selecting another set of test compute nodes. If the current test value is not below the predetermined tree performance threshold, embodiments include selecting from the test compute nodes one or more potential problem nodes and testing individually potential problem nodes and links to potential problem nodes.

7835284, Nov 16, 2010

Oct 6, 2006

11/539300

Charles Jens Archer - Rochester MN, US
Roy Glenn Musselman - Rochester MN, US
Amanda Peters - Rochester MN, US
Kurt Walter Pinnow - Rochester MN, US
Brent Allen Swartz - Chippewa Falls WI, US
Brian Paul Wallenfelt - Eden Prairie MN, US

International Business Machines Corporation - Armonk NY

G01R 31/08
G06F 11/00
H04L 12/50
H04Q 11/00

370235, 370386

A massively parallel computer system contains an inter-nodal communications network of node-to-node links. An automated routing strategy routes packets through one or more intermediate nodes of the network to reach a destination. Some packets are constrained to be routed through respective designated transporter nodes, the automated routing strategy determining a path from a respective source node to a respective transporter node, and from a respective transporter node to a respective destination node. Preferably, the source node chooses a routing policy from among multiple possible choices, and that policy is followed by all intermediate nodes. The use of transporter nodes allows greater flexibility in routing.

7836039, Nov 16, 2010

Dec 12, 2006

11/609698

Timothy Pressler Clark - Rochester MN, US
Zachary Adam Garbow - Rochester MN, US
Richard Michael Theis - Sauk Rapids MN, US
Brian Paul Wallenfelt - Eden Prairie MN, US

International Business Machines Corporation - Armonk NY

G06F 7/00

707706, 707707

A request is received that includes a primary keyword and a persistent keyword. In response to the request, a root page is found that includes a first term that matches the primary keyword. Descendant pages of the root page are searched for a second term that matches the persistent keyword. The search determines that the descendant pages are at levels on paths from the root page and that the levels are within a depth from the root page. A descendant page is found that is a descendant of the root page and that includes a second term that matches the persistent keyword. A root link that points at the root page and a descendant link that points at the descendant page are sent to the requester. If the number of times that the primary keyword was received is greater than a threshold number, then the primary keyword is added to the persistent keywords.