Patents by Inventor Robert Yuji Haitani
Robert Yuji Haitani 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).
-
Publication number: 20180330270Abstract: Techniques described herein include systems and methods for evaluating an unsupervised machine learning model. In some embodiments, the system identifies item-to-item similarity values based on historical transaction data. The system may also generate collection data for a number of users based on the historical transaction data. Similarity matrices may be created for each pair of users that include rows associated with a first collection and columns associated with a second collection. Each data field in the similarity matrix may indicate an item-to-item similarity value as identified by the system. In some embodiments, a similarity score may be calculated for the user pair based on the item-to-item similarity values included in the similarity matrix. In some embodiments, the system may generate a graphical summary representation of the similarity matrix.Type: ApplicationFiled: May 15, 2017Publication date: November 15, 2018Inventors: Charles Shearer Dorner, Robert Yuji Haitani, Sven Daehne
-
Patent number: 10120880Abstract: Systems and methods are described that recommend images, items, and/or metadata based at least in part on a reference color palette or reference color name. A color name can be converted into a representation of the color name in a color space. The reference color can be used to identify images that contain the reference color. The identified images and associated metadata can be analyzed, sorted and provided as an ordered list of items. Systems and methods are also described that identify items that contain colors affiliated with the reference color. Systems and methods are also described that validate color identifier information in metadata associated with an image. Systems and methods are also described that identify non-color specific keywords associated with the reference color.Type: GrantFiled: June 26, 2014Date of Patent: November 6, 2018Assignee: Amazon Technologies, Inc.Inventors: Charles Shearer Dorner, Robert Yuji Haitani, Timothy Andrew Ong, Gonzalo Alberto Ramos, Paul Barnhart Sayre, III
-
Patent number: 10097679Abstract: A mobile computing device is disclosed. In some aspects, the mobile computing device may execute a first application using one or more processors, and may receive, during execution of the first application, a user selection of a shift key. The mobile computing device may transition a state of the shift key from an unlocked non-shift state to a shift state based on the user selection. The mobile computing device may change the execution of the first application to an execution of a second application, and clear the state of the shift key in response to changing the execution from the first application to the second application.Type: GrantFiled: May 31, 2017Date of Patent: October 9, 2018Assignee: QUALCOMM IncorporatedInventors: Jeffrey Charles Hawkins, Thomas Bridgwater, Robert Yuji Haitani, William Rees
-
Patent number: 10073860Abstract: Systems and methods are described herein to generate visualizations associated with color palettes identified from keyword searches. Color palettes may include colors determined by human color preferences. Color palettes may be searched by name or other data associated with the color palettes based at least in part on text or audio data. Visualizations such as mood lighting and/or atmosphere colors may be based at least in part on the searched color palettes.Type: GrantFiled: June 26, 2014Date of Patent: September 11, 2018Assignee: Amazon Technologies, Inc.Inventors: Robert Yuji Haitani, Jenny Ann Blackburn, Charles Shearer Dorner, Eva Manolis, Timothy Andrew Ong, Paul Barnhart Sayre, III
-
Patent number: 10049466Abstract: Systems and methods are provided for generating color names for colors corresponding to images and/or palettes. A color image is obtained, and one or more color palettes corresponding to the color image are identified. The color palette may be generated based on palette generation criteria, which may facilitate or control a palette generation process. Illustratively, the palette generation process may include image pre-processing, color distribution generation, representative color identification, palette candidate generation, and palette determination. A color name for each color identified in the color palette and/or the color image can be identified based at least in part on color name popularity information. Color name popularity information may be identified from color name-related voting results provided by a social network site.Type: GrantFiled: October 20, 2017Date of Patent: August 14, 2018Assignee: Amazon Technologies, Inc.Inventors: Charles Shearer Dorner, Robert Yuji Haitani, Gonzalo Alberto Ramos, Paul Barnhart Sayre, III
-
Patent number: 10019143Abstract: Systems and methods are provided for determining a principal image from a collection of images presented in a perspective view. A perspective view of images may be interactive and/or images may simultaneously increase or decrease in size in response to user interaction. Methods and/or techniques may be used to determine a principal image from a set of images based on a direction, speed, and/or velocity of movement or user interaction. A principal image in the perspective view may be the largest currently presented image and/or may be presented at the forefront to the user. Furthermore, an animation and/or video may be presented to the user following a determination of a principal image and/or after a configurable period of time without subsequent user interaction, which may further highlight or bring attention to a particular item to the user.Type: GrantFiled: September 29, 2014Date of Patent: July 10, 2018Assignee: Amazon Technologies, Inc.Inventors: Robert Yuji Haitani, Charles Shearer Dorner, Janet Ellen Galore, Dominick Khanh Pham, Gonzalo Alberto Ramos
-
Publication number: 20180158128Abstract: Systems and methods are provided for generating color-related item recommendations using color palette information. A request may be received from a user for a color-related item recommendation. The request may include an input image and one or more item attributes. Based at least in part on an analysis of the input image to identify affiliated colors to the input image and the one or more item attributes, one or more items corresponding to the affiliated colors and the one or more item attributes are identified. Where there is more than one identified item, a ranking for the identified plurality of items may be generated. Item recommendations comprising at least a portion of the identified plurality of items in accordance with the generated ranking may be provided for presentation on a user device.Type: ApplicationFiled: February 1, 2018Publication date: June 7, 2018Inventors: Charles Shearer Dorner, Jenny Ann Blackburn, Robert Yuji Haitani, Eva Manolis, Timothy Andrew Ong
-
Patent number: 9961382Abstract: Features are provided for the identification of objects in content, such as video content, by analyzing data regarding viewer interactions with other content. The interaction data can be analyzed to identify correlations between time periods of the video (or the video in general) and items that are the subject of, or otherwise associated with, other content with which viewers interact. These correlations can be used to provide, to subsequent viewers of the video, information regarding the items shown in the video, recommendations regarding items or content that may be of interest to subsequent viewers of the video, etc.Type: GrantFiled: September 27, 2016Date of Patent: May 1, 2018Assignee: Amazon Technologies, Inc.Inventors: Charles Shearer Dorner, Robert Yuji Haitani, Jongwoo Lee
-
Patent number: 9916613Abstract: Systems and methods are provided for generating color-related item recommendations using color palette information. A request may be received from a user for a color-related item recommendation. The request may include an input image and one or more item attributes. Based at least in part on an analysis of the input image to identify affiliated colors to the input image and the one or more item attributes, one or more items corresponding to the affiliated colors and the one or more item attributes are identified. Where there is more than one identified item, a ranking for the identified plurality of items may be generated. Item recommendations comprising at least a portion of the identified plurality of items in accordance with the generated ranking may be provided for presentation on a user device.Type: GrantFiled: June 26, 2014Date of Patent: March 13, 2018Assignee: Amazon Technologies, Inc.Inventors: Charles Shearer Dorner, Jenny Ann Blackburn, Robert Yuji Haitani, Eva Manolis, Timothy Andrew Ong
-
Patent number: 9892133Abstract: A system that verifies the attributes included in the description of an item using artificial intelligence is provided. For example, the system may use a feature extractor to identify color, shape, and/or texture features of a provided image. The system may then use a linear classifier to process the extracted features to identify attributes of the item depicted in the image. The system may compare the identified attributes with the attributes listed in the item's description. If there are any discrepancies, the system may revise the item description to include the identified attributes or provide suggested revisions to a user based on the identified attributes.Type: GrantFiled: March 13, 2015Date of Patent: February 13, 2018Assignee: Amazon Technologies, Inc.Inventors: Felix Biessmann, Cédric Philippe Charles Jean Ghislain Archambeau, Charles Shearer Dorner, Karl Anders Gyllstrom, Robert Yuji Haitani, Aengus Gabriel Martin
-
Publication number: 20180040142Abstract: Systems and methods are provided for generating color names for colors corresponding to images and/or palettes. A color image is obtained, and one or more color palettes corresponding to the color image are identified. The color palette may be generated based on palette generation criteria, which may facilitate or control a palette generation process. Illustratively, the palette generation process may include image pre-processing, color distribution generation, representative color identification, palette candidate generation, and palette determination. A color name for each color identified in the color palette and/or the color image can be identified based at least in part on color name popularity information. Color name popularity information may be identified from color name-related voting results provided by a social network site.Type: ApplicationFiled: October 20, 2017Publication date: February 8, 2018Inventors: Charles Shearer Dorner, Robert Yuji Haitani, Gonzalo Alberto Ramos, Paul Barnhart Sayre, III
-
Patent number: 9836856Abstract: Systems and methods are provided for generating color names for colors corresponding to images and/or palettes. A color image is obtained, and one or more color palettes corresponding to the color image are identified. The color palette may be generated based on palette generation criteria, which may facilitate or control a palette generation process. Illustratively, the palette generation process may include image pre-processing, color distribution generation, representative color identification, palette candidate generation, and palette determination. A color name for each color identified in the color palette and/or the color image can be identified based at least in part on color name popularity information. Color name popularity information may be identified from color name-related voting results provided by a social network site.Type: GrantFiled: December 5, 2016Date of Patent: December 5, 2017Assignee: Amazon Technologies, Inc.Inventors: Charles Shearer Dorner, Robert Yuji Haitani, Gonzalo Alberto Ramos, Paul Barnhart Sayre, III
-
Publication number: 20170272563Abstract: A mobile computing device is disclosed. In some implementations, the mobile computing device may receive, from a user, an input character string for presentation on a touch-sensitive display of the mobile computing device, may select a replacement character string based on the input character string, and may replace the input character string with the selected replacement character string. In some aspects, the input character string may be a misspelled word and the replacement character string may be a correctly spelled version of the misspelled word. In other aspects, the input character string may be an abbreviation and the replacement character string may be a completed version of the abbreviation.Type: ApplicationFiled: June 6, 2017Publication date: September 21, 2017Inventors: Jeffrey Charles Hawkins, Thomas Bridgwater, Robert Yuji Haitani, William Rees
-
Publication number: 20170270620Abstract: Systems and methods are provided for generating social networking recommendations. A color preference of a first user may be determined from a color palette of a first image associated with the user and/or a color palette of an item associated with the user. Other users may be identified that have a similar color preference as the first user based at least in part on the determined color preference of the first user. Interactions between the first user and one or more other users having similar color preferences with respect to the first user may be facilitated. A social networking recommendation may be generated with respect to the one or more other users having similar color preferences with respect to the first user.Type: ApplicationFiled: June 7, 2017Publication date: September 21, 2017Inventors: Robert Yuji Haitani, Jenny Ann Blackburn, Charles Shearer Dorner, Eva Manolis, Timothy Andrew Ong
-
Publication number: 20170264732Abstract: A mobile computing device is disclosed. In some aspects, the mobile computing device may execute a first application using one or more processors, and may receive, during execution of the first application, a user selection of a shift key. The mobile computing device may transition a state of the shift key from an unlocked non-shift state to a shift state based on the user selection. The mobile computing device may change the execution of the first application to an execution of a second application, and clear the state of the shift key in response to changing the execution from the first application to the second application.Type: ApplicationFiled: May 31, 2017Publication date: September 14, 2017Inventors: Jeffrey Charles Hawkins, Thomas Bridgewater, Robert Yuji Haitani, William Rees
-
Patent number: 9697573Abstract: Systems and methods are provided for generating social networking recommendations. A color preference of a first user may be determined from a color palette of a first image associated with the user and/or a color palette of an item associated with the user. Other users may be identified that have a similar color preference as the first user based at least in part on the determined color preference of the first user. Interactions between the first user and one or more other users having similar color preferences with respect to the first user may be facilitated. A social networking recommendation may be generated with respect to the one or more other users having similar color preferences with respect to the first user.Type: GrantFiled: June 26, 2014Date of Patent: July 4, 2017Assignee: Amazon Technologies, Inc.Inventors: Robert Yuji Haitani, Jenny Ann Blackburn, Charles Shearer Dorner, Eva Manolis, Timothy Andrew Ong
-
Patent number: 9679532Abstract: Systems and methods are described that recommend images, items, and/or metadata based at least in part on a reference color palette or reference color name. A color name can be converted into a representation of the color name in a color space. The reference color can be used to identify images that contain the reference color. The identified images and associated metadata can be analyzed, sorted and provided as an ordered list of items. Systems and methods are also described that identify items that contain colors affiliated with the reference color. Systems and methods are also described that validate color identifier information in metadata associated with an image. Systems and methods are also described that identify non-color specific keywords associated with the reference color.Type: GrantFiled: June 26, 2014Date of Patent: June 13, 2017Assignee: Amazon Technologies, Inc.Inventors: Charles Shearer Dorner, Jenny Ann Blackburn, Janet Ellen Galore, Robert Yuji Haitani, William R. Hazlewood, Timothy Andrew Ong, Dominick Pham, Gonzalo Alberto Ramos, Paul Barnhart Sayre, III
-
Publication number: 20170084053Abstract: Systems and methods are provided for generating color names for colors corresponding to images and/or palettes. A color image is obtained, and one or more color palettes corresponding to the color image are identified. The color palette may be generated based on palette generation criteria, which may facilitate or control a palette generation process. Illustratively, the palette generation process may include image pre-processing, color distribution generation, representative color identification, palette candidate generation, and palette determination. A color name for each color identified in the color palette and/or the color image can be identified based at least in part on color name popularity information. Color name popularity information may be identified from color name-related voting results provided by a social network site.Type: ApplicationFiled: December 5, 2016Publication date: March 23, 2017Inventors: Charles Shearer Dorner, Robert Yuji Haitani, Gonzalo Alberto Ramos, Paul Barnhart Sayre, III
-
Patent number: D803867Type: GrantFiled: May 9, 2016Date of Patent: November 28, 2017Assignee: Amazon Technologies, Inc.Inventors: Robert Yuji Haitani, Janet Ellen Galore, Dominick Khanh Pham, Gonzalo Alberto Ramos, Stefan Vant
-
Patent number: D803868Type: GrantFiled: May 9, 2016Date of Patent: November 28, 2017Assignee: Amazon Technologies, Inc.Inventors: Robert Yuji Haitani, Janet Ellen Galore, Dominick Khanh Pham, Gonzalo Alberto Ramos, Stefan Vant