Patents by Inventor Jacob Walker

Jacob Walker 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: 20240311382
    Abstract: A record processing and storage system operates by: receiving formatted row data that includes a fixed-length batch section and a temporary variable-length batch section; storing, in a compressed data format, at least one variable-length data value of each of a plurality of temporary variable-length row sections of each of the plurality of formatted row data; generating a plurality of modified formatted row data from the plurality of formatted row data by, for each formatted row data, replacing a fixed-length offset value for each variable-length field stored in the compressed data format with a key value utilized to access the corresponding variable-length data value in the compressed data format; and truncating the each formatted row data to remove inclusion of the temporary variable-length batch section; and storing the plurality of modified formatted row data as a plurality of pages in a page storage system.
    Type: Application
    Filed: May 22, 2024
    Publication date: September 19, 2024
    Applicant: Ocient Holdings LLC
    Inventors: George Kondiles, Jacob Walker Trueb, Philip Joseph Dakin
  • Patent number: 12032581
    Abstract: A record processing and storage system is operable to receive a plurality of formatted record data. Each of the plurality of formatted record data includes a fixed-length batch section that includes a plurality of fixed-length row sections. Each of the plurality of fixed-length row sections includes at least one fixed-length data value at least one fixed-length offset value. Each of the plurality of formatted record data further includes a variable-length batch section that includes a plurality of variable-length row sections. Each of the plurality of variable-length row sections includes at least one variable-length data value, where the fixed-length offset value for the corresponding one of the plurality of records indicates an offset of the at least one variable-length data value in the each formatted record data. A plurality of pages that include the plurality of formatted record data are generated and stored in a page storage system.
    Type: Grant
    Filed: July 18, 2023
    Date of Patent: July 9, 2024
    Assignee: Ocient Holdings LLC
    Inventors: George Kondiles, Jacob Walker Trueb, Philip Joseph Dakin
  • Publication number: 20230359633
    Abstract: A record processing and storage system is operable to receive a plurality of formatted record data. Each of the plurality of formatted record data includes a fixed-length batch section that includes a plurality of fixed-length row sections. Each of the plurality of fixed-length row sections includes at least one fixed-length data value at least one fixed-length offset value. Each of the plurality of formatted record data further includes a variable-length batch section that includes a plurality of variable-length row sections. Each of the plurality of variable-length row sections includes at least one variable-length data value, where the fixed-length offset value for the corresponding one of the plurality of records indicates an offset of the at least one variable-length data value in the each formatted record data. A plurality of pages that include the plurality of formatted record data are generated and stored in a page storage system.
    Type: Application
    Filed: July 18, 2023
    Publication date: November 9, 2023
    Applicant: Ocient Holdings LLC
    Inventors: George Kondiles, Jacob Walker Trueb, Philip Joseph Dakin
  • Patent number: 11562563
    Abstract: Methods and systems used for the classification of a crop grown within an agricultural field using remotely-sensed image data. In one example, the method involves unsupervised pixel clustering, which includes gathering pixel values and assigning them to clusters to produce a pixel distribution signal. The pixel distribution signals of the remotely-sensed image data over the growing season are summed up to generate a temporal representation of a management zone. Location information of the management zone is added to the temporal data and ingested into a Recurrent Neural Network (RNN). The output of the model is a prediction of the crop type grown in the management zone over the growing season. Furthermore, a notification can be sent to an agricultural grower or to third parties/stakeholders associated with the grower and/or the field, informing them of the crop classification prediction.
    Type: Grant
    Filed: July 13, 2020
    Date of Patent: January 24, 2023
    Assignee: Farmers Edge Inc.
    Inventors: Changchi Xian, Jacob Walker Bengtson
  • Patent number: 11521380
    Abstract: A method for shadow and cloud masking for remote sensing images of an agricultural field using multi-layer perceptrons includes electronically receiving an observed image, performing using at least one processor an image segmentation of the observed image to divide the observed image into a plurality of image segments or superpixels, extracting features for each of the image segments using the at least one processor, and determining by a cloud mask generation module executing on the at least one processor a classification for each of the image segments using the features extracted for each of the image segments, wherein the cloud mask generation module applies a classification model including an ensemble of multilayer perceptrons to generate a cloud mask for the observed image such that each pixel within the observed image has a corresponding classification.
    Type: Grant
    Filed: February 3, 2020
    Date of Patent: December 6, 2022
    Inventors: Faisal Ahmed, Jacob Walker Bengtson, David Eric Chalmers, Changchi Xian, Fatema Tuz Zohra, Chad Richard Bryant
  • Patent number: 11321941
    Abstract: A method for predicting crop yield of an agricultural field may include steps of applying a pre-season model to provide a pre-season model crop yield prediction, applying an in-season model to provide an in-season model crop yield prediction, applying a statistical imagery model to provide a statistical imagery model crop yield prediction, applying a histogram-based image model to provide a histogram-based image model crop yield prediction, applying crop-specific models to provide at least one crop-specific model crop yield prediction, and combining at a computing system crop yield predictions from a plurality of models within a set comprising the pre-season model, the in-season model, the statistical imagery model, the histogram-based image model, and the crop-specific models, to produce a final crop yield prediction.
    Type: Grant
    Filed: April 10, 2020
    Date of Patent: May 3, 2022
    Assignee: Farmers Edge Inc.
    Inventors: Jacob Walker Bengtson, Chad Richard Bryant, Changchi Xian, Charles Cuell, Keilan Scholten, Fatema Tuz Zohra
  • Patent number: 11222206
    Abstract: A method for determining harvest state of an agricultural field includes obtaining an observed image of the agricultural field from a data store containing agricultural image data, filtering the observed image using an image filtering module to provide a filtered image for processing, and assigning coordinates to the filtered image, the assigning coordinates to the filtered image performed by a coordinate projection module to provide an input image, processing the input image to determine a set of image statistics for the input image using a statistics calculation module, determining by a harvest state prediction module the harvest state of the agricultural field using the set of image statistics, wherein the harvest state is selected from a set including a pre-harvest state, an in-harvest state, and a post-harvest state and electronically transmitting a notification of the harvest state of the agricultural field to a computing device.
    Type: Grant
    Filed: January 30, 2020
    Date of Patent: January 11, 2022
    Assignee: Farmers Edge Inc.
    Inventors: Jacob Walker Bengtson, Chad Richard Bryant, Faisal Ahmed
  • Publication number: 20210019522
    Abstract: Methods and systems used for the classification of a crop grown within an agricultural field using remotely-sensed image data. In one example, the method involves unsupervised pixel clustering, which includes gathering pixel values and assigning them to clusters to produce a pixel distribution signal. The pixel distribution signals of the remotely-sensed image data over the growing season are summed up to generate a temporal representation of a management zone. Location information of the management zone is added to the temporal data and ingested into a Recurrent Neural Network (RNN). The output of the model is a prediction of the crop type grown in the management zone over the growing season. Furthermore, a notification can be sent to an agricultural grower or to third parties/stakeholders associated with the grower and/or the field, informing them of the crop classification prediction.
    Type: Application
    Filed: July 13, 2020
    Publication date: January 21, 2021
    Inventors: Changchi Xian, Jacob Walker Bengtson
  • Publication number: 20200342226
    Abstract: A method for predicting crop yield of an agricultural field may include steps of applying a pre-season model to provide a pre-season model crop yield prediction, applying an in-season model to provide an in-season model crop yield prediction, applying a statistical imagery model to provide a statistical imagery model crop yield prediction, applying a histogram-based image model to provide a histogram-based image model crop yield prediction, applying crop-specific models to provide at least one crop-specific model crop yield prediction, and combining at a computing system crop yield predictions from a plurality of models within a set comprising the pre-season model, the in-season model, the statistical imagery model, the histogram-based image model, and the crop-specific models, to produce a final crop yield prediction.
    Type: Application
    Filed: April 10, 2020
    Publication date: October 29, 2020
    Applicant: Farmers Edge Inc.
    Inventors: Jacob Walker Bengtson, Chad Richard Bryant, Changchi Xian, Charles Cuell, Keilan Scholten, Fatema Tuz Zohra
  • Patent number: 10789240
    Abstract: In some implementations, a computer-implemented method includes analyzing first data from a first data source to determine a first schema of the first data source, and analyzing second data from a second data source to determine a second schema of the second data source. The method can further include generating a first two-dimensional aggregation of a first time data series having a time dimension and a dimension corresponding to aggregated values of a first metric, and generating a second two-dimensional aggregation of a second time data series having a time dimension and a dimension corresponding to aggregated values of a second metric. The method can also include computing a correlation value between the first two-dimensional aggregation and the second two-dimensional aggregation, and providing an indication of duplicated data between the first data source and the second data source if the correlation value meets a threshold.
    Type: Grant
    Filed: November 6, 2017
    Date of Patent: September 29, 2020
    Assignee: Google LLC
    Inventors: Jacob Walker, Laura Eidem
  • Publication number: 20200250428
    Abstract: A method for shadow and cloud masking for remote sensing images of an agricultural field using multi-layer perceptrons includes electronically receiving an observed image, performing using at least one processor an image segmentation of the observed image to divide the observed image into a plurality of image segments or superpixels, extracting features for each of the image segments using the at least one processor, and determining by a cloud mask generation module executing on the at least one processor a classification for each of the image segments using the features extracted for each of the image segments, wherein the cloud mask generation module applies a classification model including an ensemble of multilayer perceptrons to generate a cloud mask for the observed image such that each pixel within the observed image has a corresponding classification.
    Type: Application
    Filed: February 3, 2020
    Publication date: August 6, 2020
    Applicant: Farmers Edge Inc.
    Inventors: Faisal Ahmed, Jacob Walker Bengtson, David Eric Chalmers, Changchi Xian, Fatema Tuz Zohra, Chad Richard Bryant
  • Publication number: 20200250427
    Abstract: A method for shadow and cloud masking for remote sensing images of an agricultural field using a convolutional neural network, the method includes electronically receiving an observed image, the observed image comprising a plurality of pixels and each of the pixels associated with corresponding band information and determining by a cloud mask generation module executing on the at least one processor a classification for each of the plurality of pixels in the observed image using the band information by applying a classification model, the classification model comprising a convolutional neural network comprising a plurality of layers of nodes. The cloud mask generation module applies a plurality of transformations to transform data between layers in the convolutional neural network to generate a cloud map.
    Type: Application
    Filed: February 3, 2020
    Publication date: August 6, 2020
    Applicant: Farmers Edge Inc.
    Inventors: Ali Mashhoori, Jacob Walker Bengtson, David Eric Chalmers, Changchi Xian, Chad Richard Bryant
  • Publication number: 20200250426
    Abstract: A method for determining harvest state of an agricultural field includes obtaining an observed image of the agricultural field from a data store containing agricultural image data, filtering the observed image using an image filtering module to provide a filtered image for processing, and assigning coordinates to the filtered image, the assigning coordinates to the filtered image performed by a coordinate projection module to provide an input image, processing the input image to determine a set of image statistics for the input image using a statistics calculation module, determining by a harvest state prediction module the harvest state of the agricultural field using the set of image statistics, wherein the harvest state is selected from a set including a pre-harvest state, an in-harvest state, and a post-harvest state and electronically transmitting a notification of the harvest state of the agricultural field to a computing device.
    Type: Application
    Filed: January 30, 2020
    Publication date: August 6, 2020
    Applicant: Farmers Edge Inc.
    Inventors: Jacob Walker Bengtson, Chad Richard Bryant, Faisal Ahmed
  • Publication number: 20190138628
    Abstract: In some implementations, a computer-implemented method includes analyzing first data from a first data source to determine a first schema of the first data source, and analyzing second data from a second data source to determine a second schema of the second data source. The method can further include generating a first two-dimensional aggregation of a first time data series having a time dimension and a dimension corresponding to aggregated values of a first metric, and generating a second two-dimensional aggregation of a second time data series having a time dimension and a dimension corresponding to aggregated values of a second metric. The method can also include computing a correlation value between the first two-dimensional aggregation and the second two-dimensional aggregation, and providing an indication of duplicated data between the first data source and the second data source if the correlation value meets a threshold.
    Type: Application
    Filed: November 6, 2017
    Publication date: May 9, 2019
    Applicant: Google LLC
    Inventors: Jacob Walker, Laura Eidem
  • Publication number: 20070058943
    Abstract: A method for recording audio and/or video of an event on a plurality of recordable media comprises the steps of capturing audio and/or video at the event from at least one pickup to a recording station, transferring the captured audio and/or video from the recording station to a file server for storage, copying the captured audio and/or video from the file server to at least one computer, and recording the audio and/or video from the at least one computer to the plurality of recordable media. The captured audio and/or video may be separated into content files representing songs or topics. The captured audio and/or video may be copied from one computer to another computer, which may also record to the media. A robotic duplication system may be attached to the computer. The file server is instructed to begin the copying process once all audio and/or video has been captured.
    Type: Application
    Filed: November 10, 2004
    Publication date: March 15, 2007
    Applicant: DiscLive, Inc.
    Inventors: David Blanchard, Rich Isaacson, Sami Valkonen, Jacob Walker