Patents by Inventor Phillip Popp
Phillip Popp 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: 20240134921Abstract: A user of a network-based system may correspond to a user profile that describes the user. The user profile may describe the user using one or more descriptors of items that correspond to the user (e.g., items owned by the user, items liked by the user, or items rated by the user). In some situations, such a user profile may be characterized as a “taste profile” that describes an array or distribution of one or more tastes, preferences, or habits of the user. Accordingly, the user profile machine within the network-based system may generate the user profile by accessing descriptors of items that correspond to the user, clustering one or more of the descriptors, and generating the user profile based on one or more clusters of the descriptors.Type: ApplicationFiled: December 14, 2023Publication date: April 25, 2024Inventors: Phillip Popp, Ching-Wei Chen, Peter C. DiMaria, Markus K. Cremer
-
Patent number: 11886521Abstract: An apparatus (a) groups descriptors into a cluster based on associating the descriptors with each of a first item and a second item, (b) accesses biometric data of a user, (c) determines a first activity of the user based on contextual data correlating the cluster with the biometric data, including determining whether the first activity represents an anomalous phase of the user based on a time period of the first activity being shorter than a threshold duration, and (d) generates a user profile based on the first activity of the user and the cluster, including (i) responsive to determining that the first activity represents the anomalous phase of the user, omitting a name of the cluster from the user profile, and (ii) responsive to a second activity of the user matching the first activity associated with the cluster, generating a recommendation including a third item based on the user profile.Type: GrantFiled: March 15, 2021Date of Patent: January 30, 2024Assignee: Gracenote, Inc.Inventors: Phillip Popp, Ching-Wei Chen, Peter C. DiMaria, Markus K. Cremer
-
Publication number: 20230350935Abstract: A clustering machine can cluster descriptive vectors in a balanced manner. The clustering machine calculates distances between pairs of descriptive vectors and generates clusters of vectors arranged in a hierarchy. The clustering machine determines centroid vectors of the clusters, such that each cluster is represented by its corresponding centroid vector. The clustering machine calculates a sum of inter-cluster vector distances between pairs of centroid vectors, as well as a sum of intra-cluster vector distances between pairs of vectors in the clusters. The clustering machine calculates multiple scores of the hierarchy by varying a scalar and calculating a separate score for each scalar. The calculation of each score is based on the two sums previously calculated for the hierarchy. The clustering machine may select or otherwise identify a balanced subset of the hierarchy by finding an extremum in the calculated scores.Type: ApplicationFiled: July 6, 2023Publication date: November 2, 2023Inventors: Aneesh Vartakavi, Peter C. DiMaria, Markus K. Cremer, Phillip Popp
-
Patent number: 11741147Abstract: A clustering machine can cluster descriptive vectors in a balanced manner. The clustering machine calculates distances between pairs of descriptive vectors and generates clusters of vectors arranged in a hierarchy. The clustering machine determines centroid vectors of the clusters, such that each cluster is represented by its corresponding centroid vector. The clustering machine calculates a sum of inter-cluster vector distances between pairs of centroid vectors, as well as a sum of intra-cluster vector distances between pairs of vectors in the clusters. The clustering machine calculates multiple scores of the hierarchy by varying a scalar and calculating a separate score for each scalar. The calculation of each score is based on the two sums previously calculated for the hierarchy. The clustering machine may select or otherwise identify a balanced subset of the hierarchy by finding an extremum in the calculated scores.Type: GrantFiled: March 2, 2021Date of Patent: August 29, 2023Assignee: Gracenote, Inc.Inventors: Aneesh Vartakavi, Peter C. DiMaria, Markus K. Cremer, Phillip Popp
-
Publication number: 20210200825Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that involve a user profile based on clustering tiered descriptors.Type: ApplicationFiled: March 15, 2021Publication date: July 1, 2021Inventors: Phillip Popp, Ching-Wei Chen, Peter C. DiMaria, Markus K. Cremer
-
Publication number: 20210182329Abstract: A clustering machine can cluster descriptive vectors in a balanced manner. The clustering machine calculates distances between pairs of descriptive vectors and generates clusters of vectors arranged in a hierarchy. The clustering machine determines centroid vectors of the clusters, such that each cluster is represented by its corresponding centroid vector. The clustering machine calculates a sum of inter-cluster vector distances between pairs of centroid vectors, as well as a sum of intra-cluster vector distances between pairs of vectors in the clusters. The clustering machine calculates multiple scores of the hierarchy by varying a scalar and calculating a separate score for each scalar. The calculation of each score is based on the two sums previously calculated for the hierarchy. The clustering machine may select or otherwise identify a balanced subset of the hierarchy by finding an extremum in the calculated scores.Type: ApplicationFiled: March 2, 2021Publication date: June 17, 2021Inventors: Aneesh Vartakavi, Peter C. DiMaria, Markus K. Cremer, Phillip Popp
-
Publication number: 20210149939Abstract: A neural network-based classifier system can receive a query including a media signal and, in response, provide an indication that a particular received query corresponds to a known media type or media class. The neural network-based classifier system can select and apply various models to facilitate media classification. In an example embodiment, classifying a media query includes accessing digital media data and a context parameter from a first device. A model for use with the network-based classifier system can be selected based on the context parameter. In an example embodiment, the network-based classifier system provides a media type probability index for the digital media data using the selected model and spectral features corresponding to the digital media data. In an example embodiment, the digital media data includes an audio or video signal sample.Type: ApplicationFiled: January 25, 2021Publication date: May 20, 2021Inventors: Markus K. Cremer, Jason Cramer, Phillip Popp, Cameron Aubrey Summers
-
Patent number: 10970327Abstract: A clustering machine can cluster descriptive vectors in a balanced manner. The clustering machine calculates distances between pairs of descriptive vectors and generates clusters of vectors arranged in a hierarchy. The clustering machine determines centroid vectors of the clusters, such that each cluster is represented by its corresponding centroid vector. The clustering machine calculates a sum of inter-cluster vector distances between pairs of centroid vectors, as well as a sum of intra-cluster vector distances between pairs of vectors in the clusters. The clustering machine calculates multiple scores of the hierarchy by varying a scalar and calculating a separate score for each scalar. The calculation of each score is based on the two sums previously calculated for the hierarchy. The clustering machine may select or otherwise identify a balanced subset of the hierarchy by finding an extremum in the calculated scores.Type: GrantFiled: January 15, 2019Date of Patent: April 6, 2021Assignee: GRACENOTE, INC.Inventors: Aneesh Vartakavi, Peter C. DiMaria, Markus K. Cremer, Phillip Popp
-
Patent number: 10949482Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that involve a user profile based on clustering tiered descriptors. An example method includes grouping descriptors into a cluster of descriptors based on an association between the descriptors and each of a first item and a second item, accessing, via a user device, biometric data of a user, determining a first activity in which the user is engaged based on contextual data that correlates the cluster of descriptors with the biometric data of the user received from the user device via the network, generating a user profile based on the first activity of the user and the cluster of descriptors, and generating, in response to a second activity of the user matching the first activity associated with the cluster of descriptors within the user profile, a recommendation including a third item based on the user profile.Type: GrantFiled: October 16, 2018Date of Patent: March 16, 2021Assignee: GRACENOTE, INC.Inventors: Phillip Popp, Ching-Wei Chen, Peter C. DiMaria, Markus K. Cremer
-
Patent number: 10902043Abstract: A neural network-based classifier system can receive a query including a media signal and, in response, provide an indication that a particular received query corresponds to a known media type or media class. The neural network-based classifier system can select and apply various models to facilitate media classification. In an example embodiment, classifying a media query includes accessing digital media data and a context parameter from a first device. A model for use with the network-based classifier system can be selected based on the context parameter. In an example embodiment, the network-based classifier system provides a media type probability index for the digital media data using the selected model and spectral features corresponding to the digital media data. In an example embodiment, the digital media data includes an audio or video signal sample.Type: GrantFiled: June 17, 2016Date of Patent: January 26, 2021Assignee: GRACENOTE, INC.Inventors: Markus K. Cremer, Jason Cramer, Phillip Popp, Cameron Aubrey Summers
-
Patent number: 10678828Abstract: A neural network-based classifier system can receive a query including a media signal and, in response, provide an indication that the query corresponds to a specified media type or media class. The neural network-based classifier system can select and apply various models to facilitate media classification. In an example embodiment, a query can be analyzed for various characteristics, such as a noise profile, before it is input to the network-based classifier. If the query has greater than a specified threshold noise characteristic, then a successful classification can be unlikely and a classification process based on the query can be terminated before computational resources are expended. Query signals that meet or exceed a threshold condition can be provided to the network-based classifier for media classification. In an example embodiment, a remote device or a central media classifier circuit can determine a noise profile for a query.Type: GrantFiled: June 17, 2016Date of Patent: June 9, 2020Assignee: GRACENOTE, INC.Inventors: Jason Cramer, Markus K. Cremer, Phillip Popp, Cameron Aubrey Summers
-
Patent number: 10635701Abstract: A neural network-based classifier system can receive a query including a media signal and, in response, provide an indication that the query corresponds to a specified media type or media class. The neural network-based classifier system can select and apply various models to facilitate media classification. In an example embodiment, a query can be analyzed for various characteristics, such as a noise profile, before it is input to the network-based classifier. If the query has greater than a specified threshold noise characteristic, then a successful classification can be unlikely and a classification process based on the query can be terminated before computational resources are expended. Query signals that meet or exceed a threshold condition can be provided to the network-based classifier for media classification. In an example embodiment, a remote device or a central media classifier circuit can determine a noise profile for a query.Type: GrantFiled: June 17, 2016Date of Patent: April 28, 2020Assignee: GRACENOTE, INC.Inventors: Jason Cramer, Markus K. Cremer, Phillip Popp, Cameron Aubrey Summers
-
Publication number: 20190146988Abstract: A clustering machine can cluster descriptive vectors in a balanced manner. The clustering machine calculates distances between pairs of descriptive vectors and generates clusters of vectors arranged in a hierarchy. The clustering machine determines centroid vectors of the clusters, such that each cluster is represented by its corresponding centroid vector. The clustering machine calculates a sum of inter-cluster vector distances between pairs of centroid vectors, as well as a sum of intra-cluster vector distances between pairs of vectors in the clusters. The clustering machine calculates multiple scores of the hierarchy by varying a scalar and calculating a separate score for each scalar. The calculation of each score is based on the two sums previously calculated for the hierarchy. The clustering machine may select or otherwise identify a balanced subset of the hierarchy by finding an extremum in the calculated scores.Type: ApplicationFiled: January 15, 2019Publication date: May 16, 2019Inventors: Aneesh Vartakavi, Peter C. DiMaria, Markus K. Cremer, Phillip Popp
-
Patent number: 10223358Abstract: A clustering machine can cluster descriptive vectors in a balanced manner. The clustering machine calculates distances between pairs of descriptive vectors and generates clusters of vectors arranged in a hierarchy. The clustering machine determines centroid vectors of the clusters, such that each cluster is represented by its corresponding centroid vector. The clustering machine calculates a sum of inter-cluster vector distances between pairs of centroid vectors, as well as a sum of intra-cluster vector distances between pairs of vectors in the clusters. The clustering machine calculates multiple scores of the hierarchy by varying a scalar and calculating a separate score for each scalar. The calculation of each score is based on the two sums previously calculated for the hierarchy. The clustering machine may select or otherwise identify a balanced subset of the hierarchy by finding an extremum in the calculated scores.Type: GrantFiled: March 7, 2016Date of Patent: March 5, 2019Assignee: Gracenote, Inc.Inventors: Aneesh Vartakavi, Peter C. DiMaria, Markus K. Cremer, Phillip Popp
-
Publication number: 20190050488Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that involve a user profile based on clustering tiered descriptors. An example method includes grouping descriptors into a cluster of descriptors based on an association between the descriptors and each of a first item and a second item, accessing, via a user device, biometric data of a user, determining a first activity in which the user is engaged based on contextual data that correlates the cluster of descriptors with the biometric data of the user received from the user device via the network, generating a user profile based on the first activity of the user and the cluster of descriptors, and generating, in response to a second activity of the user matching the first activity associated with the cluster of descriptors within the user profile, a recommendation including a third item based on the user profile.Type: ApplicationFiled: October 16, 2018Publication date: February 14, 2019Inventors: Phillip Popp, Ching-Wei Chen, Peter C. DiMaria, Markus K. Cremer
-
Patent number: 10140372Abstract: A user of a network-based system may correspond to a user profile that describes the user. The user profile may describe the user using one or more descriptors of items that correspond to the user (e.g., items owned by the user, items liked by the user, or items rated by the user). In some situations, such a user profile may be characterized as a “taste profile” that describes an array or distribution of one or more tastes, preferences, or habits of the user. Accordingly, the user profile machine within the network-based system may generate the user profile by accessing descriptors of items that correspond to the user, clustering one or more of the descriptors, and generating the user profile based on one or more clusters of the descriptors.Type: GrantFiled: September 12, 2012Date of Patent: November 27, 2018Assignee: Gracenote, Inc.Inventors: Phillip Popp, Ching-Wei Chen, Peter C. DiMaria, Markus K. Cremer
-
Publication number: 20170255617Abstract: A clustering machine can cluster descriptive vectors in a balanced manner. The clustering machine calculates distances between pairs of descriptive vectors and generates clusters of vectors arranged in a hierarchy. The clustering machine determines centroid vectors of the clusters, such that each cluster is represented by its corresponding centroid vector. The clustering machine calculates a sum of inter-cluster vector distances between pairs of centroid vectors, as well as a sum of intra-cluster vector distances between pairs of vectors in the clusters. The clustering machine calculates multiple scores of the hierarchy by varying a scalar and calculating a separate score for each scalar. The calculation of each score is based on the two sums previously calculated for the hierarchy. The clustering machine may select or otherwise identify a balanced subset of the hierarchy by finding an extremum in the calculated scores.Type: ApplicationFiled: March 7, 2016Publication date: September 7, 2017Inventors: Aneesh Vartakavi, Peter C. DiMaria, Markus K. Cremer, Phillip Popp
-
Publication number: 20170193097Abstract: A neural network-based classifier system can receive a query including a media signal and, in response, provide an indication that the query corresponds to a specified media type or media class. The neural network-based classifier system can select and apply various models to facilitate media classification. In an example embodiment, a query can be analyzed for various characteristics, such as a noise profile, before it is input to the network-based classifier. If the query has greater than a specified threshold noise characteristic, then a successful classification can be unlikely and a classification process based on the query can be terminated before computational resources are expended. Query signals that meet or exceed a threshold condition can be provided to the network-based classifier for media classification. In an example embodiment, a remote device or a central media classifier circuit can determine a noise profile for a query.Type: ApplicationFiled: June 17, 2016Publication date: July 6, 2017Inventors: Jason Cramer, Markus K. Cremer, Phillip Popp, Cameron Aubrey Summers
-
Publication number: 20170193362Abstract: A neural network-based classifier system can receive a query including a media signal and, in response, provide an indication that a particular received query corresponds to a known media type or media class. The neural network-based classifier system can select and apply various models to facilitate media classification. In an example embodiment, classifying a media query includes accessing digital media data and a context parameter from a first device. A model for use with the network-based classifier system can be selected based on the context parameter. In an example embodiment, the network-based classifier system provides a media type probability index for the digital media data using the selected model and spectral features corresponding to the digital media data. In an example embodiment, the digital media data includes an audio or video signal sample.Type: ApplicationFiled: June 17, 2016Publication date: July 6, 2017Inventors: Markus K. Cremer, Jason Cramer, Phillip Popp, Cameron Aubrey Summers
-
Publication number: 20140074839Abstract: A user of a network-based system may correspond to a user profile that describes the user. The user profile may describe the user using one or more descriptors of items that correspond to the user (e.g., items owned by the user, items liked by the user, or items rated by the user). In some situations, such a user profile may be characterized as a “taste profile” that describes an array or distribution of one or more tastes, preferences, or habits of the user. Accordingly, the user profile machine within the network-based system may generate the user profile by accessing descriptors of items that correspond to the user, clustering one or more of the descriptors, and generating the user profile based on one or more clusters of the descriptors.Type: ApplicationFiled: September 12, 2012Publication date: March 13, 2014Applicant: GRACENOTE, INC.Inventors: Phillip Popp, Ching-Wei Chen, Peter C. DiMaria, Markus K. Cremer