Amazon Technologies, Inc. patent applications on January 16th, 2025
Patent Applications by Amazon Technologies, Inc. on January 16th, 2025
Amazon Technologies, Inc.: 4 patent applications
Amazon Technologies, Inc. has applied for patents in the areas of C12Q1/6886 (1), C12Q1/6881 (1), G06F16/84 (1), G06F18/214 (1), G06F40/154 (1) C12Q1/6886 (1), G06F16/86 (1), G06N20/00 (1), H04W76/10 (1)
With keywords such as: job, network, wireless, cell, such, rna, mesh, perform, attribute, and wap in patent application abstracts.
Patent Applications by Amazon Technologies, Inc.
Inventor(s): Samuel Anthony DANZIGER of Seattle WA (US) for amazon technologies, inc., Haibao TANG of Cupertino CA (US) for amazon technologies, inc., David HECKERMAN of Bellevue WA (US) for amazon technologies, inc., Frank Wilhelm SCHMITZ of Seattle WA (US) for amazon technologies, inc., Alena HARLEY of Los Gatos CA (US) for amazon technologies, inc.
IPC Code(s): C12Q1/6886, C12Q1/6881
CPC Code(s): C12Q1/6886
Abstract: disclosed herein are methods for classifying a cell present in a sample. such as a tumor, of a subject. comprising: sequencing bulk dna from first and second (e.g., tumor and healthy) a subject's tissue samples; classifying somatic variants as first or second sample alleles; sequencing rna from the cell; aligning each rna sequence with the bulk dna; classifying each rna sequence as a first, a second, or an unknown allele sequence, depending on whether it substantially aligns with the first, the second sample allele, or cannot be determined; and identifying the cell as a first, a second, or an unknown cell, based on the classifying of each of the plurality of rna sequences. methods can comprise validating identification by allelic frequency of germ-line variants in the rna sequences. the methods provide improved characterization of heterogenous cell populations, such as cell populations contaminated with cells from different sources, or tumor populations.
Inventor(s): Shrikant G Nayak of Karnataka (IN) for amazon technologies, inc., Sathya Prakash Podila Venkata Subramanya of Karnataka (IN) for amazon technologies, inc., Divya Nalam of Karnataka (IN) for amazon technologies, inc., Vijay Daniel Manason of Karnataka (IN) for amazon technologies, inc., Valluri Subbanna Chowdary of Karnataka (IN) for amazon technologies, inc.
IPC Code(s): G06F16/84, G06F18/214, G06F40/154, G06F40/16, G06N5/02, G06N20/20
CPC Code(s): G06F16/86
Abstract: results of applying a set of voting rules to a target corpus of documents are used to obtain a set of derived probabilistic labels indicating the probabilities of the presence of a particular attribute within the documents' constituent objects. a machine learning model is trained to identify a candidate portion of a document from which a value of the attribute is to be extracted. the training data for the model includes learned representations obtained from paths of constituent objects, and the corresponding derived labels. a proposed value for the attribute, obtained based on an assigned attribute value presence probability score for an individual constituent object from a selected candidate portion of a document, is provided.
20250021884. MACHINE LEARNING SERVICE_simplified_abstract_(amazon technologies, inc.)
Inventor(s): Leo Parker Dirac of Seattle WA (US) for amazon technologies, inc., Nicolle M. Correa of Seattle WA (US) for amazon technologies, inc., Aleksandr Mikhaylovich Ingerman of Seattle WA (US) for amazon technologies, inc., Sriram Krishnan of Sammamish WA (US) for amazon technologies, inc., Jin Li of Bellevue WA (US) for amazon technologies, inc., Sudhakar Rao Puvvadi of Bellevue WA (US) for amazon technologies, inc., Saman Zarandioon of Seattle WA (US) for amazon technologies, inc.
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: a machine learning service implements programmatic interfaces for a variety of operations on several entity types, such as data sources, statistics, feature processing recipes, models, and aliases. a first request to perform an operation on an instance of a particular entity type is received, and a first job corresponding to the requested operation is inserted in a job queue. prior to the completion of the first job, a second request to perform another operation is received, where the second operation depends on a result of the operation represented by the first job. a second job, indicating a dependency on the first job, is stored in the job queue. the second job is initiated when the first job completes.
Inventor(s): Denny Drivas Delp of Austin TX (US) for amazon technologies, inc., Casey Eric Edwards of Austin TX (US) for amazon technologies, inc., Hsuan-Man Hung of Miaoli (TW) for amazon technologies, inc., Wei-Chun Wang of New Taipei City (TW) for amazon technologies, inc., Matthew James Richards of San Francisco CA (US) for amazon technologies, inc., Benjamin Jeffrey Lowe of San Jose CA (US) for amazon technologies, inc.
IPC Code(s): H04W76/10, H04W48/16
CPC Code(s): H04W76/10
Abstract: the disclosure describes techniques for configuring wireless routers of a wireless mesh network with one or more secondary wireless access points (waps) such that client devices connected to the mesh network may remain online in the event that a primary wap goes offline or otherwise becomes unavailable. for instance, a user of the wireless mesh network may specify a device, such as a mobile electronic device connected to a cellular network, to operate as a secondary wap in the event that a primary wap becomes unavailable. thereafter, upon a wireless router of the mesh network detecting that the primary wap is unavailable, the wireless router may perform a network scan to identify ssid(s) that are available within the environment. the wireless router may also instruct the other routers of the mesh network to perform a network scan.
Amazon Technologies, Inc. patent applications on January 16th, 2025