Abstract: A system and method for predicting oil production is disclosed herein. A computing system receives production data for a plurality of wells in a plurality of geographic regions. The computing system identifies a subset of wells from the plurality of wells. The subset of wells includes wells that have a threshold amount of production data. The computing system trains a machine learning model using the subset of wells. The computing system applies the trained learning model to a target well to predict oil production from the target well.

Abstract: Disclosed are various embodiments an auger of an immersion treatment system. The auger can include auger panels that move a product and a treatment liquid in a treatment tank. A first auger panel can include at least: a leading edge and a trailing edge. The at least one of the leading edge and the trailing edge can include one or more gaps that form corresponding grille passages where the at least one of the leading edge and the trailing edge are connected to another auger panel at a weld joint.

Abstract: Systems and methods of software enhancement and management can comprise inputting one or more data transformation algorithms representing asset data, decomposing the one or more data transformation algorithms into a plurality of TALPs, executing the plurality of TALPs to generate at least one or more value complexity prediction polynomials, simulating one or more investment data units and external stored data to generate a simulated data output based at least on the one or more value complexity prediction polynomials, executing a TALP control engine using predictive analytics and at least the simulated data output to create temporally sequenced TALP output data, pooling the temporally sequenced TALP output data, modeling predictive outcomes based at least on the pooled temporally sequenced TALP output data merged with external unoptimized context data via a feedback loop over time, and outputting optimized and discretized data based on the modeled predictive outcomes.

Abstract: An inorganic substrate with an improved via shape and methods for facilitating formation of such improved via shape are disclosed. A double-sided opening process may be applied to an inorganic substrate to form openings at the ends of a damage track previously formed in the inorganic substrate. One side of the inorganic substrate may then be sealed, such as by being temporarily bonded to a carrier or blocking substrate, so that a single-sided opening process may be applied to the other unsealed or unblocked surface of the inorganic substrate. The single-sided opening process may enlarge at least one of the openings formed by the double-sided opening process and may enlarge a channel between the openings to form a via having an advantageous shape.

Abstract: Software systems and methods convert algorithms and software codes into time affecting linear pathways (TALPs) via decomposition and convert paired Input/Output (I/O) datasets into TALPs via Value Complexity polynomials. Generated TALPs can be enhanced through merging with other TALPs. TALPs can be grouped by matching the outputs of the TALP-associated prediction polynomials with some set of given criteria into families and cross-families that are useful in a new type of software optimization that allows for output values of grouped TALPs to be modeled, pooled, discretized and optimized to enhance goals or meet user goals.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting a continued conversation are disclosed. In one aspect, a method includes the actions of receiving first audio data of a first utterance. The actions further include obtaining a first transcription of the first utterance. The actions further include receiving second audio data of a second utterance. The actions further include obtaining a second transcription of the second utterance. The actions further include determining whether the second utterance includes a query directed to a query processing system based on analysis of the second transcription and the first transcription or a response to the first query. The actions further include configuring the data routing component to provide the second transcription of the second utterance to the query processing system as a second query or bypass routing the second transcription.

Abstract: An apparatus for performing nucleic acid amplification reactions includes a thermally-conductive receptacle holder that includes multiple receptacle wells. Each well can receive a receptacle and has a through-hole extending from an inner surface of the well to an outer surface of the holder. The apparatus includes multiple optical fibers, and each optical fiber has a first end in optical communication with an associated well and a second end in optical communication with an excitation signal source and/or an emission signal detector. The first end of each optical fiber is moveable with respect to the through-hole. A cover is movable between an open position and a closed position relative to the receptacle holder, and the first end of each optical fiber moves with respect to the through-hole of the associated well as the cover moves to the open or closed position or when the cover moves into or out of contact with any receptacles within the wells.

Abstract: A method of manufacturing a robotic manipulator including determining desired manipulator properties including a manipulator shape and manipulator jamming properties; using the manipulator jamming properties and a packing computational model to determine a packing element configuration, the packing computational model defining relationships between manipulator jamming properties and different packing element configurations; controlling an additive printing machine based on the packing element configuration and manipulator shape to manufacture the robot manipulator. The robot manipulator includes a flexible outer skin defining a chamber; a connector attached to the outer skin and connected to a fluid pump to allow fluid to be added to or removed from the chamber; filling elements disposed in the chamber according to the packing element configuration.

Abstract: Methods and systems for existing software applications to automatically take advantage of multicore computer systems outside of the conventional simultaneous processing of multiple applications and without performance problems from cache misses and mismatched task processing times are presented. Unlike other multicore optimization techniques, the present invention uses techniques that are applied to design graphs and work for scaled and standard speedup-based parallel processing. The methods and systems optimize software designs that are attached to code for maximum performance on multicore computer hardware by analyzing and modifying loop structures to produce a general parallel solution, not just simple loop unrolling.

Abstract: The present invention relates generally to generating and processing spatiotemporal data transformation objects of an algorithm, and a Time-Affecting Linear Pathway (TALP)-based enhancement and management system that can use blockchain networks to generate and pool TALP predictive analytics.

Abstract: Systems and methods of software enhancement and management can comprise inputting one or more data transformation algorithms representing asset data; decomposing the one or more data transformation algorithms into a plurality of Time-Affecting Linear Pathways (TALPs), executing the plurality of TALPs to generate at least one or more value complexity prediction polynomials, executing a TALP execution engine using predictive analytics and external unoptimized context data to create temporally sequenced TALP output data from the plurality of TALPs, modeling predictive outcomes using at least TALP optimization criteria data and the temporally sequenced TALP output data and merging additional external unoptimized context data via a feedback loop over time, and outputting optimized and discretized temporally sequenced output data based on the modeled predictive outcomes.

Abstract: Embodiments disclosed herein generally relate to a method and a system to generate well trajectories. A computing device receives one or more parameters associated with a target well in a target location. The computing device receives two or more data points for the target well in the target location. The computing device generates a modified wellbore path based on the one or more parameters associated with a target well and the two or more data points via a trained wellbore prediction model. The computing device compares the modified wellbore path for the target well to one or more wellbore paths of one or more wells co-located with the target well in the target location. The computing device updates the modified wellbore path for the target well by adjusting one or more coordinates of the modified wellbore path based on the comparison. The computing device generates a three-dimensional model of the target location.

Abstract: A method includes receiving a spoken utterance that includes a plurality of words, and generating, using a neural network-based utterance classifier comprising a stack of multiple Long-Short Term Memory (LSTM) layers, a respective textual representation for each word of the of the plurality of words of the spoken utterance. The neural network-based utterance classifier trained on negative training examples of spoken utterances not directed toward an automated assistant server. The method further including determining, using the respective textual representation generated for each word of the plurality of words of the spoken utterance, that the spoken utterance is one of directed toward the automated assistant server or not directed toward the automated assistant server, and when the spoken utterance is directed toward the automated assistant server, generating instructions that cause the automated assistant server to generate a response to the spoken utterance.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting a continued conversation are disclosed. In one aspect, a method includes the actions of receiving first audio data of a first utterance. The actions further include obtaining a first transcription of the first utterance. The actions further include receiving second audio data of a second utterance. The actions further include obtaining a second transcription of the second utterance. The actions further include determining whether the second utterance includes a query directed to a query processing system based on analysis of the second transcription and the first transcription or a response to the first query. The actions further include configuring the data routing component to provide the second transcription of the second utterance to the query processing system as a second query or bypass routing the second transcription.

Abstract: Software systems and methods convert algorithms and software codes into time affecting linear pathways (TALPs) via decomposition and convert paired Input/Output (I/O) datasets into TALPs via Value Complexity polynomials. Generated TALPs can be enhanced through merging with other TALPs. TALPs can be grouped by matching the outputs of the TALP-associated prediction polynomials with some set of given criteria into families and cross-families that are useful in a new type of software optimization that allows for output values of grouped TALPs to be modeled, pooled, discretized and optimized to enhance goals or meet user goals.

Abstract: A method for automatic speech recognition using joint acoustic echo cancellation, speech enhancement, and voice separation includes receiving, at a contextual frontend processing model, input speech features corresponding to a target utterance. The method also includes receiving, at the contextual frontend processing model, at least one of a reference audio signal, a contextual noise signal including noise prior to the target utterance, or a speaker embedding including voice characteristics of a target speaker that spoke the target utterance. The method further includes processing, using the contextual frontend processing model, the input speech features and the at least one of the reference audio signal, the contextual noise signal, or the speaker embedding vector to generate enhanced speech features.

Abstract: Methods and systems for existing software applications to automatically take advantage of multicore computer systems outside of the conventional simultaneous processing of multiple applications and without performance problems from cache misses and mismatched task processing times are presented. Unlike other multicore optimization techniques, the present invention uses techniques that are applied to design graphs and work for scaled and standard speedup-based parallel processing. The methods and systems optimize software designs that are attached to code for maximum performance on multicore computer hardware by analyzing and modifying loop structures to produce a general parallel solution, not just simple loop unrolling.