Abstract: A computer-implemented user-friendly system and method of designing and managing smart contracts on a distributed ledger (blockchain). The system creates a number of computer programs that correspond to a business user's model of the contract terms. In this manner, the business user can generate the smart contract without needing to understand programming or involve third parties like developers.

Abstract: Generally, the present disclosure is directed to user interface understanding. More particularly, the present disclosure relates to training and utilization of machine-learned models for user interface prediction and/or generation. A machine-learned interface prediction model can be pre-trained using a variety of pre-training tasks for eventual downstream task training and utilization (e.g., interface prediction, interface generation, etc.).

Abstract: The system can include a set of joints, a controller, and a model engine; and can optionally include a support structure and an end effector. Joints can include: a motor, a transmission mechanism, an input sensor, and an output sensor. The system can enable articulation of the plurality of joints.

Abstract: The present disclosure relates to a method of producing metallurgical coke from a combination of non-coking and non-metallic carbon-based microwave susceptor. The method is energy efficient, economical, and environmentally friendly. The present disclosure also relates to metallurgical coke having improved coke quality, such as improved coke strength after reaction.

Abstract: Disclosed herein are system, method, and computer program product embodiments for machine-assisted process modeling and validation. An embodiment operates by receiving, by at least one processor, a process document describing a process in a user locale. The embodiment then generates the model notation in accordance with a model notation format by processing the process document with a deep learning technique based on a prompt for modeling the process document. The embodiment then outputs the model notation.

Abstract: Generally, the present disclosure is directed to user interface understanding. More particularly, the present disclosure relates to training and utilization of machine-learned models for user interface prediction and/or generation. A machine-learned interface prediction model can be pre-trained using a variety of pre-training tasks for eventual downstream task training and utilization (e.g., interface prediction, interface generation, etc.).

Abstract: A data processing and analysis system that optimizes the resources to be used for data storage and refresh events. A partitioner module for a data analysis system can receive a first client criteria and a first client dataset that includes tabular data and calculate scores that are used to generate partitioning strategies. The selected partitioning strategy can be implemented to produce aggregated data that can be stored in an intelligent data mart. The partitions can then be accessed by a data visualization platform for intelligent, dynamic responses to user requests for data analyses and generation of visualizations. By providing synchronous partitioning of data (especially big data) and intelligent refresh, the data can move from the back-end to the front-end with minimal user clicks and minimal latency in performance.

Abstract: The present disclosure relates to synthetic biology and, in particular, the bioproduction of bakuchiol, and engineered enzymes for producing the same.

Abstract: A vehicle includes a primary axle powered by an actuator and a secondary axle powered by a motor and including a wheel and a clutch selectively coupling the wheel to the motor via mating components. A controller is electrically connected to the clutch and the motor. The controller is programmed to, in response to an engagement of the clutch being unsuccessful within a first duration of time, command a series of speeds to the motor based on wheel speed and an alternating offset that changes between positive and negative signs at predefined periods so that relative speeds between the mating components oscillate due to the alternating offset to jiggle the clutch into engagement.

Abstract: A data processing and analysis system that optimizes the resources to be used for data storage and refresh events. A partitioner module for a data analysis system can receive a first client criteria and a first client dataset that includes tabular data and calculate scores that are used to generate partitioning strategies. The selected partitioning strategy can be implemented to produce aggregated data that can be stored in an intelligent data mart. The partitions can then be accessed by a data visualization platform for intelligent, dynamic responses to user requests for data analyses and generation of visualizations. By providing synchronous partitioning of data (especially big data) and intelligent refresh, the data can move from the back-end to the front-end with minimal user clicks and minimal latency in performance.

Abstract: The present disclosure relates to systems and methods for enhancing computer services with parallel models. A training dataset can be generated. Computer models can be trained using the training dataset. Second data can be partitioned into a set of data subsets. Each data subset can be allocated to a different computer model. Projections of data points can be generated by executing each computer model using a corresponding data subset. Relative differences between the projections can be determined. An output of the computer models can be provided by aggregating the projections of data points.

Abstract: The invention relates to methods of diagnosing, prognosing, or monitoring or staging the progression of non-alcoholic fatty liver disease (NAFLD) using biomarkers. The invention also relates to a method of scoring to determine the severity of NAFLD, and a method of treating NAFLD.

Abstract: The disclosure relates to a method and data storage device for managing host requests in the data storage device. The method includes receiving, from a host device, a read request for reading data from the data storage device, identifying a type of the read request, and based on the type of the read request being a random read request, performing one or more first operations related to processing of the read request in parallel with one or more second operations including: fetching a logical block address of the data from the read request; and obtaining a logical-to-physical (L2P) mapping table from a first memory associated with the data storage device, based on the logical block address, the L2P mapping table used for reading the data from the data storage device.

Abstract: A system for low-count quantitative single-photon emission computed tomography (LC-QSPECT) is provided. The system is programmed to a) store a computer tomography (CT) scan of a subject being examining including a plurality of defined volumes of interest (VOIs) of the subject being examined; b) model a system matrix based on the stored CT, wherein the model describes the probability that photons emitted from each of the defined VOIs are detected in different projection bins, wherein a plurality of projection bins are defined around the subject and the defined VOIs; c) adjust the model with analysis of stray-radiation noise around the subject; d) detect, by the one or more sensors, one or more photons being emitted by an alpha-particle-emitting isotope; and e) execute the adjusted model with the one or more detected photons as inputs to determine a source VOI of the detected photons.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for dialogue systems. A transcription of a user utterance is obtained. The transcription of the utterance is tokenized to identify multiple tokens for the utterance. Token-level utterance encodings corresponding to different tokens of the transcription are generated. A system action encoding from data indicating system actions previously performed by the dialogue system are generated. A dialogue context vector based on the utterance encoding and the system action encoding are generated. The token-level utterance encodings, the system action encoding, and the dialogue context vector are processed using a slot tagger to produce token-level output vectors. A limited set of candidate token classifications for the tokens of the user utterance are determined based on the token-level utterance encodings. A response for output is provided in response to the user utterance.

Abstract: A computer that includes a processor and a memory, the memory including instructions executable by the processor to generate radar data by projecting radar returns of objects within a scene onto an image plane of camera data of the scene based on extrinsic and intrinsic parameters of a camera and extrinsic parameters of a radar sensor to generate the radar data. The image data can be received at an image channel of an image/radar convolutional neural network (CNN) and receive the radar data at a radar channel of the image/radar CNN, wherein features are transferred from the image channel to the radar channel at multiple stages Image object features and image confidence scores can be determined by the image channel, and radar object features and radar confidences by the radar channel. The image object features can be combined with the radar object features using a weighted sum.

Abstract: A system for single-photon emission computed tomography (SPECT) is provided. The system includes a computer device comprises at least one processor in communication with at least one memory device. The at least one processor is programmed to: a) store a model trained to denoise computer tomography (CT) scans of a subject being examined; b) receive a CT scan of a first subject being examined; c) execute the model with the CT scan of the first subject as an input, wherein the model performs denoising on the CT scan while accounting for an observer loss function; and d) output a denoised-CT scan of the first subject.

Abstract: A system for single-photon emission computed tomography (SPECT) is provided. The system includes a computer device comprises at least one processor in communication with at least one memory device. The at least one processor is programmed to: a) store a model trained to generate an attenuation map of a subject being examined; b) receive a scatter-energy window projection of a first subject to be examined; c) execute the model with the scatter-energy window projection of the first subject as an input, wherein the model generates an attenuation map; d) receive a photopeak-energy window projection of the first subject to be examined; and e) perform attenuation compensation on the photopeak-energy window projection using the generated attenuation map.

Abstract: Example methods include determining an input prompt comprising an utterance labeled with a sequence of slot-value pairs, wherein the sequence of slot-value pairs indicates possible slots and values in the utterance, and wherein the utterance relates to a task. The methods include determining a contextual representation comprising a concatenation of a history of utterances exchanged between a user and a service agent. The utterances describe a context for the task. The methods include training, based on a concatenation of the input prompt and the contextual representation, a sequence-to-sequence language model to predict a sequence of dialog states for an input task. The sequence of dialog states comprise an assignment of values to slots for which the user has indicated a preference in dialog sequences. The methods include providing the trained sequence-to-sequence language model.

Abstract: Example methods include determining an input schema representation for a task. The schema representation comprises natural language descriptions of slot and intent descriptions, wherein respective indices are associated with each of the slot descriptions and each of the intent descriptions. The methods include determining a contextual representation comprising a concatenation of a history of dialog sequences exchanged between a user and a service agent, wherein the dialog sequences describe a context for the task. The methods include training, a sequence-to-sequence language model and based on a concatenation of the input schema representation and the contextual representation, to predict a sequence of dialog states for an input task, wherein the sequence of dialog states comprises an assignment of values to slots for which the user has indicated a preference in dialog sequences corresponding to the input task. The methods include providing the trained sequence-to-sequence language model.