Abstract: This application describes, among other things, systems and methods for deploying a task-specific machine-learning model. An example method includes receiving a prompt associated with one or more commands and a plurality of tokens. A first task-specific machine-learning model is identified based on a first command of the one or more commands. Some or all of the tokens of the plurality of tokens are applied to a node associated with the first task-specific machine-learning model, and a plurality of restricted data is received. Based on evaluating the plurality of restricted data, a correlation between the first node and a second node is determined. If the correlation satisfies a threshold condition, a plurality of text data different than the prompt is generated, otherwise the some or all of the tokens are again provided to the first node. Some or all of the tokens are then traversed and applied to the second node.

Abstract: This application describes, among other things, methods of selecting a task-specific machine-learning model for addressing a clinical task. An example method includes receiving a prompt from a user. Based on determining that the prompt requests assistance with a clinical task, a machine-learning model trained to select from among a plurality of task-specific machine-learning models each trained to assist with one of a plurality of clinical tasks selects a respective task-specific machine-learning model from among the plurality of task-specific machine-learning models based on the prompt. The prompt is provided to the selected task-specific machine-learning model. And a response received from the selected task-specific machine-learning model is provided to the user.

Abstract: This application describes, among other things, systems and methods for interacting with a task-specific orchestration. An example method includes obtaining medical data from one or more data collections. A set of user interface elements is presented at a user interface, where each respective user interface element of the set of user interface elements represents a respective task-specific orchestration that includes one or more respective machine-learning models fine-tuned for a specific task or domain based on the medical data. When a user interface element representing a respective task-specific orchestration is selected, at least some of the medical data is provided to the respective task-specific orchestration, and a different user interface is presented for communicating with the respective task-specific orchestration. Based on receiving a prompt at the different user interface, a response object is generated by the task-specific orchestration based on the prompt and at least some of the medical data.

Abstract: This application describes, amongst other things, methods and systems for building and deploying agents. An example method includes obtaining orchestration data about a set of task-specific components selected to provide a response to the prompt, where each respective task-specific components in the set of task-specific components is configured to assist with a respective clinical task of the one or more clinical tasks. The method further includes, determining an order in which each respective task-specific components of the set of task-specific components should be utilized to prepare a complete response to the prompt that address the one or more clinical tasks based on the obtained orchestration data about the set of task-specific components. The method also includes, in accordance with the determined order, providing first data related to the prompt to a first task-specific component and receiving a first response from the first task-specific component.

Abstract: This application describes, among other things, methods of enabling data transforms across multiple task-specific orchestrations. An example method includes, based on determining that a prompt requests assistance with a clinical task, selecting, by a machine-learning model trained to select from among a plurality of task-specific components, a set of task-specific components based on the prompt. The method includes obtaining orchestration data about the set of task-specific components, where each task-specific component is configured to assist with a respective clinical task. The method includes determining, from the orchestration data, a data-compatibility criterion for clinical task data relating to the one or more clinical tasks. The method includes receiving the clinical task data.

Abstract: This application describes, among other things, systems and methods for configuring a task-specific machine-learning model. An example method includes, based on a request to modify a machine-learning model for performing a clinical task, retrieving a corresponding node architecture defining conditional logic for performing the clinical task. The conditional logic is executed based on a first order, including an input node, an output node, and an intermediate node, of a first set of interconnected nodes including a data source node, a machine-learning model node, and a conditional logic node. A representation is generated including a first feature for configuring conditional logic of the node architecture and a second feature for configuring a parameter of a node in the first set of interconnected nodes. A selection of the first or second feature defines a second order of a second set of interconnected nodes, causing the node architecture's conditional logic to be updated.

Abstract: This application describes, among other things, methods of providing third-party interactions to a set of task-specific components. An example method includes receiving, at a user interface of a computing device, a user identifier and a prompt related to an identified clinical task. The method includes determining a set of task-specific components and a set of databases to which the user identifier has access. The method includes selecting, by a machine-learning model trained to select from among the set of task-specific components, a task-specific component from among the set of task-specific components. The method includes communicatively coupling the task-specific component to a database from the set of databases based on the prompt. The method includes providing the prompt to the task-specific component. The method includes receiving a response to the prompt generated by the task-specific component using information from the database and providing the response to a user.

Abstract: This application describes, among other things, machine-learning models for performing specific clinical tasks. An example method includes receiving a prompt at a first computing system in communication with a machine-learning model trained to assist in performing a clinic task that includes generating a report of a patient's medical records, guiding a patient through a care plan, creating patient care guidelines based on a patient's health profile, identifying patients requiring follow-up at a hospital, identifying changes in a standard of care for a disease setting, or evaluating unstructured data associated with a patient to identify a cohort of similar patients. Based on the prompt, a natural language response is generated that is responsive to the prompt and is based on an analysis by the machine-learning model of a repository of data that is determined to be relevant to the prompt. And the natural language response is provided to second computing system.

Abstract: Systems and methods facilitate sensing and tallying defecation events of subjects, such as participants in clinical trials for treatments for treating digestive diseases, such as irritable bowel syndrome (IBS), inflammatory bowel disease (IBD), and chronic constipation. Systems and methods may also be used by individual patients for sensing and tallying defecation events, and resulting data may be reviewed by a healthcare provider when evaluating patient gastrointestinal health and/or treatments.

Abstract: A method for reducing the turbidity of as-mined sand comprising adding water to the as-mined sand to increase its moisture content to between about 5% and about 40% by weight, mixing the sand and water, piling the wet sand on the ground, allowing the sand to rest for a predetermined period of between about 12 hours and about 3 days, then harvesting less than all of the sand from the pile as reduced turbidity sand.

Abstract: A method and system comprising storing a set of user application programs each requiring an application specific subset of data to perform application processes and generate a respective genomic variant characterization for each of a plurality of patients with cancerous cells and receiving cancer treatment. The method including, obtaining clinical records data including cancer related information, generating genomic sequencing data for the patient's cancerous cells and normal cells, shaping at least a subset of the genomic sequencing data to generate system structured data. Storing the system structured data in a first database, selecting the application specific data from the first database, storing the application specific data in a second database for application program interfacing, receiving the respective genomic variant characterization from the user application program, and storing the genomic variant characterization from the user application program in a third database.

Abstract: A method for identifying actionable care events includes receiving data sources relating to a subject; storing data from them in a first database; generating a database comprising structured data fields and metadata fields from the sources; generating output data related to fields within the data or metadata fields; populating the database with the output data; generating criteria sets corresponding to respective actionable care events; evaluating the generated database using the criteria sets; identifying whether any of the criteria sets are not sufficiently satisfied by the database, wherein an underlying error or an indication of missing or incomplete information within the database with respect to a criteria set indicates a corresponding actionable care event; determining that other data sources within the collection do not sufficiently satisfy any of the identified criteria sets; and generating, based on the identifying and determining, a notification that at least one actionable care event applies.

Abstract: A centralized document system receives a request to merge a first document package associated with a first party and a second document package associated with a second party. The first document package includes a first set of documents and the second document package includes a second set of documents. In response to the request, the centralized document system identifies a first subset of documents included in both the first and second sets of documents and identifies a second subset of documents with conflicts between the first and second sets of documents. The centralized document system rectifies the second subset of documents to cure the conflicts between the first and second sets of documents. The centralized document system generates a merged document package including the first subset of documents and the rectified second subset of documents for execution by the first and second parties.

Abstract: A 100% solids composition and method for priming or sealing a concrete surface wherein the 100% solids composition is formed of a tree rosin ester resin and a vegetable oil or vegetable oil-derived plasticizer, which are renewable or largely renewable, and wherein the 100% solids composition provides strong adhesion, can be applied by brushing or spraying at a temperature of less than 400° F. without adding a solvent or water thereto, produces substantially no VOCs, requires no time for curing or evaporation, and is ready for traffic or other normal use after cooling.

Abstract: The invention comprises a system for wet screening of oilwell proppant at the wellsite to provide a controlled and controllable amount of properly sized and screened proppant and fluid to a frac fluid blending system.

Abstract: The invention comprises a system for wet screening of oil well proppant at the wellsite to provide a controlled and controllable amount of properly sized and screened proppant and fluid to a frac fluid blending system.

Abstract: A universal secure mobile device entry upgrade for electronic locks adds a wireless unlocking functionality to an existing host lock assembly. An electronics unit having a processing unit, a wireless communication device, a lock input, and a lock output is installed between a host motor output and host motor of a host lock. The original unlocking functionality of the host lock is maintained by either repeating an unlock signal from the host motor output to the host motor using the processing unit, or through a two-position switch that passes a host unlock signal to the host motor by default, but switches to a second position that allows an unlock signal to be sent to the host motor when a wireless unlocking is signaled from a mobile unlocking device such as a smartphone or the like. An integrated security chip and real-time clock may be included to increase security.

Abstract: A method, structure, and composition for repairing wide and/or deep cracks, joints, and other gaps in pavement surfaces using one or a series of layers of a compressible aggregate of uniform size, with each layer of the compressible aggregate having a binder applied thereto which flows downwardly into and binds all or an upper portion of the compressible aggregate.

Abstract: Hot-applied asphaltic and non-asphaltic sealant compositions and methods having or using defined effective polymer concentration (EPC) values of at least 7.0 are provided which (a) provide improved softening points and improved resilience without the use of any inorganic filler materials, while at the same time maintaining or increasing the ductilities of the compositions, or (b) enable the use of one or more inorganic filler materials to provide improved softening points and improved resilience while maintaining desirable viscosity levels and at least significantly limiting any losses in ductility or increasing the ductilities of the compositions.

Abstract: A centralized document system receives a request to merge a first document package associated with a first party and a second document package associated with a second party. The first document package includes a first set of documents and the second document package includes a second set of documents. In response to the request, the centralized document system identifies a first subset of documents included in both the first and second sets of documents and identifies a second subset of documents with conflicts between the first and second sets of documents. The centralized document system rectifies the second subset of documents to cure the conflicts between the first and second sets of documents. The centralized document system generates a merged document package including the first subset of documents and the rectified second subset of documents for execution by the first and second parties.