Abstract: Systems or techniques that facilitate systems and methods for providing explainability of natural language processing are provided. In various embodiments, a system can access a plain text clinical sentence. In various aspects, the system can generate, via execution of a first machine learning model, an assertion status classification label for a word of interest in the plain text clinical sentence. In various instances, the system can extract, from a hidden attention layer of the first machine learning model, word-wise attention scores corresponding to the plain text clinical sentence and render, on an electronic display, both the assertion status classification label and a graphical representation of the word-wise attention scores. In various cases, the system can determine, via execution of a second machine learning model, a reliability score for the assertion status classification label, based on the word-wise attention scores, and can render the reliability score on the electronic display.

Abstract: A system for finding Buy Now, Pay Later (BNPL) offers is programmed to receive BNPL loan product data associated with a BNPL loan available from a BNPL lender. The BNPL loan product data includes one or more of the following: a product, a product category, and a bank identification number (BIN). The system receives a search query from a consumer computing device associated with a consumer. The search query includes product data. The system is programmed to store the BNPL loan product data and the product data from the search query in one or more tables on a database. The system is programmed to determine that the product data in the search query matches at least a portion of the BNPL loan product data. Based on the determination, the system transmits an alert message to the consumer computing device. The alert message includes information identifying the BNPL loan.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first user equipment (UE) may receive a registration message including a decode key associated with a ranging service. The UE may receive, from a second UE, an encoded value and an identifier associated with the second UE. The UE may validate the identifier using the encoded value and the decode key. The UE may establish a ranging session associated with the second UE based at least in part on validating the identifier. Numerous other aspects are described.

Abstract: A biocomposite formulation comprising a polyamide, an engineering polyester and biocarbon. The biocomposite can be reinforced with various additives, including reactive compatibilizers, bio-sourced carbons, nanofillers and recycled carbon fibers.

Abstract: Architecture that enables a user to designate acceptance to receiving social cards from other user in a social network using a personal digital assistant. A mapping component maintains the mappings of all users who have accepted to participate in card sharing and the acceptance level. A whitelist of users can be created that lists the users to whom a social card can be sent from an endpoint. The user can create local groups dynamically at runtime on the local endpoint, where the local groups enable the sharing of the personalized content with multiple users concurrently. The shared card is selected by the sending user and becomes available to the PDA on the proactive canvas of the recipient's PDA along with other cards. Based on the user engagement history, these cards can be ranked among other cards social or non-social PDA cards. Conflation, push notifications, and filtering are also provided.

Abstract: A defect profiling and tracking system for a process-manufacturing enterprise is provided. The system includes a memory and a processor. The processor is configured to access entity data for a plurality of entities of the process-manufacturing enterprise and process parameter data for one or more deviating entities. The processor is configured to analyze the entity data and the process parameter data for each of the deviating entities to determine a plurality of relationships between quality defects and the process parameters to generate a unique entity specific process signature (EPS) for each entity. The processor is configured to receive real-time process parameter data for one or more entities to generate a real-time process signature for the one or more entities and compare the real-time process signature of each entity with EPS corresponding to the entity to detect one or more EPS matches that are indicative of a quality defect.

Abstract: A cooling tower for evaporative cooling of water is contained within an ISO-compliant shipping container frame, permitting stacking of cooling towers for transport and for certain industrial applications. A volume of fill media is contained within the frame. Spaced apart troughs underlie the fill media, running substantially the length of the fill media and connecting to a basin. Baffles are connected to one upper edge of the troughs, while an air flow space is positioned over the other upper trough edge. A water distribution system, with variable flow nozzles positioned closely above the fill media, sprays water over the upper surface of the fill media, where it moves by gravity down into the troughs. Fans atop the fill media move air vertically upward through the fill media.

Abstract: The technology disclosed relates to generating automated test plan scripts. Repository data associated with a test plan script is received. Source code and test plan solution data corresponding to the repository data are analyzed. For example, the repository data may be analyzed using natural language processing and static code analysis. In some embodiments, test steps of the test plan are performed to generate repository data. A suggestion of a reusable component for a particular test step or test validation is provided for one or more of the test steps. A selection of the suggestion of the reusable component for at least one of the test steps is received. An automated test plan script corresponding to the selection is generated.

Abstract: A high strength low alloy steel sheet product produced by a continuous strip process. The sheet product comprises from 0.045 to 0.06 weight percent Carbon, from 0.75 to 1.2 weight percent Manganese, from 0.02 to 0.04 weight percent Aluminum, and from 0.075 to 0.12% weight percent Titanium and an Fe balance. The steel sheet product has been subjected to cold rolling and batch annealing to form a steel sheet product having a yield strength of at least 500 MPa, a substantially ferritic microstructure with nano TiC precipitates and a hole expansion ratio of at least 60%.

Abstract: A cooling tower for evaporative cooling of water is contained within an ISO-compliant shipping container frame, permitting stacking of cooling towers for transport and for certain industrial applications. A volume of fill media is contained within the frame. Spaced apart troughs underlie the fill media, running substantially the length of the fill media and connecting to a basin. Baffles are connected to one upper edge of the troughs, while an air flow space is positioned over the other upper trough edge. A water distribution system, with variable flow nozzles positioned closely above the fill media, sprays water over the upper surface of the fill media, where it moves by gravity down into the troughs. Fans atop the fill media move air vertically upward through the fill media.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first user equipment (UE) may receive a registration message including a decode key associated with a ranging service. The UE may receive, from a second UE, an encoded value and an identifier associated with the second UE. The UE may validate the identifier using the encoded value and the decode key. The UE may establish a ranging session associated with the second UE based at least in part on validating the identifier. Numerous other aspects are described.

Abstract: An artificial intelligence (AI)-based defect diagnosis system for automatic identification of one or more defect drivers in a manufacturing environment is presented. The diagnosis system includes an input data module, an input specifications module, a product selection module, a product grouping module, a defect driver identification module, and an output module. A related method is also presented.

Abstract: In embodiments of systems and methods for managing communication between an unmanned aerial vehicle (UAV) and an unmanned aerial vehicle controller (UAC), the UAV may receive from an unmanned aerial system traffic management (UTM) device a command request from the UAC, including one or more destination Generic Public Subscription Identifiers (GPSIs), a control command, a data command, and a first tunnel-to-add indication. The UAV may send to the UAV via the UTM device a command response, which may include information responsive to the command request, and a second tunnel-to-add indication. The UAV may establish an application layer communication tunnel with the UAC based on the first tunnel-to-add indication and the second tunnel-to-add indication. The communication tunnel may be configured to enable further communications with the UAC.

Abstract: A suspension and optimized resumption is provided for a multi-USIM UE. The UE is configured to transmit a suspension-triggering message to a first network to begin a transition of a first USIM from an RRC_CONNECTED state to an RRC_IDLE state. A contention-free random access procedure is also disclosed for the optimized resumption of the first USIM from the RRC_IDLE state back to the RRC_CONNECTED state.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment may transmit, in association with a first subscription of the UE, a tune away configuration that indicates one or more tune away parameters associated with a second subscription of the UE; tune away from a network connection associated with the first subscription according to the tune away configuration; and perform a communication procedure associated with the second subscription based at least in part on tuning away from the network connection associated with the first subscription. Numerous other aspects are provided.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, in association with a first subscription of the UE, an indication of a high priority identifier to be used for paging messages associated with the first subscription. The high priority identifier may be associated with a same set of paging occasions as a second identifier allocated to the UE for paging. The UE may tune away from a network connection associated with a second subscription of the UE and monitor one or more paging occasions associated with the high priority identifier and the second identifier based at least in part on tuning away. Accordingly, the UE may determine, using the high priority identifier, whether a high priority paging message is present for the UE based at least in part on the monitoring. Numerous other aspects are provided.

Abstract: A framework for enhanced search is provided to enable the user to contextually search documents, based on specified events. A management framework provides systems for obtaining a user's contextual data and the user's interaction data for which a Context Graph and an Interaction Graph are created, respectively. The user's context data include the various events associated with the user. The user's interaction data include times and locations the user interacted with a particular document, which device was used, the type of interaction, etc. The data from the two graphs are correlated and joined into an event graph. Upon receiving a natural language query from a user, one or more contextual query elements are identified, and the event graph is spanned to identify matching results which are then provided to the requesting user device.

Abstract: Methods and systems are provided for geocoding. An example method encompasses receiving, from a delivery data corpus, a delivery data comprising one or more addresses. The method thereafter comprises identifying, one or more tokens from said one or more addresses. Further the method leads to calculating, for each of said one or more tokens, an end token score and a sub-sequence token score. The method thereafter encompasses chunking, said one or more addresses based on said end token score and said sub-sequence token score to generate one or more address chunks. Further the method comprises generating, one or more polygon regions for each generated address chunks based on said chunking. Thereafter the method comprises merging, one or more generated polygon regions for each of the generated address chunks.

Abstract: The technology disclosed relates to generating automated test plan scripts. Repository data associated with a test plan script is received. Source code and test plan solution data corresponding to the repository data are analyzed. For example, the repository data may be analyzed using natural language processing and static code analysis. In some embodiments, test steps of the test plan are performed to generate repository data. A suggestion of a reusable component for a particular test step or test validation is provided for one or more of the test steps. A selection of the suggestion of the reusable component for at least one of the test steps is received. An automated test plan script corresponding to the selection is generated.

Abstract: A suspension and optimized resumption is provided for a multi-USIM UE. The UE is configured to transmit a suspension-triggering message to a first network to begin a transition of a first USIM from an RRC_CONNECTED state to an RRC_IDLE state. A contention-free random access procedure is also disclosed for the optimized resumption of the first USIM from the RRC_IDLE state back to the RRC_CONNECTED state.