Abstract: A computer-implemented method includes receiving, by a natural language processing (NLP) annotator, an input text that is to be annotated. The method further includes determining, by the NLP annotator, a user setting that indicates an aggressiveness level of annotation to be used to annotate the input text. The method further includes selecting, by the NLP annotator, from a plurality of dictionaries, a first dictionary based at least in part on the aggressiveness level. The method further includes generating, by the NLP annotator, annotated text of the input text based at least in part on the first dictionary. The method further includes outputting, by the NLP annotator, the annotated text.

Abstract: The present disclosure generally relates to a dynamic user interface having an indication of time. The dynamic user interface having the indication of time further includes one or more geometric regions that intersect the indication of time, such that colors of the indication of time are different on opposite sides of a boundary of the one or more geometric regions that intersect the indication of time. The one or more geometric regions may shift and/or change over time, thereby providing a custom and/or unique dynamic user interface having the indication of time.

Abstract: Aspects of the present disclosure include receiving, by a processor, a procedure code for a patient, wherein the procedure code is associated with a medical device, obtaining, by the processor, patient medical data for the patient, analyzing the patient medical data to identify one or more patient medical conditions and one or more other procedure codes, determining a risk score for the procedure code based on the one or more patient medical conditions and the one or more other procedure codes, and enacting an action based at least in part on the risk score for the procedure code

Abstract: A computer-implemented method includes receiving, by a natural language processing (NLP) annotator, an input text that is to be annotated. The method further includes determining, by the NLP annotator, a user setting that indicates an aggressiveness level of annotation to be used to annotate the input text. The method further includes selecting, by the NLP annotator, from a plurality of dictionaries, a first dictionary based at least in part on the aggressiveness level. The method further includes generating, by the NLP annotator, annotated text of the input text based at least in part on the first dictionary. The method further includes outputting, by the NLP annotator, the annotated text.

Abstract: A system trains a classification model. Text windows are defined from tokens based on a window size. A network model including a transformer network is trained with the text windows to define classification information. A first accuracy value is computed. (A) The window size is reduced using a predefined reduction factor value. (B) Second text windows are defined based on the reduced window size. (C) Retrain the network model with the second text windows to define classification information. (D) A second accuracy value is computed. (E) An accuracy reduction value is computed from the second accuracy value relative to the first accuracy value. When the computed accuracy reduction value is ?an accuracy reduction tolerance value, repeat (A)-(E) until the accuracy reduction value is <the accuracy reduction tolerance value. Otherwise, increase the window size, define final text windows based on the increased window size, and retrain the network model.

Abstract: Systems and methods for generating alerts based on potential health conflicts are described. The described systems and methods may provide for identifying unstructured text from a physical environment, performing natural language processing on the unstructured text to produce annotated text, comparing the annotated text to patient medical information to find a potential conflict, and generating an alert based on the potential conflict.

Abstract: Electrical protection devices, such as for use with power systems for overvoltage protection, are disclosed. One electrical protection device includes a first electrical connection, a second electrical connection, a first electrical discharge device, and a second electrical discharge device. The first electrical discharge device includes a first conductive bus connected to the first electrical connection and a second conductive bus connected to the second electrical connection. The first electrical discharge device has a first breakdown voltage. The second electrical discharge device includes a third conductive bus connected to the first electrical connection and a fourth conductive bus connected to the second electrical connection. The second electrical discharge device has a second breakdown voltage.

Abstract: Methods and systems for ensuring operation of one or more circuit breakers electrically connected on a phase of a multi-phase power line on a transformer electrically connected within a power grid at a substation are disclosed. The method includes detecting, at the transformer, a direct current component of a multi-phase power signal received at the transformer, the direct current component comprising a direct current received at a transformer neutral, the transformer neutral being electrically connected to a ground. The method further includes determining whether the direct current is above a predetermined threshold, the predetermined threshold being based on a determination that, above the predetermined threshold, at least one of the one or more circuit breakers is incapable of reliable operation. The method includes, in response to a determination that the direct current component is above the predetermined threshold, blocking the direct current between the transformer neutral and a ground.

Abstract: A method, apparatus, and non-transitory computer readable medium for transportation services using text analytics are described. The method, apparatus, and non-transitory computer readable medium may provide for inputting a text corpus comprising patient medical information, performing text analytics on the text corpus, determining if the patient has a need for transportation assistance based on the performed text analytics, and notifying a transportation service of the need for transportation assistance based on the determination.

Abstract: Systems and methods for generating alerts based on potential health conflicts are described. The described systems and methods may provide for identifying unstructured text from a physical environment, performing natural language processing on the unstructured text to produce annotated text, comparing the annotated text to patient medical information to find a potential conflict, and generating an alert based on the potential conflict.

Abstract: Aspects of the present disclosure provide a computer-implemented method that includes obtaining the medical condition of the individual based at least in part on a personal identifier associated with the individual, the medical condition being determined by performing natural language processing of medical information associated with the individual. The method further includes obtaining characteristics of the plurality of items. The method further includes comparing the characteristics of the plurality of items to a restriction associated with the medical condition of the individual. The method further includes, responsive to determining that at least one of the characteristics of the plurality of items violates the restriction associated with the medical condition of the individual, preventing the individual from obtaining the item of the plurality of items associated with the violation.

Abstract: A control device for an electrical protection circuit for use in an alternating current system including a transformer is disclosed. An example system includes a first measurement probe, a second measurement probe configured to measure an electrical property within the electrical protection circuit, and a control module, including a processing device. The control module is configured to monitor a measurement from the first measurement probe and transmit a protection activation control signal to the switch assembly based on the measurement from the first measurement probe exceeding a first predetermined threshold. The control module is also configured to monitor a measurement from the second measurement probe and transmit a protection deactivation control signal to the switch assembly based on the measurement from the second measurement probe satisfying a second predetermined threshold.

Abstract: Embodiments include methods, system and computer program products for identifying adverse effects of medications. Aspects include obtaining a plurality of medical records for an individual, at least one of the plurality of medical records including a medication prescribed to the individual. Aspects also include creating annotations for each medical record by performing natural language processing on the medical record, wherein the annotations include a date associated with the medical record. Aspects further include grouping medications prescribed to the individual into two groups based on the annotations, the groups including a first group of medications that the individual is currently prescribed and the second group of medications that the individual does not have a current prescription for. Aspects also include identifying a known adverse interaction between one of the first group of medications and one of the second group of medications and notifying the individual of the known adverse interaction.

Abstract: Embodiments include methods, systems and computer program products for performing named entity recognition. Aspects include obtaining a text having a plurality of words and comparing each of the plurality of words to a dictionary. Aspects also include creating, based on the comparison, an annotation for at least one of the plurality of words that the least one of the plurality of words refers to a named entity. Aspects further include parsing the text to identify a part of speech for each of the plurality of words and removing the annotations from each of the at least one of the plurality of words that has a part of speech that is not one or a noun and a noun supporting adjective.

Abstract: The invention relates to a process for preparing polymeric particles, based on the use of a polyester polymer (PE) comprising units from a dicarboxylic acid component and a diol component, wherein at least 2 mol. % of the diol component is a poly(alkylene glycol). The process comprises the melt-blending of the aromatic polymer (P) with the PE, the cooling the blend and the recovery of the particles by dissolution of the PE into water. The present invention relates to polymeric particles obtained therefrom and to the use of these particles in SLS 3D printing, coatings and toughening of thermoset resins.

Abstract: A process for preparing particles of polyphenylene sulfide polymer (PPS), based on the use of a polyester polymer (PE) comprising units from a dicarboxylic acid component and a diol component, wherein at least 2 mol. % of the diol component is a poly(alkylene glycol). The process comprises the melt-blending of the PPS with the PE, the cooling the blend and the recovery of the particles by dissolution of the PE into water. The present invention relates to PPS particles obtained therefrom and to the use of these particles in SLS 3D printing, coatings and toughening of thermoset resins.

Abstract: A system determines user intent from text. A conversation element is received. An intent is determined by matching a domain independent relationship and a domain dependent term determined from the received conversation element to an intent included in an intent database that stores a plurality of intents and by inputting the matched intent into a trained classifier that computes a likelihood that the matched intent is the intent of the received conversation element. An action is determined based on the determined intent. A response to the received conversation element is generated based on the determined action and output.

Abstract: A search engine is enhanced to employ user preferences to customize answer output by, receiving a first plurality of candidate answers and weights to a first search query for a first user from a first stage of a non-semantic search engine routing and processing path; augmenting the weights for the plurality of candidate answers according to a set of preference coefficients according to a first set of preferences for the first user; selecting one or more of the first plurality of candidate answers according to the augmented weights; and producing an output including the selected one or more candidate answers.

Abstract: A system determines user intent from text. A conversation element is received. An intent is determined by matching a domain independent relationship and a domain dependent term determined from the received conversation element to an intent included in an intent database that stores a plurality of intents and by inputting the matched intent into a trained classifier that computes a likelihood that the matched intent is the intent of the received conversation element. An action is determined based on the determined intent. A response to the received conversation element is generated based on the determined action and output.

Abstract: Systems and method for detecting potentially harmful harmonic and direct current signals at a transformer are disclosed. One system includes a protection circuit electrically connected to a transformer neutral, the transformer electrically connected to a power grid, the protection circuit including a DC blocking component positioned between the transformer neutral and ground and one or more switches selectively actuated to form a path between the transformer neutral and ground in the event of unwanted DC current at the transformer neutral. The system also includes a control circuit electrically connected to the protection circuit and positioned to selectively actuate the switches based on observed conditions within the protection circuit. The system further includes a plurality of test connections disposed within the protection circuit and useable to test electrical properties of the protection circuit.