Abstract: Described herein are systems, methods, and graphical user interfaces for creating conversation models that may be executed by natural language understanding systems and/or intelligent assistant systems, particularly in enterprise and corporate environments. A conversation modeling interface may allow a modeler to position a plurality of graphical conversation-element objects on a canvas region of the interface, to specify associations and relationships between the various represented conversation-elements to define a conversation flow, and to provide input data to define various parameters and characteristics of the conversation-elements of the conversation.

Abstract: A transversal radio frequency filter circuit having a low noise amplifier connected along an input signal path, a first power divider connected between the low noise amplifier and four single taps, and an output path connected to the outputs of each of the four single taps. Each of the four single taps having a coefficient control mechanism, a polarity selection mechanism, and a time delay element. The coefficient control mechanism can include a wideband digital step attenuator configured to support high control range of the coefficient. Additionally, the circuit can include a second power divider connected between the outputs of each of the four single taps and the output path. The circuit can further include a field-programmable gate array configured to control coefficient control mechanisms, the polarity selection mechanisms, and the time delay elements (when they are variable time delay elements).

Abstract: Described herein are systems, methods, and graphical user interfaces for creating conversation models that may be executed by natural language understanding systems and/or intelligent assistant systems, particularly in enterprise and corporate environments. A conversation modeling interface may allow a modeler to position a plurality of graphical conversation-element objects on a canvas region of the interface, to specify associations and relationships between the various represented conversation-elements to define a conversation flow, and to provide input data to define various parameters and characteristics of the conversation-elements of the conversation.

Abstract: Systems and methods for processing natural language inputs to determine user intents using an insights repository are provided. An insights repository system is configured to build an insights repository as a data structure representing a plurality of entities and relationships among those various entities. The insights repository system may receive information from various sources via an event stream, and may process the information using event rules. Based on the application of the event rules, the system may configure an insights repository data structure representing various entities, relationships between various entities, and the strengths of relationships between various entities. After the insights repository is created, consumers may execute queries against the insights repository.

Abstract: A language understanding system is configured to process utterances to predict intents of users, including by suggesting utterances and intents based on searches performed by one or more microservices. A central service is configured to receive inputs/queries from a user, to communicate with a plurality of language processing microservices, and to return a response to the user. The microservices may be configured to apply respective search algorithms comparing the input to respective data sources such as databases, indexes, or knowledge graphs. The microservices may rate utterances and/or entities in the respective data sources with respect to the input. The one or more microservices may generate a ranked list and return the ranked list to the central service. The central service may then apply a secondary rating/ranking algorithm in order to select one or more predicted utterances and/or entities to return to the user based on the initial user input.

Abstract: Systems and methods for processing natural language inputs to determine user intents using an insights repository are provided. An insights repository system is configured to build an insights repository as a data structure representing a plurality of entities and relationships among those various entities. The insights repository system may receive information from various sources via an event stream, and may process the information using event rules. Based on the application of the event rules, the system may configure an insights repository data structure representing various entities, relationships between various entities, and the strengths of relationships between various entities. After the insights repository is created, consumers may execute queries against the insights repository.

Abstract: A language understanding system is configured to process utterances to predict intents of users, including by suggesting utterances and intents based on searches performed by one or more microservices. A central service is configured to receive inputs/queries from a user, to communicate with a plurality of language processing microservices, and to return a response to the user. The microservices may be configured to apply respective search algorithms comparing the input to respective data sources such as databases, indexes, or knowledge graphs. The microservices may rate utterances and/or entities in the respective data sources with respect to the input. The one or more microservices may generate a ranked list and return the ranked list to the central service. The central service may then apply a secondary rating/ranking algorithm in order to select one or more predicted utterances and/or entities to return to the user based on the initial user input.

Abstract: Described herein are systems, methods, and graphical user interfaces for creating conversation models that may be executed by natural language understanding systems and/or intelligent assistant systems, particularly in enterprise and corporate environments. A conversation modeling interface may allow a modeler to position a plurality of graphical conversation-element objects on a canvas region of the interface, to specify associations and relationships between the various represented conversation-elements to define a conversation flow, and to provide input data to define various parameters and characteristics of the conversation-elements of the conversation.

Abstract: A cutting device for cutting strips of unvulcanized rubber to proper lengths for building a pneumatic tire, in particular a radial tire, said device comprising at least one conveyor and a cutting apparatus working crosswise with respect to said conveyor for cutting a strip of unvulcanized rubber, wherein said apparatus for cutting said strip comprises means to vibrate a knife longitudinally to and fro with high frequency e.g. ultrasonic frequency and means to move the knife vibrating longitudinally to and fro along a track crosswise with respect to said strip.

Abstract: A nursing bottle unit includes an open-ended elongated tubular nursing holder having a neck portion at one open end thereof, a disposable and collapsible liquid-retaining bag open at one end thereof, received within the tubular nursing holder, a plug member at least partially received within the neck portion adapted to clamp a portion of the bag against the internal surface of the neck portion, and a nipple mounted on the neck portion. The plug member has an axial bore formed therethrough and a one-way check valve associated therewith for allowing liquid to be withdrawn from the bag while serving to prevent the entry of air thereinto. In addition, a piston or valve member is provided which, upon withdrawal of the liquid from the bag and as a result of the vacuum generated in the bag and the prevailing ambient atmospheric pressure, causes the bag to collapse so that the effective inner volume of the bag always substantially equals the volume of the liquid remaining therein.