Abstract: Techniques for facilitating natural language interactions with visual interactive content are described. During a build time, a system analyzes various websites and applications relating to a particular user goal to understand website and application navigation and information relating to the user goal. The learned information is used to store configuration data. During runtime, when a user request performance of an action, the system engages in a dialog with the user to complete the user's goal. The system uses the stored configuration data to determine actions to be performed at a website or application to complete the user's goal, and determines system responses to present to the user to facilitate completion of the goal. Such system responses may request information from the user, may inform the user of information displayed at the website or application, etc.

Abstract: An inflatable structure (300) made from a composite material, wherein the inflatable structure is manufactured from at least two formed material sheets (315) that are cut out of the composite material according to a predefined cut-out structure (320), and wherein the formed material sheets are glued together at respective joins (330) of the formed material sheets via a respective double-sided adhesive tape (340).

Abstract: Techniques for facilitating natural language interactions with visual interactive content are described. During a build time, a system analyzes various websites and applications relating to a particular user goal to understand website and application navigation and information relating to the user goal. The learned information is used to store configuration data. During runtime, when a user request performance of an action, the system engages in a dialog with the user to complete the user's goal. The system uses the stored configuration data to determine actions to be performed at a website or application to complete the user's goal, and determines system responses to present to the user to facilitate completion of the goal. Such system responses may request information from the user, may inform the user of information displayed at the website or application, etc.

Abstract: An aerated beverage composition is described herein. The aerated beverage composition comprises coffee having a weight percentage in a range of 0.1-20% with respect to the aerated beverage composition, at least one structurant having a weight percentage in a range of 10-40% with respect to the aerated beverage composition, at least one sweetener having a weight percentage in a range of 21-60% with respect to the aerated beverage composition, at least one solvent. The viscosity of the aerated beverage composition is in a range of 10,0000-3,40,000 cps. The aerated beverage composition, when reconstituted with water, provides a creamy, frothy, and stable ready-to-drink beverage. The present disclosure also provides a simple and convenient process for preparing the aerated beverage composition.

Abstract: Tows of fiber are mingled with resin, wrapped in layers on a mandrel, and the layers are adhered to each other and cured on the mandrel. After all layers have been wrapped and adhered to each other and cured, thereby forming a fabric panel, the fabric panel is cut along the length of the mandrel and peeled from the mandrel. The length of the fabric panel then is wrapped around a roll. In other words, the roll is shorter than the mandrel and, with respect to the fabric panel, the roll is oriented perpendicular to the mandrel. Fibers in different layers of the fabric panel may be disposed at different angles with respect to the length of the fabric panel. Two, three, four, five, or more layers may be provided on the fabric panel.

Abstract: Techniques for storing and using multi-session context are described. A system may store context data corresponding to a first interaction, where the context data may include action data, entity data and a profile identifier for a user. Later the stored context data may be retrieved during a second interaction corresponding to the entity of the second interaction. The second interaction may take place at a system different than the first interaction. The system may generate a response during the second interaction using the stored context data of the prior interaction.

Abstract: Techniques are disclosed herein for integrating document question answering in an artificial intelligence-based platform, such as a chatbot system. The techniques include receiving a query from a user, rewriting the query to include one or more specific descriptors, computing an embedding vector for the rewritten query, retrieving one or more textual passages from a document store utilizing the embedding vector for the rewritten query, determining one or more answers to the rewritten query within the one or more textual passages, and returning the one or more answers.

Abstract: Techniques for storing and using multi-session context are described. A system may store context data corresponding to a first interaction, where the context data may include action data, entity data and a profile identifier for a user. Later the stored context data may be retrieved during a second interaction corresponding to the entity of the second interaction. The second interaction may take place at a system different than the first interaction. The system may generate a response during the second interaction using the stored context data of the prior interaction.

Abstract: In some examples, this disclosure describes a light-emitting diode (LED) driver circuit configured to: control a set of LED channels; receive, from each LED channel of the set of LED channels, channel status information that indicates whether the respective LED channel is activated or deactivated; and determine, based on the channel status information corresponding to each LED channel of the set of LED channels, a channel status of the respective LED channel. Additionally, the LED driver circuit is configured to output, to a master computing device, the channel status corresponding to each LED channel of the set of LED channels; and output, to the master computing device, channel mapping information, wherein the master computing device is configured to determine, based on the channel status information and the channel mapping information, whether one or more error conditions are present in the set of LED channels.

Abstract: Techniques for conversation recovery in a dialog management system are described. A system may determine, using dialog models, that a predicted action to be performed by a skill component is likely to result in an undesired response or that the skill component is unable to respond to a user input of a dialog session. Rather than informing the user that the skill component is unable to respond, the system may send data to the skill component to enable the skill component to determine a correct action responsive to the user input. The data may include an indication of the predicted action and/or entity data corresponding to the user input. The system may receive, from the skill component, response data corresponding to the user input, and may use the response data to update a dialog context for the dialog session and an inference engine of the dialog management system.

Abstract: A dialog system receives a user request corresponding to a dialog with a user. The dialog system processes the user request to determine multiple service providers capable of responding to the user request. The dialog system selects one service provider based on a request-to-handle score, and selects another service provider based on a satisfaction rating. The dialog system updates the dialog state based on further input provided by the user to determine an output responsive to the user request.

Abstract: A risk management system deploys an anomaly detection method for a target data instance without explicitly storing data processing architectures in memory. The anomaly detection method determines whether the target data instance is an anomaly with respect to a reference set of data instances. In one embodiment, the anomaly detection method mimics traversal through one or more trees in an isolation forest without explicitly constructing or storing the trees of the isolation forest in memory. This allows the risk management system to avoid unnecessary storage and retrieval of parts of each tree that would not be traversed if the tree were constructed. Moreover, the anomaly detection method allows anomaly detection to be efficiently performed within memory-constrained systems.

Abstract: A risk management system deploys an anomaly detection method for a target data instance without explicitly storing data processing architectures in memory. The anomaly detection method determines whether the target data instance is an anomaly with respect to a reference set of data instances. In one embodiment, the anomaly detection method mimics traversal through one or more trees in an isolation forest without explicitly constructing or storing the trees of the isolation forest in memory. This allows the risk management system to avoid unnecessary storage and retrieval of parts of each tree that would not be traversed if the tree were constructed. Moreover, the anomaly detection method allows anomaly detection to be efficiently performed within memory-constrained systems.

Abstract: A dialog manager receives text data corresponding to a dialog with a user. Entities represented in the text data are identified. Context data relating to the dialog is maintained, which may include prior dialog, prior API calls, user profile information, or other data. Using the text data and the context data, an N-best list of one or more dialog models is selected to process the text data. After processing the text data, the outputs of the N-best models are ranked and a top-scoring output is selected. The top-scoring output may be an API call and/or an audio prompt.

Abstract: An aerated beverage composition is described herein. The aerated beverage composition comprises coffee having a weight percentage in a range of 0.1-20% with respect to the aerated beverage composition, at least one structurant having a weight percentage in a range of 10-40% with respect to the aerated beverage composition, at least one sweetener having a weight percentage in a range of 21-60% with respect to the aerated beverage composition, at least one solvent. The viscosity of the aerated beverage composition is in a range of 10,0000-3,40,000 cps. The aerated beverage composition, when reconstituted with water, provides a creamy, frothy, and stable ready-to-drink beverage. The present disclosure also provides a simple and convenient process for preparing the aerated beverage composition.

Abstract: A system that can engage in a dialog with a user may select a system response to a user input based on how the system estimates a user may respond to a potential system response. Models may be trained to evaluate a potential system response in view of various available data including dialog history, entity data, etc. Each model may score the potential system response for various qualitative aspects such as whether the response is likely to be comprehensible, on-topic, interesting, likely to lead to the dialog continuing, etc. Such scores may be combined to other scores such as whether the potential response is coherent or engaging. The models may be trained using previous dialog/chatbot evaluation data. At runtime the scores may be used to select a system response to a user input as part of the dialog.

Abstract: Described herein is a system for rescoring automatic speech recognition hypotheses for conversational devices that have multi-turn dialogs with a user. The system leverages dialog context by incorporating data related to past user utterances and data related to the system generated response corresponding to the past user utterance. Incorporation of this data improves recognition of a particular user utterance within the dialog.

Abstract: Described herein is a system for rescoring automatic speech recognition hypotheses for conversational devices that have multi-turn dialogs with a user. The system leverages dialog context by incorporating data related to past user utterances and data related to the system generated response corresponding to the past user utterance. Incorporation of this data improves recognition of a particular user utterance within the dialog.

Abstract: A method of translating a structured document into a dynamic interactive document having fillable fields, the method including the steps of: (a) inputting the structured document into a computer resource; (b) initially utilising the parsable structure of the structured document to determine input fillable fields in the structured document; and (c) outputting a second structured document including a series of interactive fillable fields corresponding to the determined input fillable fields.

Abstract: New classes of thiadiazole and oxadiazole compounds for use in LC mixtures are disclosed. In an embodiment, the new classes of thiadiazoles and oxadiazoles comprise at least one phenyl ring attached to the heterocyclic ring, where no alkyl, alkenyl or alkynyl tails are attached to the phenyl ring, but one alkyl, alkenyl or alkynyl tail is attached to the other end of the molecule, and a fluoro or cyano group appears in the para position of the phenyl ring. These compounds are disclosed as being effective at inducing smectic A phases in liquid crystal mixtures, particularly in liquid crystal mixtures also possessing a smectic C phase, more particularly in materials possessing a chiral smectic C (ferroelectric) phase.