Abstract: Techniques for using enhanced logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system and inputting the utterance into a machine-learning model including a series of network layers. A final network layer of the series of network layers can include a logit function. The machine-learning model can map a first probability for a resolvable class to a first logit value using the logit function. The machine-learning model can map a second probability for a unresolvable class to an enhanced logit value. The method can also include the chatbot system classifying the utterance as the resolvable class or the unresolvable class based on the first logit value and the enhanced logit value.

Abstract: Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.

Abstract: In general, the disclosure relates to a method for redirecting a user to a captive portal. The method includes trapping an incoming frame originating from a host, where the incoming frame comprises a L2 header and a payload, wherein the payload specifies information associated with an external server, wherein the user of the host has not been authenticated by the captive portal at a time when the incoming frame is trapped, extracting the L2 header, an L3 header, and the payload from the incoming frame, forwarding the L3 header and the payload towards a redirection server executing on the network device, wherein the redirection server is configured to generate a redirection response based on the payload; encapsulating the redirection response to obtain an L3 response packet, encapsulating the L3 response packet using information from the L2 header to obtain an output frame, and transmitting the output frame towards the host.

Abstract: An atherectomy catheter includes an elongate flexible catheter body, a cutter near the distal end of the catheter body, a drive shaft connected to the cutter and extending within the catheter body, an imaging element near the distal end of the catheter body.

Abstract: An integrated circuit interconnect structure includes a first metallization level including a first metal line having a first sidewall and a second sidewall extending a length in a first direction. A second metal line is adjacent to the first metal line and a dielectric is between the first metal line and the second metal line. A second metallization level is above the first metallization level where the second metallization level includes a third metal line extending a length in a second direction orthogonal to the first direction. The third metal line extends over the first metal line and the second metal line but not beyond the first sidewall. A conductive via is between the first metal line and the third metal line where the conductive via does not extend beyond the first sidewall or beyond the second sidewall.

Abstract: Disclosed herein are techniques for addressing an overconfidence problem associated with machine learning models in chatbot systems. For each layer of a plurality of layers of a machine learning model, a distribution of confidence scores is generated for a plurality of predictions with respect to an input utterance. A prediction is determined for each layer of the machine learning model based on the distribution of confidence scores generated for the layer. Based on the predictions, an overall prediction of the machine learning model is determined. A subset of the plurality of layers are iteratively processed to identify a layer whose assigned prediction satisfies a criterion. A confidence score associated with the assigned prediction of the layer of the machine learning model is assigned as an overall confidence score to be associated with the overall prediction of the machine learning model.

Abstract: Connecting agent to customers is the cornerstone of contact center operations. When a customer is connected to an agent for real-time communications (e.g., voice), they can be particular sensitive to any delay, such as the delay to establish a media channel between the agent's endpoint and the customer's device. By establishing a media channel between the agent's device and a server having initially received the communication, the communication may be attached to the existing media channel without requiring the time and resources otherwise necessary to establish the media channel. Additionally, if a problem or failure occurs, a server utilized for the connection may seek to establish the media channel with a second network, such as a telephone network, or a second agent endpoint or endpoint component.

Abstract: Methods and systems for providing a visual indication of suture strain include detecting a force applied to the suture; obtaining an image including the suture; identifying, based on at least one of an algorithm to convert a plurality of forces to a plurality of colors or in a table that associates a plurality of colors to a plurality of forces, respectively, a color associated with the force applied to the suture; generating an augmented version of the image; and displaying the augmented version of the image, where the identified color is used to represent at least a portion of the suture.

Abstract: Various embodiments of the present technology may provide methods and apparatus for an interface having a first bi-directional channel and a second bi-directional channel. The interface operates in one of a first operational state and a second operational state, and performs an exemplary power-saving scheme if it is operating in the second operational state. The interface may detect a plurality of power states and initiate the power-saving scheme based on the detected power state. The plurality of power states may comprise a first power state (low current mode), a second power state (high current mode), and a third power state (mid-current mode).

Abstract: In some examples, a system may include a memory resource storing instructions, and one or more processors. In various examples the one or more processors may be configured to execute the instructions to receive data indicating that an order has been dropped by a driver of a first computing system. The order may include a set of order parameters that may include a first order parameter and a second order parameter. Additionally, the one or more processors may be configured to execute the instructions to determine a remaining delivery time period based at least a time when the order was dropped and the first order parameter. Moreover, the one or more processors may be configured to execute the instructions to obtain profile data of a set of drivers that includes availability data indicating the corresponding driver is available for assignment.

Abstract: A system comprises one or more observation stations. Each observation station of the one or more observation stations comprises a corresponding set of one or more sensors. Additionally, the system comprises one or more physical machines that implement a computation engine configured to receive first observation data from the one or more observation stations. The computation engine may use the first observation data to train a machine learning system. The computation engine may subsequently use the trained machine learning system to provide feedback regarding an additional instance of the observation subject. The computation engine outputs the feedback.

Abstract: Systems and methods described herein provide unified policy management framework network functions in enterprise networks.

Abstract: Aspects of the present invention disclose a method for dynamic password inducing techniques for security configuration and validation of a user. The method includes one or more processors identifying textual data of a user. The method further includes generating a set of password parameters for a password. The method further includes identifying one or more password dynamisms of the user from one or more sources, where the one or more password dynamisms are dynamic inputs, from the user, to an authentication device. The method further includes modifying the textual data to include a text placeholder, wherein the text placeholder includes a replacement parameter that induces the user to provide a password dynamism. The method further includes configuring the set of password parameters for the password of the user based at least in part on the one or more password dynamisms of the user from the one or more sources.

Abstract: A distributed storage system includes table controllers collectively storing partitions of a logical table having multiple rows. For each of the partitions, a corresponding table controller stores a subset of the rows of the logical table across individual pages. A management controller updates a schema of the logical table from a first to a second schema definition by, for each of the partitions, sending an update command indicating the second schema definition to the corresponding table controller. The first table controller corresponds to a first partition that includes a first subset of the rows. The first table controller, prior to receiving the update command, includes an identifier of the first schema definition within each page of data for the first subset. Subsequent to receiving the update command, the first table controller, when writing each new page of data for the first subset, includes an identifier of the second schema definition.

Abstract: Systems, methods, and devices for outputting indications regarding voice-based interactions are described. A first speech-controlled device detects spoken audio corresponding to recipient information. The first device captures the audio and sends audio data corresponding to the captured audio to a server. The server determines a second speech-controlled device of the recipient and sends a signal to the recipient's second speech-controlled device representing a message is forthcoming. The recipient's second speech-controlled device outputs and indication representing a message is forthcoming.

Abstract: Embodiments relate to a system, computer program product, and method for determining shelter areas for two-wheeler vehicles, and, more specifically, for dynamically distinguishing the behavior of two-wheeler vehicles and non-two-wheeler vehicles as an indicator of shelter areas from inclement weather. The behavior of the vehicles is distinguished through a plurality of two-wheeler vehicles slowing down and congregating at a particular location as a shelter against inclement weather, while non-two-wheeler vehicles may slow down, however, not stop proximate this location.

Abstract: The present invention relates to techniques for activating a lock in a vehicle. Said techniques discuss capturing an image of an interior of the vehicle, the image comprising an occupant on a seat of the vehicle, detecting a weight value of the occupant on a respective seat of the vehicle, processing the image for determining whether the occupant is a human or an object or an animal. It further discusses in response to the determination that the occupant is the human processing the image for determining a parameter of the human, and activating a lock based on the parameter, or the weight value and the parameter.

Abstract: A machine learning model data quality improvement detection tool is provided for identifying an accurate reference group and an accurate monitored group of a machine learning model. The tool monitors a behavior of the machine learning model for a predetermined time frame. The tool compares a determined fairness metric a pre-defined fairness threshold. Responsive to the fairness metric failing to meet the pre-defined fairness threshold, the tool modifies the monitored group to include a first portion of the reference group. The tool compares a newly determined fairness metric to the pre-defined fairness threshold. Responsive to the newly determined fairness metric meeting the pre-defined fairness threshold, the tool identifies the modified monitored group including the first portion of the user-defined reference group as a new monitored group and the modified reference group without the first portion of the user-defined reference group as a new reference group.

Abstract: Imatinib is approved and marketed in solid oral dosage forms which may be dispersed in water or apple juice for patients having swallowing difficulty. Dispersion of Imatinib solid dosage forms in apple juice may increase palatability and patient compliance but apple juice may not be available all the time for administration. Further, dispersion of Imatinib solid oral dosage forms may not administer correct and consistent dose of medicine every time. The present invention therefore provides liquid dosage forms of Imatinib which correctly and consistently administers correct dose of drug to the patients.

Abstract: Disclosed are various embodiments for executing entity-specific cryptographic code in a cryptographic coprocessor. In one embodiment, encrypted code implementing a cryptographic algorithm is received from a service via a network. The cryptographic coprocessor decrypts the encrypted code. The cryptographic coprocessor executes the decrypted code to generate a cryptogram including information encrypted using the cryptographic algorithm. The cryptogram is sent to the service via the network.