Disclosed are an apparatus, a system and a non-transitory computer readable medium that implement processing circuitry that receives non-dialog information from a smart device and determines a data type of data in the received non-dialog information. Based on the determined data type, the processing circuitry transforms the received first data using an input from a machine learning algorithm into transformed data. The transformed data is standardized data that is palatable for machine learning algorithms such as those used implemented as chatbots. The standardized transformed data is useful for training multiple different chatbot systems and enables the typically underutilized non-dialog information to be used to as training input to improve context and conversation flow between a chatbot and a user.

A method is provided, including: storing comments generated in response to a content item served over a network; analyzing the comments to determine features associated with each of the comments; using a scoring model to score each comment based on the comment's corresponding features; receiving a request to serve a subset of the comments; responsive to the request, selecting a ranking of the comments that is one permutation from possible rankings of the comments, wherein selecting the ranking is in accordance with a probability distribution of the possible rankings that is based on the scores of the comments; serving comments identified by the selected ranking over the network to a client device; determining a dwell time on the served comments; applying the dwell time to update the scoring model.

Artificial Intelligence (“AI”) apparatus and method are provided that correlate and consolidate operation of discrete vendor tools for detecting cyberthreats on a network. An AI engine may filter false positives and eliminate duplicates within cyberthreats detected by multiple vendor tools. The AI engine provides machine learning solutions to complexities associated with translating vendor-specific cyberthreats to known cyberthreats. The AI engine may ingest data generated by the multiple vendor tools. The AI engine may classify hardware devices or software applications scanned by each vendor tool. The AI engine may decommission vendor tools that provide redundant cyberthreat detection. The AI engine may display operational results on a dashboard directing cyberthreat defense teams to corroborated cyberthreats and away from false positives.

A method for obtaining coverage-guided fuzzing of software on a hardware target. The hardware target includes a breakpoint register, and is designed to stop an execution of the software prior to execution of an instruction of the software if the instruction is reached during the execution of the software; a memory address of the instruction is set in the breakpoint register. The method includes setting a first breakpoint prior to a first instruction of the software; executing or continuing a fuzzing iteration of the software; first checking whether the first breakpoint is reached while executing or continuing the fuzzing iteration; storing a piece of log information that includes that the first instruction in the fuzzing iteration has been reached, and optionally deleting the first breakpoint if the first check is positive. The coverage-guided fuzzing of the software includes the piece of log information.

Computer-implemented machines, systems and methods for providing insights about a machine learning model, the machine learning model trained, during a training phase, to learn patterns to correctly classify input data associated with risk analysis. Analyzing one or more features of the machine learning model, the one or more features being defined based on one or more constraints associated with one or more values and relationships and whether said one or more values and relationships satisfy at least one of the one or more constraints. Displaying one or more visual indicators based on an analysis of the one or more features and training data used to train the machine learning model, the one or more visual indicators providing a summary of the machine learning model's performance or efficacy.

A prediction engine may use the user behavior data of a user as collected by user devices to assist the user with obtaining products and services. The prediction engine may predict that a user desires to obtain a product or a service from a vendor based on user behavior data collected by applications on one or more user devices. The collected user behavior data may include a conversation of the user with one or more other persons. The prediction engine may trigger an application on a user device to prompt the user to confirm that the user requests to proceed with obtain the product or the service from the vendor. The prediction engine may notify the vendor to provide the product or the service to the user in response to receiving a confirmation from the user that the user requests to proceed with obtaining the product or the service.

Methods, systems, and computer program products for data filtering with fuzzy attribute association are provided herein. A computer-implemented method includes obtaining one or more rules, specified by an expert, that define a partial ranking of a plurality of fuzzy pairings between (i) a plurality of item attributes for items in a data catalog and (ii) a plurality of user attributes related to said items; generating an interactive session with the expert to resolve one or more ambiguities in the one or more rules; and deriving a scoring function based at least in part on (i) the one or more rules and (ii) the resolved one or more ambiguities, wherein the scoring function generates a comparative score between any two items of said data catalog for a given one of the users associated with the plurality of attributes.

In some embodiments, a self-monitoring intravenous catheter system is provided. An alarm controller is provided that receives signals representing a pH value, an oxygen saturation value, and a pressure value in proximity to the distal end of the catheter. By performing a fuzzy logic analysis of the values, the alarm controller is able to detect that the catheter is about to fail or has failed, and can cause alerts to be presented. In some embodiments, an intravenous catheter is provided that has a pH sensor and an oximeter disposed at a distal end of the catheter to obtain the pH value and oxygen saturation values analyzed by the alarm controller. Embodiments of the catheter and self-monitoring intravenous catheter system may be particularly useful in treating neonates, who are sensitive to catheter failure and are not capable of detecting the signs of failure themselves.

Implementations relate to diagnosis of crop yield predictions and/or crop yields at the field- and pixel-level. In various implementations, a first temporal sequence of high-elevation digital images may be obtained that captures a geographic area over a given time interval through a crop cycle of a first type of crop. Ground truth operational data generated through the given time interval and that influences a final crop yield of the first geographic area after the crop cycle may also be obtained. Based on these data, a ground truth-based crop yield prediction may be generated for the first geographic area at the crop cycle's end. Recommended operational change(s) may be identified based on distinct hypothetical crop yield prediction(s) for the first geographic area. Each distinct hypothetical crop yield prediction may be generated based on hypothetical operational data that includes altered data point(s) of the ground truth operational data.

A method and system for virtual environment-based interfaces applied to selected objects from video directs a system's focus of attention to an image within a first video stream and identifies an object in the image by applying a trained neural network. In response to a communication from a user comprising language and/or images describing a virtual environment, a second trained neural network is applied to generate a second video stream that embodies the identified object within a virtual environment that is in accordance with the user-described virtual environment. The second video stream is then delivered to the user. The system's focus of attention and/or generation of the virtual environment may be informed by user preferences that are inferred from user behaviors.