Abstract: The method disclosed herein includes determining a user interaction pattern with respect to a digital marker, the user interaction pattern based at least in part on user interaction with a capacitive sensor of a computing device, determining a geometric characteristic of the digital marker, and generating a predicted digital marking position of the digital marker on a digital medium of the computing device based at least in part on the determined geometric characteristic of the digital marker and the determined user interaction pattern.

Abstract: A method for determining an answer to a question of a product includes: receiving a question for a target product; obtaining a knowledge graph constructed in advance for the target product, in which, the knowledge graph includes entities and a relationship among the entities, and the entities at least include one question for the target product and a corresponding answer; and determining an answer corresponding to the question based on the relationship among the entities included in the knowledge graph.

Abstract: Methods, apparatus and systems related to automated evaluation of acting performance are disclosed. In one example aspect, a system for an automated evaluation of performance activities includes a user interface configured to allow a user to create a customized automated evaluation service. The user can select a subset of machine learning engines from one or more available machine learning engines to create such service. The user interface is further configured to receive a set of input data of a performance performed by a performer. The system includes the one or more available machine learning engines each configured to generate a sub-score in a specific area using the set of input data received from the user interface. The system also includes an aggregator configured to produce an output indicating a quality of the performance.

Abstract: Systems and methods are provided for the control of an industrial asset, such as a power generating asset. Accordingly, a cyber-attack model predicts a plurality of operational impacts on the industrial asset resulting from a plurality of potential cyber-attacks. The cyber-attack model also predicts a corresponding plurality of potential mitigation responses. In operation, a cyber-attack impacting at least one component of the industrial asset is detected via the cyber-attack neutralization module and a protected operational impact of the cyber-attack is identified based on the cyber-attack model. The cyber-attack neutralization module selects at least one mitigation response of the plurality of mitigation responses based on the predicted operational impact and an operating state of the industrial asset is altered based on the selected mitigation response.

Abstract: A face authentication apparatus includes a face image acquisition unit, a collation unit, a time measurement unit, and a threshold change unit. The face image acquisition unit acquires a face image of an authentication target. The collation unit performs face authentication on the face image of the authentication target on the basis of a threshold. The time measurement unit measures the elapsed time from the time of starting operation of the face authentication apparatus. The threshold change unit restricts changing of the threshold to a value larger than a value determined depending on the measured elapsed time.

Abstract: In a computer-implemented method for facilitating creation of a reusable application, during development of the reusable application, a plurality of artifacts associated with source code of the reusable application is received, wherein an artifact of the plurality of artifacts includes information related to the development of the reusable application. The plurality of artifacts is maintained as metadata for the source code of the reusable application. An application module including the source code of the reusable application and the metadata is generated, wherein the application module is configured for use by a developer for facilitating creation of a new version of the reusable application, and wherein the metadata is accessible by the developer during the creation of the new version of the reusable application for accessing the information related to the development of the reusable application.

Abstract: A method includes, through a server, determining a context of interaction between a user of a data processing device communicatively coupled to the server through a computer network and the server, fetching a set of queries from a database associated with the server in accordance with determining the context of interaction, and loading the set of queries one by one on a first media device configured to render the set of queries in an audio, a video and/or a gesture format. The method also includes, through the server, receiving a response to a query of the set of queries from the user via the first media device and/or the data processing device, and refining the set of queries based on the response received to the query from the user in accordance with an Artificial Intelligence (AI) and/or a Machine Learning (ML) engine executing on the server.

Abstract: Embodiments of the present disclosure present devices, methods, and computer readable medium for techniques for creating machine learning models. Application developers can select a machine learning template from a plurality of templates appropriate for the type of data used in their application. Templates can include multiple templates for classification of images, text, sound, motion, and tabular data. A graphical user interface allows for intuitive selection of training data, validation data, and integration of the trained model into the application. The techniques further display a numerical score for both the training accuracy and validation accuracy using the test data. The application provides a live mode that allows for execution of the machine learning model on a mobile device to allow for testing the model from data from one or more of the sensors (i.e., camera or microphone) on the mobile device.

Abstract: The present invention provides systems and methods for exchanging health data. A health data exchange platform includes health data from a plurality of data sources. The health data exchange platform preferably utilizes blockchain technology. The health data exchange platform includes both buyers of health data and suppliers of health data. The health data exchange platform includes a phenotype network system including at least one remote server, a user profile database, a report database, a permissions database, a geographic incident database, and a medical community database.

Abstract: Mechanisms are provided for determining values to associate with medical conditions of a patient. A patient assessment is received that comprises a natural language question and a corresponding answer, about a patient, provided in response to the question. Cognitive natural language processing is performed on the patient assessment to extract features from the natural language question and corresponding answer. The extracted features are evaluated within a context of a pre-existing electronic medical record of the patient. A value for a medical condition of the patient is determined based on results of the evaluation and stored in the electronic medical record for the patient.

Abstract: An online system that allows users to interact with it using expressions in natural language form includes an intent inference module allowing it to infer an intent represented by a user expression. The intent inference module has a set of possible intents, along with a small set of example natural language expressions known to represent that intent. When a user interacts with the system using a natural language expression for which the intent is not already known, the intent inference module applies a natural language inference model to compute scores indicating whether the user expression textually entails the various example natural language expressions. Based on the scores, the intent inference module determines an intent that is most applicable for the expression. If an intent cannot be determined with sufficient confidence, the intent inference module may further attempt to determine whether the various example natural language expressions textually entail the user expression.

Abstract: Aspects of the present disclosure relate to identifying and quantifying relationships between entities. Data sources can be queried to receive data regarding a party. Entities can be extracted from the data to receive a set of entities, wherein the party is a first entity of the set of entities. An ontological structure can be built that interrelates entities within the set of entities. An initial relationship strength can be determined between the first entity and a second entity based on co-occurrence between the first and second entities, wherein the second entity is a second party. A relationship score can be calculated between the first and second entities based on the initial relationship strength and at least one additional factor.

Abstract: In some implementations, a method of generating a third person view of a computer-generated reality (CGR) environment is performed at a device including non-transitory memory and one or more processors coupled with the non-transitory memory. The method includes: obtaining a first viewing vector associated with a first user within a CGR environment; determining a first viewing frustum for the first user within the CGR environment based on the first viewing vector associated with the first user and one or more depth attributes; generating a representation of the first viewing frustum; and displaying, via the display device, a third person view of the CGR environment including an avatar of the first user and the representation of the first viewing frustum adjacent to the avatar of the first user.

Abstract: Improved systems and methods for improved management of models for data science can facilitate seamless collaboration of data science teams and integration of data science workflows. Systems and methods provided herein can provide an open, unified platform to build, validate, deliver, and monitor models at scale. Systems and methods of the present disclosure may accelerate research, spark collaboration, increase iteration speed, and remove deployment friction to deliver impactful models. In particular, users may be allowed to visualize statistics about models and monitor models in real-time via a graphical user interface provided by the systems.

Abstract: A method is provided that includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable, and performing an interactive exploratory data analysis (EDA) of the values of a set of the independent variables. The method includes performing an interactive feature construction and selection based on the interactive EDA, and in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

Abstract: The present disclosure relates to systems and methods for providing a hybrid brain-computer-interface (hBCI) that can detect an individual's reinforcement signals (e.g., level of interest, arousal, emotional reactivity, cognitive fatigue, cognitive state, or the like) in and/or response to objects, events, and/or actions in an environment by generating reinforcement signals for improving an AI agent controlling the environment, such as an autonomous vehicle. Although the disclosed subject matter is discussed within the context of an autonomous vehicle virtual reality game in the exemplary embodiments of the present disclosure, the disclosed system can be applicable to any other environment in which the human user's sensory input is to be used to influence actions within the environment. Furthermore, the systems and methods disclosed can use neural, physiological, or behavioral signatures to inform deep reinforcement learning based AI systems to enhance user comfort and trust in automation.

Abstract: A system for providing a shared contents service using remote controlling of a shared autonomous device, includes: at least one shared autonomous device unit having driving, shooting, sensing and communication functions via an Internet communication network; a license transaction unit selling a license for the shared autonomous device unit, and delegating the sold license to a purchaser; a system connection unit processing the system connection of a license purchaser communication terminal by using the license delegated through the license transaction unit; a remote control unit receiving a control instruction signal of the shared autonomous device unit from the license purchaser communication terminal remotely connected through the system connection unit, and instructing to execute autonomous driving of the shared autonomous device unit according to the received control instruction signal; and a contents information providing unit providing, to a corresponding license purchaser, contents information acquired

Abstract: The present disclosure describes transaction-enabling systems and methods. A system can include a facility having a core task and a controller. The controller may include a facility description circuit to interpret historical facility parameter values and corresponding outcome values. A facility prediction circuit operates an adaptive learning system to train a facility resource allocation circuit in response to the historical facility parameter values and corresponding outcome values. The facility description circuit further interprets a plurality of present state facility parameter values and the trained facility resource allocation circuit adjusts facility resource values in response.

Abstract: The flexibility of a communication with a chatbot can be increased using a chatbot platform that can be integrated with a plurality of chat channels as well as facilitate communication between users of different chat channels. The platform can host chatbots that can leverage a plurality of resources, including internal and external natural language processors, machine learning, analytics services, and third party services to generate a response to user communications and take actions on behalf of the user. The use of the natural language processing and other additional information allows to generate an appropriate response to user queries, and to thus increase the speed with which user concerns are address. Further, the platform includes a chatbot creation program that allows a quick way to create a large number of customized chatbots without requiring advanced programming skills from the chatbot creator.

Abstract: Provided is a system and method for building context from software applications and applying the context to visual settings in a graphical user interface. In one example, the method may include receiving an identification of actions performed by a user with respect to a user interface of a software application, receiving application metadata of the actions from the software application, the application metadata providing context associated with the actions, training one or more predictive models to predict user interface preferences for the user based on the actions and the application metadata, and storing the one or more trained predictive models via a storage device.

Abstract: A plurality of metrics records, including some records indicating metrics for which anomaly analysis has been performed, is obtained. Using a training data set which includes the metrics records, a machine learning model is trained to predict an anomaly analysis relevance score for an input record which indicates a metric name. Collection of a particular metric of an application is initiated based at least in part on an anomaly analysis relevance score obtained for the particular metric using a trained version of the model.

Abstract: Techniques for improving a natural language processing (NLP) system by providing controlled access to event data to third party systems. For example, the system may control access to event data in a secured way that allows for expanded functionality such as at home games using existing sensors/devices. The system may generate event data using sensor data received from the devices and may enable a customer to configure which devices/sensors a third party system is allowed to access. In addition, the system may only send event data after receiving permission from the customer, such as upon receiving a command to begin a game. The third party system may use the event data to provide additional functionality to the customer during a period of time, which ends at the conclusion of the game, a command from the user to end the game, and/or after a timeout even occurs.

Abstract: In an information processing method of an embodiment, a computer is configured to divide observation data into training data and test data, select non-target data from the training data, select a parameter combination from a parameter set corresponding to the non-target data, classify the non-target data as clusters in a feature space of the parameter combination under clustering setting conditions, generate, for each of the clusters, a model trained to output target data included in the training data when the non-target data of the clusters is input, and reselect the parameter combination or change the clustering setting conditions such that a difference between the target data output from the model and the target data of the test data decreases.

Abstract: A video community system that provides conversation videos to a member who is one of a plurality of community members. The system can include a conversation video storage medium that stores conversation videos that are each associated with one of a plurality of thematic content events; and a member interface that couples the video community system to a plurality of user devices. The member interface receives a user request from the requesting community member for a conversation video that is associated with a particular thematic content event. In response, the video community system accesses the conversation video from the conversation video storage medium that is associated with the particular thematic content event identified in the user request. The video community system communicates the accessed conversation video and at least a portion of the particular thematic content event to the requesting community member's device for concurrent display.

Abstract: The present invention is directed to intelligent and near real-time monitoring in a streaming environment. In embodiments, a streaming platform streams raw data from raw data capture devices, where the raw data is contextually enriched using multiple information sources. A rule execution operator, integrated within the streaming platform, detects events by executing rules against the contextually enriched data. The rules applied are customizable, flexible, multivariate, and dynamically responsive to changing information. When an event is detected, an action can be instantiated in response to the event detection and/or newly derived information. The action and/or instructions for performing the action are communicated to external sources, where the action can be initiated and/or completed. Accordingly, actions are instantiated in near real time relative to the initial receipt of raw data from which the events were detected. Actions may be delayed using sophisticated temporal reasoning, in some embodiments.

Abstract: An optimization method executed by a computer upon attempting to solve a ground state of an Ising model by simulating a state change of the Ising model when a magnetic field applied to the Ising model is reduced, the Ising model representing a problem to be solved, the method including: executing a first process, the first process being a real time propagation in which an intensity of the magnetic field is reduced with progress of time in simulation; and in response to the progress of time in the real time propagation of the first process, executing a second process, the second process including reducing energy of the Ising model based on an imaginary time propagation method.

Abstract: A controller includes a processing circuit comprising one or more processors and memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations. The operations include determining a gradient of an objective function with respect to a constraint variable used to define a constraint on a control process that uses the objective function and modifying the constraint variable to have a modified value in response to determining that a trigger condition is satisfied. The trigger condition is based on the gradient. The operations include performing the control process subject to the constraint using the modified value of the constraint variable and operating equipment in accordance with a result of the control process.

Abstract: Computing systems, computing apparatuses, computing methods, and computer program products are disclosed for machine learning model lifecycle management. An example computing method includes receiving a machine learning model selection, a machine learning model experiment creation input, a machine learning model experiment run type, and a machine learning model input data path. The example method further includes determining a machine learning model execution engine based on the machine learning model experiment creation input and the machine learning model experiment run type. The example method further includes retrieving input data based on the machine learning model input data path. The example method further includes executing a machine learning model experiment based on the machine learning model execution engine, machine learning model experiment creation input, and the input data.

Abstract: There is described a neural network system for generating a graph, the graph comprising a set of nodes and edges. The system comprises one or more neural networks configured to represent a probability distribution over sequences of node generating decisions and/or edge generating decisions, and one or more computers configured to sample the probability distribution represented by the one or more neural networks to generate a graph.

Abstract: A first machine learning model processes a set of inputs to generate a first set of results. Based on that first set of results, a quality control range is calculated. A second machine learning model calculates a mean accuracy of a second set of results, based on the set of inputs. A determination of whether the mean accuracy of the second set of results is within the quality control range is made, and a user is notified of that determination.

Abstract: A controller of an information processing apparatus disclosed obtains first information about a tendency of move of a user staying in a specific facility. The controller forecasts, on the basis of the first information, an expected destination of move to which the user will move from the specific facility and an expected time slot of move during which the user will start to move from the specific facility to the expected destination of move. The controller calculates the number of users who are expected to move from the specific facility to the expected destination of move in each expected time slot of move on a slot-by-slot basis.

Abstract: The Multidimensional Machine Learning Data and User Interface Segment Tagging Engine Apparatuses, Methods and Systems (“MLUI”) transforms ambient condition data, sales data, user interface selections, cognitive intelligence question input inputs via MLUI components into project projections, campaigns, user interface visualizations, cognitive intelligence question output outputs. A category identifier selection is obtained via a category selection interaction interface mechanism. Entity segment identifier selections are obtained via entity segment selection interaction interface mechanisms. A set of visualization cognitive intelligence (CI) datapoint identifiers is determined as CI datapoint identifiers associated with each combination of a selected entity segment identifier and the selected category identifier.

Abstract: Embodiments are provided for detecting overlapping topics in a messaging system. In an example system, a plurality of trigger phrases is received, where each trigger phrase is configured to trigger a bot that receives the trigger phrase to select a corresponding topic for conversation. For each trigger phrase, a vector representation is generated. Measures of similarity are generated based at least on the vector representations, where each measure of similarity represents a degree of similarity between a respective pair of vector representations. A topic overlap is detected based on a pair of vector representations having a measure of similarity above a similarity threshold, where the topic overlap indicates two trigger phrases that are overlapping. The topic overlap is provided to an authoring tool that comprises one or more interactive elements to enable a user to change at least one of the two trigger phrases that are overlapping.

Abstract: A body and hand association method includes: an image to be detected of which an image content includes a body and a hand is acquired; a body bounding box of the body and a hand bounding box of the hand are determined in the image to be detected; an association probability between the body bounding box and the hand bounding box is determined; a circumscribed box of the body bounding box and the hand bounding box is determined; and a degree of association between the body and hand in the circumscribed box is determined based on a hand key point in the circumscribed box and the association probability.

Abstract: A method, a device, and a non-transitory storage medium are described, which provide a recommendation system with performance management service. The service may include selecting and ranking content that relate to a user query and a problem associated with an application and/or a device. The service may include invoking a remedial procedure based on user feedback data. The service may include similarity and classification models based on successful recommendation records.

Abstract: Systems and methods are provided for dynamically adjusting a website of an entity using information that has been received, stored, gathered, and/or otherwise obtained about what people want to find on the entity's website. A website may be dynamically adjusted using trending information. Dynamically adjusting may comprise generating and presenting links on the website to webpages in order of volume over a defined time threshold, or by variance over a standard volume over a longer established time frame. Dynamically adjusting the website may comprise providing an element on a website for what is most urgent to customers. A unit associated with a website may be monitored, and when the unit volume or activity starts to spike beyond normal expectations, then information about the unit is proactively and/or preemptively offered on the website, or a webpage of the website, without ever having a conversation with a user.

Abstract: The Multidimensional Machine Learning Data and User Interface Segment Tagging Engine Apparatuses, Methods and Systems (“MLUI”) transforms ambient condition data, sales data, user interface selections, cognitive intelligence question input inputs via MLUI components into project projections, campaigns, user interface visualizations, cognitive intelligence question output outputs. A cognitive intelligence (CI) datapoint identifier cache datastructure is generated, the CI datapoint identifier cache datastructure configured to comprise a category identifier and an entity segment identifier. A CI datapoint value cache datastructure is generated, the CI datapoint value cache datastructure configured to comprise a set of module datastructures, each module datastructure corresponding to a module identifier associated with the category identifier, each module datastructure comprising a set of metric datastructures, each metric datastructure corresponding to a set of calculated metrics.

Abstract: Methods of and systems to provide performance measurement are provided utilizing an architecture configured to efficiently merge and monitor different types of performance data. Connectors are provided to receive and translate different types of performance data from different sources. The performance data is translated into and stored in a common data model format. In some embodiments, key attributes are defined for each of the performance data sources that uniquely characterizes each relevant performance data so that is can be parsed into separate processing streams to increase system performance. The key attributes also act as cues to organize the performance data as it is being merged so that it can be accessed without requiring a specific source data linkage. Using model listeners, determinations can be quickly made regarding when performance data is changed to reduce calculations necessary to determine measure values. Some embodiments merge different types of performance data in real-time.

Abstract: Systems for using cognitive automation techniques to detect unauthorized events are provided. In some examples, a request for a product or service (e.g., event processing) may be received. The request may be received electronically, via a telephone communication, in person, or the like. The request may be analyzed (e.g., using a cognitive automation model) to determine whether it is potentially unauthorized. If so, one or more requests for additional information may be generated or identified. For instance, requests for authentication information, responses to questions or a series of questions, or the like, may be generated. In some examples, the additional information requested may be identified using the cognitive automation model. Responses to the request for additional information may be analyzed (e.g., using the cognitive automation model) to determine whether the request for the product or service is unauthorized. If so, processing the request may be prevented.

Abstract: From a quantum program a first mutant is generated using a processor and a memory, where the first mutant is a randomly-generated transformation of the quantum program. A quality score, a correctness distance, and a probability of acceptance corresponding to the first mutant are computed. An acceptance corresponding to the first mutant is determined according to the probability of acceptance. Upon determining that an acceptance of the first mutant corresponding to the probability of acceptance exceeds an acceptance threshold, the quantum program is replaced with the first mutant. Upon determining that the quality score exceeds a storage threshold and that the correctness distance is zero, the first mutant is stored. These actions are iterated until reaching an iteration limit.

Abstract: Anomaly detection and self-healing for robotic process automation (RPA) via artificial intelligence (AI)/machine learning (ML) is disclosed. RPA robots that utilize AI/ML models and computer vision (CV) may interpret and/or interact with most encountered graphical elements via normal learned interactions. However, such RPA robots may occasionally encounter new, unhandled anomalies where graphical elements cannot be identified and/or normal interactions will not work. Such anomalies may be processed by an anomaly handler. The RPA robots may have self-healing functionality that seeks to automatically find information that addresses anomalies.

Abstract: Aspects of systems and methods for providing contextual and event driven insights are provided. The system monitors information about the users and their conversations. Upon receiving a natural language request for information for a topic, the system utilizes a model to extract one or more topics from the request. The system utilizes the topic to query a resource for candidate users with knowledge about the topic. The system then queries a resource to identify candidate content items associated with the topic and the candidate users. Thereafter, the system refines the candidate users and the candidate content items to identify relevant users and content items that are meaningful to the user.

Abstract: In some examples, a user, either a customer or potential customer of a business, engages in conversations with a virtual assistant (VA) provided by the business. The virtual assistant (VA) is further supported by one or more human assistants (HA), if needed. In embodiments, to facilitate seamless transitions between a VA and a HA, when needed, an intelligent decision maker (IDM) is provided. The IDM receives a user question and a proposed answer to the question from a VA, evaluates the proposed answer in the context of the conversation, and determines if the proposed answer requires further review by an HA. In response to a determination that the proposed answer requires further review, the IDM sends the proposed answer to an HA, and, in response to an indication by the HA, takes further action in the conversation.

Abstract: State-of-the-art techniques hardly attempt to address controlled resource access problem in context of Basic Emergent Users (BEUs). Embodiments of the present disclosure provide a method and system for Proof of Work (POW) based protection of resources. The method includes using the POW for work done by BEUs in physical world and mapping it to digital world to generate crypto currency in terms of credit score, wherein an end user is eligible or authorized to use a resource of an entity to get a desired service if accumulated credit score is above a credit threshold. Gaining points to improve the credit score is challenging as it is based on percentage of compliance achieved by the BEU through actual work in accordance with a compliance protocol. Further, the method includes authenticating the authorized user based on a set of questions with increasing difficulty, derived based on a culture graph.

Abstract: An intelligent system, such as an autonomous robot agent, includes systems and methods to learn various aspects about a task in response to instructions received from a human instructor, to apply the instructed knowledge immediately during task performance following the instruction, and to instruct other intelligent systems about the knowledge for performing the task. The learning is accomplished free of training the intelligent system. The instructions from the human instructor may be provided in a natural language format and may include deictic references. The instructions may be received while the intelligent system is online, and may be provided to the intelligent system in one shot, e.g., in a single encounter or transaction with the human instructor.

Abstract: Embodiments described herein are directed to improving machine learning (ML) model-based techniques for automatically labeling data items based on identifying and resolving labels that are problematic. An ML model may be trained to predict labels for any given data item. The ML model may be validated to determine a confusion metric with respect to each distinct pair of labels predicted by the ML model. Each confusion metric indicates how a particular label is being mistaken for another particular label. The confusion metrics are analyzed to determine whether any of the ML model-generated labels are problematic (e.g., a label conflicts with another label, a label that is rarely predicted, a label that is incorrectly predicted, etc.). Steps for resolving the problematic labels are implemented, and the ML model is retrained based on the resolution steps. By doing so, the ML model generates a more accurate label for a data item.

Abstract: A computerized method is provided for automatically determining answers to a plurality of questions. The method includes automatically discovering a plurality of questions by processing historical data related to prior customer interactions. The automatically discovering includes applying a linguistic analytical model on the data related to historical customer interactions to detect the plurality of questions, vectoring the plurality of questions to generate mathematical representations of the questions, and grouping the plurality of questions into one or more clusters in accordance with similarities of the questions as measured based on their mathematical representations. The method also includes identifying the questions that do not have an existing answer. The method further includes determining at least one probable answer to each of the representative questions using a content mining technique that mines pertinent data from one or more identified content sources.

Abstract: A data analysis apparatus executes: a selection process selecting a first feature variable group that is a trivial feature variable group contributing to prediction and a second feature data group other than the first feature variable group from a set of feature variables; an operation process operating a first regularization coefficient related to a first weight parameter group corresponding to the first feature variable group in a manner that the loss function is larger, and operating a second regularization coefficient related to a second weight parameter group corresponding to the second feature variable group in a manner that the loss function is smaller, among a set of weight parameters configuring a prediction model, in a loss function related to a difference between a prediction result output in a case of inputting the set of feature variables to the prediction model and ground truth data corresponding to the feature variables.

Abstract: An online connection server is configured to more accurately predict connections for a viewing member of an online connection network. The online connection server may implement a machine-learning model that uses prior interactions by the viewing member to determine those connections that are likely to lead to more substantial interactions with the viewing member. The machine-learning model may be implemented using a reinforcement learning technique, such as a Deep Q network. The online connection server may further implement a state representation module that generates a state from a graph-based embedding of the viewing member profile, where the state is used to train the machine-learning model and determine an optimal candidate to recommend as a connection for the viewing member.

Abstract: A method, computer program product, and computer system identifying, by a computing device, an intent relating to a query associated with an object. A plurality of informational items associated with the object may be identified. At least a first informational item of the plurality of informational items associated with the object for which a first portion of information is already known may be identified. At least a second informational item of the plurality of informational items associated with the object for which a second portion of information is unknown may be identified. A question may be generated to determine the second portion of information based upon, at least in part, the second portion of information being unknown. An answer may be received for the question generated to determine the second portion of information.