Abstract: A system and a computer program product are provided for evaluating question-answer pairs in an answer key by generating a predicted answer to a test question based on the answer key modification history for comparison matching against a generated answer that is generated in response to the test question, and then comparing the predicted answer and generated answer to determine an accuracy score match indication therebetween so as to present an indication that the answer key may have a problem if there is a match between the predicted answer and generated answer.

Abstract: A method of automatically providing personalized learning activities to users of an online learning platform is described. A quest is built based on an input of at least a first user's educational objective. The quest includes a primary quest that starts with a start node, ends with the end node, and includes a set of intermediate nodes, wherein each node of the primary quest must be traversed by the first user in order to complete the quest. The quest includes at least one secondary quest that starts with a node of the primary quest as its start node and includes a second set of intermediate nodes. As the user selects a node of the quest, educational activities related to its respective concept are presented to the user. The user's progress in the quest is tracked.

Abstract: In an example, for each of one or more terms in a text document, one or more entities to which the term potentially maps are identified. The text document includes at least one ambiguous term. One or more features are extracted from the text document. An attention model is applied to the text document based on the extracted one or more features, resulting in an attention weight being applied to each of the one or more terms in the text document. The one or more terms are encoded based on the attention weights. Each of one or more ambiguous terms is classified based on the encoded terms, the classification assigning a value to each different entity that each ambiguous term potentially maps to. A minimum entropy loss function is evaluated using the classification, and results are back-propagated to the attention model.

Abstract: In configuring a processing system with an application made up of machine learning components, where the application has been trained on a set of training data, the application is executed on the processing system using another set of training data. Outputs of the application produced from the other set of training data identified that concur with ground truth data are identified. The components are adapted to produce outputs of the application that concur with the ground truth data using the identified outputs of the application.

Abstract: A system and a computer program product are provided for evaluating question-answer pairs in an answer key by generating a predicted answer to a test question based on the answer key modification history for comparison matching against a generated answer that is generated in response to the test question, and then comparing the predicted answer and generated answer to determine an accuracy score match indication therebetween so as to present an indication that the answer key may have a problem if there is a match between the predicted answer and generated answer.

Abstract: Embodiment of the present disclosure discloses method and device for obtaining at least one influencing causal factor based on expert subjective judgement. Initially, first relative weightage values of plurality of predefined causal factors associated with each of one or more decision trees of classification in decision-making model is determined. Decision space is determined for classification based on first relative weightage values and base hypothesis associated with classification. The decision space is mapped with expert subjective judgment provided by expert user for classification. Error value associated with classification is determined based on mapping. Base hypothesis of classification is optimized such that optimized base hypothesis corresponds to minimum value of error value. Influencing causal factor from plurality of predefined causal factors are obtained by performing ensemble technique using optimized base hypothesis.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that leverage artificial intelligence and machine learning to screen candidate pharmaceutical molecules or compounds for pharmaceutical uses (e.g., treating diseases or conditions). The screening may be based on structural similarity between the candidate pharmaceutical molecules and various pharmaceutical targets (e.g., proteins, nucleic acids, etc.). In aspects, one or more machine learning (ML) models may be trained to assign a candidate pharmaceutical molecule to one of multiple clusters based on chemical/physical properties of the candidate pharmaceutical molecule and chemical/physical properties of pharmaceutical targets associated with the clusters. The pharmaceutical targets associated with the cluster may be scored based on comparisons between the candidate pharmaceutical molecule and the pharmaceutical target, and a subset of the pharmaceutical targets may be identified based on the scores.

Abstract: An example chatbot generation platform may receive a request to generate a chatbot; determine a chatbot template for the chatbot based on the request; obtain custom chatbot information according to the chatbot template; generate a chatbot corpus for the chatbot using the custom chatbot information and the chatbot template; generate a set of question and answer (QnA) pairs based on the chatbot corpus; configure a language analysis model for the chatbot; build the chatbot according to the set of QnA pairs and the language analysis model; and deploy the chatbot to a chatbot host platform for operation. The chatbot may be built to engage in an interaction with a user via the chatbot host platform, use the language analysis model to select one or more QnA pairs from the set of QnA pairs during the interaction, and train the language analysis model based on the interaction.

Abstract: Data about clients, items included in an item inventory, executable code for recommendation processes, and executable code for feature selection process(es), are stored. The recommendation processes are used to identify items in the item inventory that are recommended for specific clients, and the feature selection process(es) is/are used to select features that are displayed to entities tasked with selecting items from the item inventory for clients. Selection feedback and client feedback are received. One or more feature selection process(es) is/are modified based on the selection feedback and/or the client feedback, to thereby change which, where or/or how certain portion of the data about clients is displayed to the entities tasked with selecting items from the item inventory for the clients, and/or change which, where and/or how certain portion of the data about items is displayed to the entities tasked with selecting items from the item inventory for the clients.

Abstract: A computer-implemented optimization problem arithmetic method includes receiving a combinatorial optimization problem, determining, based on scale or a requested accuracy of the combinatorial optimization problem, a partition mode and an execution mode, the partition mode defining a logically divided state of an arithmetic circuit, the execution mode defining a range of hardware resources to be utilized in arithmetic operation for each of partitions generated by logically dividing the arithmetic circuit, and causing the arithmetic circuit to execute arithmetic operation of the combinatorial optimization problem in accordance with the determined partition mode and the determined execution mode.

Abstract: Systems, devices, media, and methods are presented for dynamically sampling training elements while training a plurality of machine learning models. The systems and methods access a plurality of training elements and generate an element buffer including a specified number of positions. The systems and methods generate a random value for each position for the element buffer and map a training element of the plurality of training elements to each position within the element buffer in a first order. The systems and methods generate a second order for the training elements and allocate the training elements to a plurality of machine learning models according to the second order.

Abstract: Techniques are provided to reduce the possibility of missing a message when searching for the message in a messaging group. In some implementations, a user input that indicates a selected contact in a messaging group, is received. The messaging group includes a plurality of messages posted by one or more contacts. From among the plurality of messages, a first set of messages that includes messages posted by the selected contact is identified. On a display interface, the messages of the first set is displayed while hiding messages from the plurality of messages that are not included in the first set. Optionally, a second set of messages that includes messages that were not posted by the selected contact, is identified from among the plurality of messages. A hidden message quantity is determined based on a number of messages in the second set of messages and displayed on the display interface.

Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.

Abstract: A method and system are provided. The method includes providing an actionable business entity operating model. The method further includes extending the actionable business entity operating model to drive user interface behavior on a user interface device having at least a display device, by extending class and property meta classes of the actionable business entity operating model to include user interface behavior semantics. The extending step includes configuring the user interface behavior semantics to be responsive to an operation state of the actionable business entity operating model.

Abstract: A cognitive information processing system comprising: a cognitive inference and learning system coupled to receive data from a plurality of data sources and to provide insights to a destination, the cognitive inference and learning system comprising a first interface, the first interface providing the data from the plurality of data sources to the cognitive interface and learning system, and, the cognitive inference and learning system comprising a second interface, the second interface providing the cognitively processed insights to the destination.

Abstract: Systems and methods for using natural language processing (NLP) to control automated gameplay in one or more online games within an online gaming platform are disclosed. Exemplary implementations may: train a pretrained text-based system to generate sequences indicating one or more activities, wherein activities are associated with characteristics of user-controllable characters such that a particular user-controllable character having a particular characteristic may perform, within the online gaming platform, one or more activities from a particular set that is associated with the particular characteristic; receive user input describing one or more commands; generate, using the pretrained text-based system, a sequence indicating one or more activities based on the user input; transfer the generated sequence to the online gaming platform; effectuate automated execution of activities by the particular user-controllable character in accordance with the generated sequence.

Abstract: An approach for forecasting demand. The approach includes a method that includes receiving one or more variables associated with an event. The method further includes generating, by at least one computing device, a model to forecast future demand based on the one or more variables. The method further includes determining, by the at least one computing device, a load to provision one or more servers to meet the future demand. The load is based on the model.

Abstract: A Deep Learning Dendritic Cell Algorithm (DeepDCA) is employed in an intrusion detection system (IDS) and method. The framework adopts both a Dendritic Cell Algorithm (DCA) and a Self Normalizing Neural Network (SNN). The IDS classifies interned of things (IoT) intrusion, while minimizing false alarm generation, and it automates and smooths the signal extraction phase which improves the classification performance. The IDSselects the convenient set of features from the IoT-Bot dataset, and performs their signal categorization using the SNN. Experimentation demonstrated that the IDS with DeepDCA performed well in detecting IoT attacks with a high detection rate demonstrating over 98.73% accuracy and a low false-positive rate. Also, IDS was capable of performing better classification tasks than SVM, NB, KNN and MLP classifiers.

Abstract: A memory stores a hierarchy representing an arrangement of content for a graphical user interface (GUI), wherein the content includes sibling components that have a common parent component, wherein components of the GUI are respectively associated with position indicators and click counts. One or more processors are configured to: (i) provide a first representation of the GUI with the sibling components arranged according to a first ordering, wherein the first ordering is based on the position indicators of the sibling components; (ii) receive selections of the components, wherein the selections are received by way of the GUI; (iii) update the click counts based on the selections; (iv) recalculate the position indicators based on the click counts; and (v) provide a second representation of the GUI with the sibling components arranged according to a second ordering, wherein the second ordering is based on the position indicators as recalculated.

Abstract: An aspect of the invention includes a method for receiving, using a processor, a request to generate a migration plan for migrating an application from a source environment to a target environment. The request includes configuration parameters of the application. A set of possible actions that can be performed to migrate the application from the source environment to a target environment are identified, using the processor, based at least in part on the configuration parameters of the application. The migration plan is generated, using the processor, based at least in part on the request and the identified set of possible actions. The migration plan specifies a subset of the set of possible actions. The generating of the migration plan includes executing an artificial intelligence (AI) engine to identify patterns in the identified set of possible actions. The migration plan is output.

Abstract: A chat robot may be used to facilitate interaction with a user in the determination of whether to initiate and process a data subject access request (DSAR). At a DSAR submission webpage, the chatbot may interact with a user to determine the information the user is in need of and/or the actions that the user may take. The chatbot may provide the information desired by the user, avoiding the processing overhead of submission and fulfillment of a DSAR. The chatbot may also facilitate completion of a DSAR on behalf of the user when needed.

Abstract: An information processing method in an interactive apparatus that questions a user's symptom through interaction with a user includes: outputting first question information of a first type concerning the user's symptom to a display or a speaker connected to the interactive apparatus, receiving first answer information indicating an answer to the question in the first question information from a keyboard, a touch panel, or a microphone connected to the interactive apparatus, outputting second question information of the first type concerning the user's symptom to the display or the speaker when it is determined that the answer in the first answer information does not include a word in a negative expression, and outputting third question information of a second type concerning the user's symptom to the display or the speaker when it is determined that the answer in the first answer information includes the word in the negative expression.

Abstract: Ising devices interconnected via buses each include: neuron circuits that each update, when a value of an output signal from one of connection destination neuron circuits changes, a value based on an update signal; a memory holding connection destination information wherein items of address information respectively identifying the destination neuron circuits and the ising devices including these circuits and identification information about weight values are associated with each other; a control circuit that outputs, when an output signal of a destination neuron circuit in an ising device other than the own ising device changes, the value of the changed output signal and the update signal based on the destination information; and a router that receives a mode set value from a control device and determines whether to connect at least two neighboring ising devices, or a neighboring ising device and the control circuit, based on the set value.

Abstract: A system, a control unit, and a method for controlling operation of a technical system are provided. The technical system includes a plurality of sensors. The method includes receiving first sensor data from a first sensor of the plurality of sensors. The method includes detecting a first sensor anomaly based on failure of the first sensor to generate the first sensor data. The failure of the first sensor includes generation of anomalous first sensor data. The method also includes validating the first sensor anomaly based on a comparison between the first sensor data and a virtual first sensor data. Thereafter, a control command is generated to the technical system by replacing the virtual first sensor data in lieu of the first sensor data when the first sensor anomaly is validated.

Abstract: Described herein is a system and method for transforming contextually relevant items. A search query is received, and, for each of a plurality of electronically stored items (e.g., stored in a source platform), a probability that the stored item is relevant to the search query is calculated using a classification model. Stored items having a calculated probability greater than or equal to a threshold probability are identified. Contextually relevant portions of the identified stored items is determined using a contextual model. The determined contextually relevant portions of the identified stored items are extracted. The extracted contextually relevant portions of the identified stored items are transformed into a target platform. An output of the extracted contextually relevant portions of the identified stored items in the target platform is provided.

Abstract: A data analysis system utilizing custom unsupervised machine learning processes over a communications network is disclosed, the system including a repository of data, a web application deployed on a web server, the web application including a data collection interface, wherein the web application is configured for providing a graphical user interface for modifying threshold parameters of a clustering algorithm for clustering the data, executing the clustering algorithm with the threshold parameters that were modified, thereby producing a set of results, providing a graphical user interface for reviewing the set of results of the clustering algorithm and re-executing previous steps if the set of results are not useful and, executing a deep learning algorithm in a deep learning software framework on the set of results, thereby establishing relationships between the data, and providing generalizations of the data.

Abstract: An approach is provided that receives transaction data from a client that is running an app. The received transaction data identifies a latest step performed by the client. The received transaction data is compared to rules that have been generated from previous inputs of transaction data to an association rule learning algorithm. Each of the rules include steps and a confidence value corresponding to a last step of each of the respective rules. The approach identifies, based on the comparison, some rules where the latest step performed by the client is the penultimate step of the rules. One of the rules is selected based on the confidence value of the respective rule. The process then transmits a message to the client to perform the last step of the selected rule.

Abstract: Techniques are described that facilitate automatically providing entities with rephrased versions of standard answers. In one embodiment, a computer-implemented is provided that comprises determining, by a device operatively coupled to a processor, a talking style of a plurality of talking styles that an entity is associated with based on reception of natural language input from the entity proposing a question related to a defined topic. The method further comprises selecting, by the device based on the talking style, an answer rephrasing model from a plurality of answer rephrasing models respectively configured to generate different rephrased versions of a standard answer to the question, and employing, by the device, the answer rephrasing model to generate a rephrased version of the standard that corresponds to the talking style.

Abstract: Systems, methods, and apparatuses for associating digital media with physical device. A method for controlling a hardware state input based on uniform resource locator (URL) data can include identifying URL data associated with a web browser, comparing the identified URL data to stored URL data, identifying stored hardware device data based on the comparison, generating a control signal based on the determined hardware device data, and/or transmitting the control signal to a microcontroller communicatively coupled to a hardware device. The microcontroller can adjust a hardware state of the hardware device based on the received control signal.

Abstract: The present teaching relates to method, system, medium, and implementations for user machine dialogue. An instruction is received by an agent device for rendering a communication directed to a user involved in a dialogue in a dialogue scene and is used to render the communication. A first representation of a mindset of the agent is updated accordingly after the rendering. Input data are received in one or more media types capturing a response from the user and information surrounding the dialogue scene and a second representation of a mindset of the user is updated based on the response from the user and the information surrounding of the dialogue scene. A next communication to the user is then determined based on the first representation of the mindset of the agent and the second representation of the mindset of the user.

Abstract: Apparatus, system and computer-implemented method for arranging, organising and mapping ideas or planning processes in a graphical workspace for idea management. This includes a graphical user interface (GUI) with an idea map window and a word processor document window. The idea map represents ideas as a hierarchical network of nodes and links. Selection of a subset of the ideas to be shown as a separate idea map layer, wherein the ideas of the subset have different positions, different links and relationships to the ideas displayed in the main idea map, thus creating a different layout and mapping representation; and display a separate word processor document associated with only the ideas of the subset and the relationships inside the separate idea map layer.

Abstract: Methods, systems, and computer readable media concern natural language processing and searching for identifying biological products in an electronic document. The method includes extracting, from the electronic document, a candidate text phrase representing a potential biological product reference in the electronic document and parsing the candidate text phrase into a syntactic structure including one or more terms. The method includes tagging each of the one or more terms in the syntactic structure with a vocabulary tag. The vocabulary tag represents a technical meaning of a term in the potential biological product reference. The method includes calculating a total score for the candidate text phrase based on relative tag scores associated with each vocabulary tag for the one or more terms. The method includes classifying the candidate text phrase as a biological product reference and includes searching a database for one or more product entries based on the biological product references.

Abstract: An artificial intelligence data analytics system, including: a data analytics algorithm accessible by an analyst operable for receiving data from one or more sources, applying one or more analytical tools to the data, and displaying summary information to the analyst; an artificial intelligence algorithm accessible by the analyst operable for applying a preferred artificial intelligence methodology to the data and automatically triggering and executing an action on behalf of the analyst; and an artificial intelligence learning algorithm accessible by the analyst operable for statistically scoring a plurality of potential artificial intelligence methodologies to be used by the artificial intelligence algorithm, receiving a corresponding analyst preference as to the preferred artificial intelligence methodology, and causing the artificial intelligence algorithm to utilize the preferred artificial intelligence methodology.

Abstract: A system and method that enables usage of data embedded inside social media data to help estimate buy intent (BI), to allow companies or organizations to utilize this information to track conversations about their brand, to engage with their customers/users, to conduct advisement and investment efficiency analysis, to manage and reduce potential risk, and identify the factors that may affect company sales and revenues.

Abstract: A chatbot maintains a conversation with a user by providing a plurality of separate conversational tiers that allow the chatbot to interact with the user, each of the conversational tiers having a set of production rules that are independent of production rules for other ones of the tiers. The production rules indicate a flow of conversation between the user and the chatbot. The chatbot selects one of the conversational tiers based on previous conversational tiers used by the chatbot in connection with conversing with the user and based on content of conversations between the user and the chatbot. The chatbot responds to statements of the user according to a specific production rule that is chosen by the chatbot based on a particular one of the conversational tiers that has been selected and based on other factors. A scripting engine may match statements of the user with specific production rules.

Abstract: Disclosed herein are a parameter server and a method for sharing distributed deep-learning parameters using the parameter server. The method for sharing distributed deep-learning parameters using the parameter server includes initializing a global weight parameter in response to an initialization request by a master process; performing an update by receiving a learned local gradient parameter from the worker process, which performs deep-learning training after updating a local weight parameter using the global weight parameter; accumulating the gradient parameters in response to a request by the master process; and performing an update by receiving the global weight parameter from the master process that calculates the global weight parameter using the accumulated gradient parameters of the one or more worker processes.

Abstract: Embodiments disclose a man-machine interaction method, a device, and a graphical user interface. The method includes: displaying, by an electronic device, at least one icon on a display, where at least one shortcut function is preset for a first software program marked by a first icon of the at least one icon; detecting, by the electronic device on a pressure-sensitive surface, first pressure input exerted on the first icon; determining, by the electronic device, information about the at least one shortcut function when determining that the first pressure input meets a first preset condition; continuing, by the electronic device after detecting the first pressure input, to detect second pressure input exerted on the first icon; and activating a default shortcut function of the at least one shortcut function when the electronic device determines that second pressure input meets a second preset condition.

Abstract: A system and method include an analytics engine of a system of an enterprise sharing issues encountered in the system. The method includes storing considerations to be applied to the sharing. The considerations include a service level agreement, contract, or confidentiality agreement. The method also includes deciding to share one or more of the issues based on applying the considerations to each of the issues, and sharing the one of more of the issues with one or more sharing partners based on the applying the considerations.

Abstract: A method trains an artificial intelligence system to respond to a complex query. A query/answer (Q/A) system sends a first query to an information server, where the first query is a query about a first topic with regard to a first entity, and where the information server provides access to unstructured information sources. In response to receiving a negative response to the first query for the first entity, the Q/A system sends variations of the first query and a second query about a second topic to the information server. The Q/A system identifies a pattern in the table of information in order to create the answer to the first query for the first entity. The Q/A system then trains an artificial intelligence system to respond to a complex query about the first entity with information in the table of information.

Abstract: Electronic apparatus that stores user information received from a plurality of sensor that tracks user activities of a user over a specified time period. The electronic apparatus includes circuitry that detects a baseline emotion of the user based on the user information. The circuitry detects a dominant emotion of the user based on a change in an emotional characteristic of the user and the detected baseline emotion. The circuitry further recommends content and an emotional storyboard to the user based on specified emotion associated with the content, the baseline emotion, and the dominant emotion. The recommended content and the emotional storyboard is to induce a change in an emotional type of the dominant emotion from a negative emotional type to a positive emotional type.

Abstract: The present invention relates to a method and apparatus for analysing a pair of data sets with respect to a predicate, the predicate having a predicate criterion, each data set comprising one or more elements sorted according to the predicate criterion. The invention comprises recursive partitioning of the data sets in a parallel manner across multiple computing cores until a base case is reached. The invention is particularly suited for carrying out join, filter and sort operations on large data sets within database management systems.

Abstract: Methods, apparatus, and systems are disclosed to improve selection of medical treatment. An example apparatus includes a user interface to receive health information for a patient and a data analyzer to access historical patient information stored in a database, and determine a condition based on comparing historical patient information stored in a database to the health information for the patient. The example apparatus includes a machine learning engine to recommend a treatment plan, including: a data analytic algorithm server to determine success rates of the treatment plan for the condition; and a model generator to generate a patient model, wherein the patient model predicts effects of the treatment plan. The example apparatus includes a communications interface to facilitate scheduling an appointment with a clinician.

Abstract: A vehicle includes a controller programmed to identify tag phrases for locations that express a relationship between the location and a learned location tag. The tag phrases are based on words and word sequences learned from prior selections and inputs of a user. The controller is programmed to communicate the tag phrases to the user and provide trip assistance based on a selected tag phrase chosen by the user. The locations and tag phrases are accessible to devices such that locations are identified with common tag phrases on each of the devices.

Abstract: A segment targeting system generates target segment audiences for delivery of digital content. The segment targeting system generates hit recency and frequency summary data, which identifies hit recency and hit frequency for each of multiple cookie identifiers that satisfied a metric in at least one of multiple segments and in a time range in user specified target segment audience criteria. At least a portion of this summary data is used to train a machine learning system. The machine learning system can include multiple machine learning models, with each model being associated with a different false positive to false negative penalty ratio modelling parameter when learning recency and frequency combinations of hits on webpages in each segment that work well to separate cookie identifiers that satisfied a metric for an offering in a target segment and cookie identifiers that satisfied a metric for an offering in other segments.

Abstract: A classification model with a high precision ratio at a high recall ratio is learned. A classification model learning system (100) includes a learning data storage unit (110) and a learning unit (130). The learning data storage unit (110) stores pieces of learning data each of which has been classified as a positive example or a negative example. The learning unit (130) learns, by using the pieces of learning data, a classification model in such a way that a precision ratio of classification by the classification model is made larger under a constraint of a minimum value of a recall ratio of classification by the classification model.

Abstract: An information delivery system allows for the organization and presentation of information to users. Illustratively, aspects of the disclosure correspond to a system and method which provides for interactive information delivery, or interactive learning. More particularly, a platform is disclosed which provides an independent interactive interface for content delivery and e-learning and for creation of teaching or learning presentations.

Abstract: Aspects of the disclosure relate to cognitive automation-based engine processing to propagate data across multiple systems via a private network to overcome technical system, resource consumption, and architecture limitations. Data to be propagated can be manually input or extracted from a digital file. The data can be parsed by analyzing for correct syntax, normalized into first through sixth normal forms, segmented into packets for efficient data transmission, validated to ensure that the data satisfies defined formats and input criteria, and distributed into a plurality of data stores coupled to the private network, thereby propagating data without repetitive manual entry. The data may also be enriched by, for example, correcting for any errors or linking with other potentially related data. Based on data enrichment, recommendations of additional target(s) for propagation of data can be identified. Reports may also be generated. The cognitive automation may be performed in real-time to expedite processing.

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: A server computing device, including memory storing a knowledge graph including a plurality of ontology entities connected by a plurality of edges. The server computing device may further include a processor configured to generate a glossary file based on the knowledge graph. The glossary file may include a plurality of ontology entities included in the knowledge graph. The processor may receive a plurality of utterance templates. Each utterance template may include an utterance and a predefined intention. For each utterance template, the processor may generate one or more utterance template copies in which one or more ontology entities included in the utterance are replaced with one or more utterance template fields. The processor may generate a plurality of training utterances at least in part by filling the one or more utterance template fields of the one or more utterance template copies with respective ontology entities included in the glossary file.

Abstract: A method of training a predictive model to predict a likely field value for one or more user selected fields within an application. The method comprises providing a user interface for user selection of the one or more user selected fields within the application; analyzing a pre-existing, user provided data set of objects; training, based on the analysis, the predictive model; determining, for each user selected field based on the analysis, a confidence function for the predictive model that identifies the percentage of cases predicted correctly at different applied confidence levels, the percentage of cases predicted incorrectly at different applied confidence levels, and the percentage of cases in which the prediction model could not provide a prediction at different applied confidence levels; and providing a user interface for user review of the confidence functions for user selection of confidence threshold levels to be used with the predictive model.