Abstract: A system, computer program product, and method are provided to apply artificial intelligence and natural language processing to a route navigation module. An artificial intelligence platform transforms the functionality of the navigation module in real-time. As natural language input is received, a parser is leveraged to parse the input into grammatical sub-components. An analyzer is involved to analyze and identify an associated category for the parsed sub-component(s). A sensor is provided operatively couple to the navigation module. The parsed and analyzed data are applied to an operating state of the sensor. The artificial intelligence platform dynamically translates the identified category of the received input to a natural language instruction congruent with the parsed grammatical sub-components.

Abstract: Systems and methods for embodiments of a graph based artificial intelligence systems for identity management are disclosed. Embodiments of the identity management systems disclosed herein may utilize a network graph approach to analyzing identities, roles, entitlements or other identity management artifacts of a distributed networked enterprise computing environment. Specifically, embodiments of an artificial intelligence based identity management systems may perform predictive modeling for entitlement diffusion or role evolution or other aspects of identity management artifact using network identity graphs.

Abstract: A content review system for an online system automatically determines if received content items to be displayed to users violate any policies of the online system. The content review system generates a semantic vector representing the semantic features of a content item, for example, using a neural network. By comparing the semantic vector for the content item with semantic vectors of content items previously determined to violate one or more policies, the content review system determines whether the content item also violates one or more policies. The content review system may also maintain templates corresponding to portions of semantic vectors shared by multiple content items. An analysis of historical content items that conform to the template is performed to determine a probability that received content items that conform to the template violate a policy.

Abstract: The present disclosure provides systems and methods for communication efficient distributed mean estimation. In particular, aspects of the present disclosure can be implemented by a system in which a number of vectors reside on a number of different clients, and a centralized server device seeks to estimate the mean of such vectors. According to one aspect of the present disclosure, a client computing device can rotate a vector by a random rotation matrix and then subsequently perform probabilistic quantization on the rotated vector. According to another aspect of the present disclosure, subsequent to quantization but prior to transmission, the client computing can encode the quantized vector according to a variable length coding scheme (e.g., by computing variable length codes).

Abstract: A method for indicating a responding virtual assistant from one of a plurality of virtual assistants is disclosed. The method includes receiving a spoken query from a user of an electronic device. The method includes determining whether the spoken query addresses a particular one of a plurality of virtual assistants on the electronic device. The method includes polling a first set of the virtual assistants with the spoken query in response to the spoken query not addressing a particular one of the plurality of virtual assistants. The method further includes presenting a response to the spoken query with an indicator of a virtual assistant providing the response. An apparatus and computer program product are also disclosed, which perform the method.

Abstract: A method, a computer program product, and an information handling system is provided for identifying a causal relationship between metrics performing steps. The steps include receiving a correlation significance Sij between a metric Mi and a metric Mj; receiving a mutability attribute Ai for the Mi and a mutability attribute Aj for the metric Mj from a data source; and identifying the metric Mi causing the metric Mj with the Sij if only if the Ai is immutable and the Aj is mutable.

Abstract: A system includes a user model module that generates a plurality of topic-specific user knowledge models for each user of a plurality of users, each topic-specific user knowledge model representing a level of knowledge possessed by a respective user on a single topic from a set of globally defined topics shared among the plurality of users, a expertise model building module that generates a plurality of topic-specific expert knowledge models, each topic-specific expert knowledge model representing an aggregate level of knowledge possessed by a plurality of expert users on a single topic from a set of globally defined topics shared among the plurality of users, and a processor of a computer that executes instructions for comparing the topic-specific user knowledge model of the first user with the topic-specific expert knowledge model for a respective topic to determine a distance between a user knowledge level and an aggregate expert knowledge level for the topic.

Abstract: A determination is made at a machine learning service that a training data set comprising a majority category of observation records and one or more minority categories of observation records meets a criterion for automated sampling. A sampling ratio to be used for a particular category of the majority category and the one or more minority categories is identified. A selected sampling methodology is applied to the particular category to obtain a sample in accordance with the sampling ratio. A particular machine learning model is trained using a result of applying at least the selected sampling methodology on the particular category.

Abstract: A computerized method comprising receiving, from a question answering system, a minimal answer value to a query submitted by a user. Also received are electronic documents based on the minimal answer value, and a document score value, associated with the query, for each of the electronic documents. The method comprises extracting entities and attributes from electronic documents, and for each computing one or more associated score value, and aggregating the document score value with the associated score values. The method comprises selecting some of entities and attributes based on the respective aggregated score value, thereby producing selected associated elements. The method comprises generating, using a computerized natural language (NL) generating system, a comprehensive NL answer, wherein the generating is based on the minimal answer value and the selected associated elements, and sending the comprehensive NL answer for presentation to the user.

Abstract: A method for generating inference graphs over content to answer input inquiries. First, independent factors are produced from the inquiry, and these factors are converted to questions. The questions are then input to a probabilistic question answering system (PQA) that discovers relations which are used to iteratively expand an inference graph starting from the factors and ending with possible answers. A probabilistic reasoning system is used to infer the confidence in each answer by, for example, propagating confidences across relations and nodes in the inference graph as it is expanded. The inference graph generator system can be used to simultaneously bi-directionally generate forward and backward inference graphs that uses a depth controller component to limit the generation of both paths if they do not meet. Otherwise, a joiner process forces the discovery of relations that join the answers to factors in the inquiry.

Abstract: A method includes generating, as executed by a processor on a computer, a plurality of topic-specific user knowledge models for each user of a plurality of users, each topic-specific user knowledge model representing a level of knowledge possessed by a respective user on a single topic from a set of globally defined topics shared among the plurality of users, generating a plurality of topic-specific expert knowledge models, each topic-specific expert knowledge model representing an aggregate level of knowledge possessed by a plurality of expert users on a single topic from a set of globally defined topics shared among the plurality of users, comparing the topic-specific user knowledge model of the first user with the topic-specific expert knowledge model for a respective topic to determine a distance between a user knowledge level and an aggregate expert knowledge level for the topic.

Abstract: Methods, systems, and computer program products for cognitive disambiguation of problem-solving tasks involving a power grid are provided herein. A computer-implemented method includes capturing user feedback pertaining to relevance of remote terminal unit measurements related to a grid event through user interface interactions carried out by the user, wherein the user interface is communicatively linked to at least one computing device; automatically inferring rules related to the grid event to curate remote terminal unit measurements across iterations of analysis by recognizing irrelevant data and/or distractions in a visual display associated with the user interface, wherein said automatically inferring comprises implementing machine learning via the at least one computing device based on the user feedback; and outputting candidate solutions to a problem-solving task involving the grid based on the inferred rules, wherein said outputting is carried out by the at least one computing device.

Abstract: A provenance method, system, and non-transitory computer readable medium for a plurality of eidetic systems having logs, include a log-segment clustering circuit configured to crawl the logs of each of the eidetic systems to cluster segments across the logs of temporally correlated events into clustered segments, a probabilistic interleaving circuit configured to analyze the correlated segments to interleave an order of processes in the logs and assign a probability to the order of the processes occurring, and a probabilistic linearization circuit configured to create a probability tree which includes a total probability that a process in the clustered segments causes a next process in the clustered segments until an end of the temporal event of the clustered segments for each of the interleaved order of processes interleaved by the probabilistic interleaving circuit.

Abstract: We disclose a system that optimizes deployment of sensors in a computer system. During operation, the system generates a training data set by gathering a set of n signals from n sensors in the computer system during operation of the computer system. Next, the system uses an inferential model to replace one or more signals in the set of n signals with corresponding virtual signals, wherein the virtual signals are computed based on cross-correlations with unreplaced remaining signals in the set of n signals. Finally, the system generates a design for an optimized version of the computer system, which includes sensors for the remaining signals, but does not include sensors for the replaced signals. During operation, the optimized version of the computer system: computes the virtual signals from the remaining signals; and uses the virtual signals and the remaining signals while performing prognostic pattern-recognition operations to detect incipient anomalies that arise during execution.

Abstract: A method and system for profiling interests of users based on multimedia content analysis and creating users' profiles respective thereof is provided. The method comprises receiving a tracking information gathered with respect to an interaction of a user with at least one multimedia element displayed on a user node; determining a user impression respective of at least one multimedia content element using the received tracking information; generating at least one signature for the at least one multimedia element; determining at least a concept of the at least one multimedia element using the at least one generated signature, wherein an interest of the user is determined respective of the concept; creating a user profile to include at least the user interest; and storing the user profile in a data warehouse.

Abstract: Mechanisms are provided for training and operating a Question and Answer (QA) system pipeline. A corpus of information is received which comprises historical data to which one or more filter criteria are applied to extract filtered historical data relevant to a training objective for training the QA system pipeline. Attribute data, action data, and temporal characteristic data are captured from the filtered historical data. An answer key entry is automatically generated in an automatically generated training answer key data structure based on the attribute data, action data, and temporal characteristic data. The correct answer associated with the answer key entry is an action specified by the action data. The temporal characteristic data provides a historical context for the answer key entry. The QA system pipeline is trained using the automatically generated training answer key data structure.

Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.

Abstract: A computing device compresses a gradient boosting tree predictive model. A gradient boosting tree predictive model is trained using a plurality of observation vectors. Each observation vector includes an explanatory variable value of an explanatory variable and a response variable value for a response variable. The gradient boosting tree predictive type model is trained to predict the response variable value of each observation vector based on a respective explanatory variable value of each observation vector. The trained gradient boosting tree predictive model is compressed using a compression model with a predefined penalty constant value and with a predefined array of coefficients to reduce a number of trees of the trained gradient boosting tree predictive model. The compression model minimizes a sparsity norm loss function. The compressed, trained gradient boosting tree predictive model is output for predicting a new response variable value from a new observation vector.

Abstract: Mechanisms are provided for performing load balancing of question processing in a Question and Answer (QA) system, implemented by the data processing system, having a plurality of QA system pipelines. The mechanisms receive an input question for processing by the QA system and determine a predicted question difficulty of the input question. The mechanisms select a QA system pipeline from the plurality of QA system pipelines based on the predicted question difficulty and route the input question to the selected QA system pipeline for processing. In addition, the mechanisms process the input question with the selected QA system pipeline to generate an answer for the input question.

Abstract: This disclosure relates to processing sequential interaction data through machine learning. In one aspect, a method includes obtaining a dynamic interaction graph constructed based on a dynamic interaction sequence. The dynamic interaction sequence includes interaction feature groups corresponding to interaction events. Each interaction feature group includes a first object, a second object, and an interaction time of an interaction event that involved the first object and the second object. The dynamic interaction graph includes multiple nodes including, for each interaction feature group, a first node that represents the first object of the interaction feature group and a second node that represents the second object of the interaction feature group. A current sequence corresponding to a current node to be analyzed is determined. The current sequence is input into a Transformer-based neural network model. The neural network model determines a feature vector corresponding to the current node.