Abstract: A machine learning (ML) based code transformation system that transforms a source programming code developed using a source library for execution on a source platform into remediated code for execution on a target platform is disclosed. Metadata extracted from the source programming code is used to detect the source programming language, source libraries, and the source platform. The metadata also enables modularizing the source programming code based on the functionality and identifying a node from a plurality of nodes in a communication network to execute the various source code modules. A similarity map is generated mapping the source libraries to the target libraries and the source code modules that are incompatible with the target platform are identified and remediated with similar target code modules using the similarity map.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating customized recommendations for environmentally-conscious cloud computing frameworks for replacing computing resources of existing datacenters. One of the methods involves receiving, through a user interface presented on a display of a computing device, data regarding a user's existing datacenter deployment and the user's preferences for the new cloud computing framework, generating one or more recommendations for environmentally-conscious cloud computing frameworks based on the received data, and presenting such recommendations through the user interface for the user's review and consideration.

Abstract: A device determines, from a network slice template associated with a network slice, a quality of service (QoS) profile for the network slice that includes performance metrics for corresponding QoS parameters associated with providing a service. The device monitors performance of the network slice in association with the QoS profile, and determines, based on the performance, that a performance indicator for a QoS parameter of the network slice is outside a threshold range of a performance metric. The device determines, based on the performance information and the QoS profile, a slice modification to the network slice template for the network slice, where the slice modification is configured to cause the performance indicator to be within the threshold range of the performance metric. The device causes a network slice orchestrator to update an instantiation of the network slice according to the slice modification and the network slice template.

Abstract: A device may receive a request to identify items that satisfy parameters of the request. The device may identify a plurality of items that satisfy the parameters. The device may generate a plurality of explanation sets. An explanation set of the plurality of explanation sets may relate to an item of the plurality of items. The explanation set may include at least one of: a positive explanation indicating that the item is positively associated with a first characteristic that relates to a first preference of a user, or a negative explanation indicating that the item is negatively associated with a second characteristic that relates to a second preference of the user. The device may select an item from the plurality of items based on the plurality of explanation sets. The device may provide information that includes an explanation set of the item selected.

Abstract: The present invention provides a deployment platform that enables solution modules to be created and deployed without writing new code. The solution modules may include existing solutions, solution components, connectors, and the like selected from a solution library. The deployment platform includes a development engine providing functionality for generating deployment information for the solution module. The deployment information may include a blueprint or other information for deploying the solution module to target infrastructure. The deployment platform also includes a deployment engine providing functionality for deploying the solution module to the target infrastructure automatically. During deployment, the deployment engine pushes components of the solution module to the target infrastructure in accordance with the deployment information.

Abstract: Implementations are directed to an agile security platform for enterprise-wide cyber-security and performing actions of receiving, from an agile security platform, analytical attack graph (AAG) data representative of one or more AAGs, each AAG representing one or more lateral paths within an enterprise network for reaching a target asset from one or more assets within the enterprise network, determining, for each instance of a plurality of instances of the AAG, a graph value representing a measure of hackability of the enterprise network at respective times, providing a profile of the enterprise network based on a set of graph values determined for instances of the AAG, the profile representing changes in graph values over time, determining an effectiveness of one or more security controls based on the profile, and selectively executing one or more remedial actions in response to the effectiveness.

Abstract: Knowledge graph systems are disclosed for implementing multiple approaches, including stand alone or combined approaches, for knowledge graph pruning. The approaches are based on graph sampling work such as, for example, information gain theory. The approaches are applied by a knowledge graph system to perform schema pruning, automatic graph pruning, and query correlation for improving query performance.

Abstract: An Artificial Intelligence (AI)-based attribute prediction system generates predictions for attributes of highly customized equipment in response to received user requests. Processed historical data is initially used to generate feature combinations which are then employed along with a plurality of statistical and machine learning (ML) models in order to identify a best scoring model-feature combination in two selection cycles using multiple selection criteria. The predictions for an attribute are generated by the best scoring model and feature combination. Various insights regarding the features affecting the attribute can be additionally derived to provide recommendations to the user.

Abstract: Methods, systems, and apparatus for root cause analysis in a communication network. In one aspect, a method includes providing a quantum computer with data representing a topology of the communication network, the topology comprising a graph of vertices representing network devices and edges representing connections between network devices; receiving, from the quantum computer, data representing a first subset of network devices, wherein the first subset comprises a dominating set of vertices or a vertex cover for the graph; monitoring network devices in the first subset to generate alarm data representing triggered network device alarms; providing the alarm data to a quantum computer; receiving, from the quantum computer, data representing a second subset of network devices, wherein the second subset comprises a set cover for the alarm data and the network devices in the second subset comprise diagnosed sources of failures in the communication network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neuromorphic experiential analysis of sensor data. The methods, systems, and apparatus include actions of obtaining sensor emissions from multiple sensors, generating monotonic data that indicates an orientation of the sensor emissions in respect to time, determining that the monotonic data matches a registered query, and in response to determining that the monotonic data matches a registered query, invoking an executor.

Abstract: An Artificial Intelligence (AI) based data processing system transforms a plurality of time series data sets for processing by one or more deep learning (DL) models for generating forecasts. The DL models are initially trained on training data generated from the historical data. During operation, a plurality of transformed time series data sets are generated from the plurality of time series data sets associated with different entities in an entity hierarchy via data flattening and data stacking. A primary model of the one or more DL models is trained on first-party data for generating the forecasts. An extended model of the one or more DL models is trained on third-party data from external data sources. Whenever new data is available in the first-party data or the third-party data, the primary model and the extended model are correspondingly updated.

Abstract: An Artificial Intelligence (AI)-based regulatory data processing system accesses a regulatory text corpus for training machine learning (ML) models including a topic extraction model, a feature selection model, an entity identification model and a section classification model. The regulatory text corpus includes documents pertaining to a specific domain corresponding to a received domain-specific regulatory text document. Various trained machine learning (ML) models are used to extract topics, identify entities from the new regulatory document and to classify portions of the domain-specific regulatory text document into one of a plurality of predetermined sections. The information in the new regulatory document is therefore converted into machine consumable form which can facilitate automatic execution of downstream processes such as identification of actions needed to implement the regulations and robotic process automation (RPA).

Abstract: An Artificial Intelligence (AI)-based innovation data processing system receives at least one query word related to a category. Information material including textual and non-textual data is retrieved from a plurality of data sources using the at least one query word. The information material is tokenized and parsed using a dependency parser for entity recognition, building entity relationships and for generating knowledge graphs. The output of the dependency parser is accessed by a trained classifier for obtaining respective confidence levels for each of the sentences in the textual data. The confidence levels are compared to a predetermined threshold confidence level for determining if the sentences include references to innovations. In addition, trends in the innovations are determined and responses to user queries are generated based on one or more of knowledge graphs and the trends.

Abstract: A system for auto classification of products includes an entity recognizer and a model selector. The entity recognizer receives training data including an attribute of a product. The model selector selects a feature from the training data using a first statistical model to provide a first feature and a second statistical model to provide a second feature, and trains a probabilistic classifier using the first and the second features for providing a first and a second classification models respectively. Further, the model selector calculates an accuracy score of the obtained classification models for each distinct category in a preset hierarchy of categories and selects a classification model from the obtained classification models based on the accuracy score. The selected classification model has a highest accuracy score for a corresponding category in the preset hierarchy.

Abstract: A device receives a request associated with standardizing organization-specific roles within an organization, where the request includes data that identifies titles for the organization-specific roles. The device converts the data to vectors that represent semantic meanings of the titles. The device sets a configuration of a data model by assigning weighted values to title-class identifiers that are used to associate titles, of a standardized set of titles, to a hierarchy of role classifications. The device uses the data model to determine scores that indicate likelihoods of the titles mapping to the title-class identifiers. The device identifies, based on scores, a subset of title-class identifiers that associate particular titles, of the standardized set of titles, and particular role classifications. The subset of title-class identifiers is stored in association with information relating to the particular titles. The device performs an action based on the information relating to the particular titles.

Abstract: In some examples, machine learning and rule-based identification, anonymization, and de-anonymization of sensitive structured and unstructured data may include receiving input data that is to be masked, and determining, for the input data, at least one type 1 of entity extraction from a plurality of types of entity extractions to be performed on the input data. The at least one determined type of entity extraction may be performed on the input data, and at least one entity may be extracted from the input data. At least one replacement strategy may be determined from a plurality of replacement strategies for the at least one extracted entity. Further, the at least one determined replacement strategy may be applied to the at least one extracted entity to generate masked data.

Abstract: In some examples, structure-based multi-intent email classification may include receiving an email thread that includes a plurality of emails including an email that is to be classified, and identifying, for the email thread, a process associated with the email thread, Based on the process associated with the email thread and for each sentence of the email that includes a plurality of sentences, a corresponding classifier may be determined from a plurality of classifiers, and applied to each sentence of the email to generate classified sentences. At least one entity may be extracted from each of the classified sentences of the email. Based on the at least one extracted entity, the email may be classified.

Abstract: An Artificial Intelligence (AI) based transaction data processing and reconciliation system analyzes transaction data of different accounts to determine anomalous transactions, tagged transactions with Required Adjustments tag (R-tag), or aging transactions. Different Artificial intelligence (AI) based models are trained to produce corresponding risk scores that enable the determinations. Those transactions having low-risk scores are automatically reconciled whereas transactions having higher risk scores can be flagged for further review. Furthermore, the accounts corresponding to the transactions are also analyzed via different AI-based account-level models to identify accounts that can be R-tagged and/or accounts that are at the risk of being de-certified. Those accounts with higher risk scores can be flagged for further review while accounts with lower risk scores can be automatically certified.

Abstract: A system maintains a knowledge layout to support the building of event and analytics models in parity. The system uses the event models to provide a snapshot of the relevant conditions present when a challenge event occurs. The system uses the analytics models to select one or more actions (which may include robotic tasks) to respond to the challenge condition. In some cases, the system may render continued response compulsory until a successful response to the challenge event is achieved.

Abstract: A system may execute a pipelined multiple-tier test stack to support migration of computing resources via a migratory data stream. Via the pipelined multiple-tier test stack, the system may perform extract, transform, and load operations on the migratory data stream. The extract, transform, and load operations may be used to identify applications that may undergo testing. At a generation tier of the pipelined multiple-tier test stack, the system may generate test scripts, which may be used to test the application. The tests may be validated by the system via a validation tier of the pipelined multiple-tier test stack. To govern the operations, the pipelined multiple-tier test stack may rely on a multi-point reference data model.