Abstract: A device may determine an association between a second set of parameters and a third set of parameters using a pseudoinversion network and a multiple regression procedure. The device may determine semantic embeddings based on a set of semantic descriptions of the second set of parameters. The device may determine a semantic similarity between parameters of the second set of parameters based on the semantic embeddings. The device may determine a consistency error based on the semantic similarity. The device may generate, using a regression-based learning model technique, a matrix representing an association between the second set of parameters and the third set of parameters based on the association and the consistency error. The device may perform an action based on the matrix.

Abstract: A device receives priority data identifying priorities relevant to a configuration of an application and receives feature data identifying features related to the priorities. The device identifies technology services based on a machine learning-driven analysis of the priorities and features, and includes data identifying the technology services as part of the reference architecture. The device provides data identifying the reference architecture for display via an interface, and receives data identifying technology services that have been selected by a user. The device updates scores associated with the reference architecture based on the selected technology services. A subset of the scores may be updated to reflect one or more degrees to which one or more cloud service providers offer the selected technology services. The device provides data identifying the updated scores for display via the interface to allow the scores to be used to select a particular cloud service provider.

Abstract: A system includes a security controller located within a central-zone in communication with a provisioned agent operating on an edge-zone device. The security controller may implement controller-blind security control on the edge-zone device by making security authorization determinations using a secure-operation confidence analysis performed by the provisioned agent. The provisioned agent, operating within the edge-zone, may have access to un-sanitized data, which may be unavailable to the security controller in the central-zone. The provisioned agent may access condition-descriptors via a secure-operation confidence assignment matrix. Using the condition-descriptors, the provisioned agent determine feedback, which may include a secure-operation confidence coefficient, based on the un-sanitized data to which the security controller is blind.

Abstract: Implementations include providing a security rating and a data criticality value of one or more transactions, the one or more transactions to be recorded to a blockchain, and the blockchain being of a blockchain network, selecting a consensus protocol, the consensus protocol selected from a set of consensus protocols, and the consensus protocol selected based on the security rating and the data criticality value, defining a set of consensus nodes, the set of consensus nodes including nodes from one of a super node pool and a weak node pool, and executing, by the set of consensus nodes, the consensus protocol to record the one or more transactions to the blockchain.

Abstract: A device may receive image data that includes an image of a document and lexicon data identifying a lexicon, and may perform an extraction technique on the image data to identify at least one field in the document. The device may utilize form segmentation to automatically generate label data identifying labels for the image data, and may process the image data, the label data, and data identifying the at least one field, with a first model, to identify visual features. The device may process the image data and the visual features, with a second model, to identify sequences of characters, and may process the image data and the sequences of characters, with a third model, to identify strings of characters. The device may compare the lexicon data and the strings of characters to generate verified strings of characters that may be utilized to generate a digitized document.

Abstract: A device may receive source code from a source data structure, and may receive information associated with a target data structure. The device may analyze the source code to extract statements, and may utilize natural language processing on the statements to identify functions and keywords associated with the source data structure. The device may train a machine learning model with the functions and the keywords to generate a trained machine learning model, and may process the information associated with the target data structure, with the trained machine learning model, to transform a source query to a target query compatible with the target data structure. The device may process the target query, with a neural network model, to generate an optimized target query, and may cause data from the source data structure to be migrated to the target data structure based on the optimized target query.

Abstract: Implementations are directed to methods for detecting and identifying advanced persistent threats (APTs) in networks, including receiving first domain activity data from a first network domain and second domain activity data from a second network domain, including multiple alerts from the respective first and second network domains and where each alert of the multiple alerts results from one or more detected events in the respective first or second network domains. A classification determined for each alert of the multiple alerts with respect to a cyber kill chain. A dependency is then determined for each of one or more pairs of alerts and a graphical visualization of the multiple alerts is generated, where the graphical visualization includes multiple nodes and edges between the nodes, each node corresponding to the cyber kill chain and representing at least one alert, and each edge representing a dependency between alerts.

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage medium, for implementation of secret superposition protocols. In one aspect a method includes, performing, by a sender party, quantum operations on one or more qubits, comprising preparing, according to a predetermined secret superposition protocol, one or more qubits in respective uniform superposition quantum states; transmitting, by the sender party, to a recipient party, and through a secure channel, data indicating use of the predetermined secret superposition protocol; and transmitting, by the sender party and to the recipient party, one or more of the qubits, wherein the recipient party performs one or more measurements on the qubits to verify use of the predetermined secret superposition protocol.

Abstract: A device may receive assessment scores for a candidate associated with an entity and performance data identifying performance metrics and time periods associated with existing members of the entity. The device may process the assessment scores and the performance data, with an attrition model, to identify attrition scores for the candidate and confidences of the attrition scores, and may calculate a final attrition score based on the attrition scores. The device may process the assessment scores and the performance data, with a performance model, to identify performance scores for the candidate and confidences of the performance scores, and may calculate a final performance score based on the performance scores. The device may calculate an overall score based on the final attrition score and the final performance score, and may perform one or more actions based on the overall score.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing intelligent extraction of information from a document. A computing module receives input data representing an image of a document. The module also receives context data for the document. The context data includes parameters that are descriptive of the document in the image. The module processes the input data and the context data to determine a complexity value that characterizes a level of complexity in identifying information to be extracted from the document. The system selects a machine-learning model to use in extracting information from the document. The model is selected based on the complexity value and from multiple candidate models. The system extracts information from the document using the selected model, including converting a portion of the image of the document that shows typed or handwritten text into a digitized text string.

Abstract: Embodiments of the present disclosure provide systems and methods for controlling a manufacturing process in a manner that protects sensitive information from misuse by different entities involved in the manufacturing process. According to the present disclosure, a blueprint providing information regarding subcomponents of a product to be manufactured may be provided to a synthesizer device. The synthesizer device may engage in two-party computation with IP providers to generate a set of machine commands, which may be encrypted, and then provide a message including the set of machine commands to a manufacturer device. The manufacturer device may obtain authorization from the IP provider(s) based on the message, where the authorization may enable the manufacturer device to configure a manufacturing process in accordance with the set of machine commands to manufacture the subcomponents of the product.

Abstract: Customer relationship management (“CRM”) method implemented in a computer system, including a lead knowledge engine in communication with a plurality of tele-agent stations. The lead knowledge engine includes a semantic graph database with a knowledge graph and a dynamic profiling module configured to identify query tele-agents via tele-agent dashboards to receive internal sales information indicative of product product/service interest and tele-agent experience and expertise. The lead knowledge engine is further configured to query a sales analytics engine and receive external sales information to identify product/service interest and generate target-lead profiles. The lead knowledge engine automatically ranks tele-agents and creates inside sales or expert support teams to support particular products or services, parses leads, and updates tele-agent dashboards.

Abstract: Implementations include processing a set of documents using an auto-encoder to provide a first sub-set of documents, the first sub-set of documents including electronic documents with a relatively high likelihood of providing true positives in an auditing process, processing a sub-set of documents using a set of auto-generated rules to provide a second sub-set of documents, the second sub-set of documents including electronic documents with a relatively high likelihood of providing false positives in an auditing process, and defining a master set of documents for the auditing process based on the sub-set of documents, the first sub-set of documents, and the second sub-set of documents, the master set of documents including at least a portion of the sub-set of documents, and at least a portion of the first sub-set of documents, and being absent the second sub-set of documents.

Abstract: The invention concerns a query response device comprising: an input adapted to receive user queries; a memory (106) adapted to store one or more routing rules; one or more live agent engines (116) configured to support interactions with one or more live agents; one or more virtual assistant engines (120) configured to support interactions with one or more virtual assistants instantiated by an artificial intelligence module (103); and a routing module (104) coupled to said live agent engines and to said virtual assistant engines, the routing module comprising a processing device configured: to select, based on content of at least a first user message from a first user relating to a first user query and on said one or more routing rules, a first of said live agent engines or a first of said virtual assistant engines; and to route one or more further user messages relating to the first user query to the selected engine.

Abstract: A system maintains a knowledge layout to support the analysis of active events and determination of epicenter and aftershock nodes via an event reach stack. At an input layer of the event reach stack, the system may receive active event data. At a semantic layer, the system may parse the active event data to determine event phrases. Based on the event phrases, the system may identify epicenter nodes directly affected by the active event. At an analytic model layer, the system may successively determine aftershock nodes by traversing the knowledge layout outward from the epicenter nodes. The system then directs the response to the active event to the aftershock and epicenter nodes, via action at a focus response layer of the event reach stack.

Abstract: A model management tool is provided for performing analysis on data in a knowledge graph representation and enforcing data standardization to increase performance when reusing existing models to develop new artificial intelligence applications.

Abstract: A system and method for hierarchical, clustered reinforcement learning is disclosed. A plurality of subject objects may be obtained, and a plurality of clusters of the subject objects may be determined. Clustered reinforcement learning may be performed on each cluster, including training a respective cluster agent for the each cluster. A first cluster of the plurality of clusters may be selected for revision based on selection criteria. After selection of the selected first cluster, individual reinforcement learning may be performed on each individual subject object included in the selected first cluster, including training a respective individual agent for the each individual subject object. An action may be controlled based on a result of the hierarchical, clustered reinforcement learning.

Abstract: Embodiments of the present disclosure leverage distributed ledger technologies to exert user-centric control over data shared with third party service providers. User access provider (UAP) devices manage user-configured permissions and metadata that control access to user data by the third party service providers. Permissions may enable service providers to access, write, and share user data with other service providers having appropriate permissions. Users may provide data to various service providers as they interact with services supported by the platform and as the data is received it may be validated and then stored on the distributed ledger. Data may be periodically synchronized across different service provider nodes responsible for maintaining the distributed ledger to ensure consistency with respect to each user's data.

Abstract: This document described digital decoupling architectures that enable existing computing systems to run in parallel with new computing technologies. In some aspects, a method includes receiving, by a digital decoupling system and from a source computing system, one or more updated data sets that each include data that has been updated at the source computing system. A source data entry of a source table of a database of the digital decoupling system is updated based on each updated data set. In response to detecting the change to the source table, a target data entry that includes data of the updated source data entry is added to a target table of the database. An adapter module obtains the data of the target data entry and generates an event that specifies the data of the target data entry. The event is sent to one or more destination computing elements.

Abstract: Implementations include receiving two or more time-series data sequences representative of a target process executed within a physical environment, executing automated time-series process segmentation to provide a plurality of subsequence segments for each of the two or more time-series data sequences, each subsequence segment corresponding to a phase of the target process, processing the two or more subsequence segments using at least one time-series transformation to provide a feature data set for each subsequence segment, applying each feature data set to provide time-series models for anomaly detection and forecasting, respectively, each time-series model being provided as one of a recurrent neural network (RNN), a convolution neural network (CNN), and a generative adversarial network (GAN), determining anomaly scores based on the time-series models, and selectively providing an alert to one or more users, each alert indicating at least one anomaly and a respective probability.