Abstract: A device may receive real time telecommunications data associated with a telecommunications network, and may select a first machine learning model from a first plurality of machine learning models based on the real time telecommunications data. The device may select a second machine learning model from a second plurality of machine learning models based on the real time telecommunications data. The device may process, in a first stage, the real time telecommunications data, with the first machine learning model, to determine a probability score indicating whether a customer technical problem telephone call will occur. The device may process, in a second stage and based on the probability score satisfying a threshold, the real time telecommunications data, with the second machine learning model, to determine a category associated with the customer technical problem telephone call, and may perform one or more actions based on the category.

Abstract: An authentication and applications access system provides access to a plurality of backend applications via a social media application installed on a user device. Metadata associated with a request to access one of the plurality of backend applications is initially extracted. The metadata is used to authenticate the request via a plurality of validation steps. Upon authentication, the information from the request is provided to the backend application to receive the results responsive to the request. Any sensitive data included in the results is suppressed via data substitution steps from the transmission to the user device. The output from the applications access system with the sensitive data occluded is provided for display on a social media user interface (UI) on a user device.

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: Methods, systems, and apparatus for authenticating and authorizing users using quantum key distribution through segmented quantum computing environments. In one aspect, a method includes receiving a first and second plaintext data input from a first party and from a second party, respectively; applying a quantum computation translation operation to the first and second plaintext data inputs to generate a corresponding first sequence of quantum computations and a second sequence of quantum computations; implementing the first and second sequence of quantum computations in a first and second segmented quantum computing environment, respectively, to obtain a first and second sequence of measurement results; generating a first and second encryption key using the first and second sequence of measurement results, respectively, and an encrypted authorization token using the second encryption key; and sending the first encryption key to the first party, and the encrypted authorization token to the second party.

Abstract: In some examples, artificial intelligence based corpus enrichment for knowledge population and query response may include generating, based on annotated training documents, an entity and relation annotation model, identifying, based on application of the entity and relation annotation model to a document set that is to be annotated, entities and relations between the entities for each document of the document set to generate an annotated document set, and categorizing each annotated document into a plurality of categories. Artificial intelligence based corpus enrichment may include determining whether an identified category includes a specified number of annotated documents, and if not, additional annotated documents may be generated for the identified category that may represent a corpus.

Abstract: A system includes a multi-layer throughput optimization (TPO) stack to generate a token containing prescriptions for rightsizing database service throughput.

Abstract: Methods, systems, and apparatus for quantum random number generation. In one aspect, a method includes initializing N qubits in respective superposition states; computing a randomly selected oracle randomization function using i) the initialized N qubits and ii) multiple ancilla qubits, wherein the multiple ancilla qubits comprise a first ancilla qubit and one or more second ancilla qubits; performing a phase flip operation on the first ancilla qubit; computing an inverse of the randomly selected oracle randomization function using i) the N qubits and ii) the multiple ancilla qubits; performing a diffusion operation on the N qubits; and measuring the N qubits and providing data representing the measured states of the N qubits as N random bits.

Abstract: A multi-layer elastic requisition stack may generate pool requisition tokens for controlling requisition of pooled database-compute resources. The elastic requisition stack may determine candidate databases for inclusion in elastic pools by analyzing historical utilization data and generating predicted utilization data. Based on the historical and predicted utilization data, the elastic requisition stack may determine multiplexing characteristics for the candidate databases and complement factors among the databases. The elastic requisition stack may compare unpooled database performance to pooled database performance to determine whether to pool the candidate databases.

Abstract: In some examples, collective application portfolio migration control may include determining, for a plurality of applications that are to be clustered for migration to a cloud environment, a coupling coefficient that represents a type of coupling between pairs of applications from the plurality of applications, a proximity coefficient that represents application proximities, and a connectedness coefficient that represents application connections. A combined application relatedness coefficient may be determined based on the coupling coefficient, the proximity coefficient, and the connectedness coefficient. A portfolio graph may be generated based on the combined application relatedness coefficient to generate migration application clusters to duster the plurality of applications. Migration of the plurality of applications to the cloud environment may be controlled based on the migration application clusters.

Abstract: This application discloses a system and method for federated collaborative machine learning model development using local training datasets that are not shared. An adaptive and evolutionary approach is used to select local training nodes that are most fit from one training round to the next training round to optimize an overall cost and performance function for the federated learning, to cross-over model architecture between local training nodes, and to perform model architecture mutation within local training nodes. The local training nodes are further clustered to account for the inhomogeneity in the local datasets. Such adaptive, evolutionary, and collaborative federated learning thus provides cost-effective and high-performance model development.

Abstract: This specification relates to methods, and systems for stakeholder and impact discovery. One of the methods includes receiving a knowledge representation model indicating at least a first stakeholder and a first impact; determining an impact model based at least in part on the knowledge representation model; receiving distributed sensor data; and determining at least a second impact based at least in part on the impact model and the distributed sensor data.

Abstract: In some implementations, a device may receive release data identifying new releases associated with cloud providers. The device may receive customer data associated with customers of the cloud providers. The device may receive interest data identifying interests of the customers. The device may filter the release data and may process the filtered release data and taxonomy data identifying historical release data, with a model, to generate classification data identifying classifications of the release data. The device may process the filtered release data, the classification data, and the customer data, with a model, to identify a set of release data that is relevant for each customer, and to generate sets of release data for the customers. The device may identify additional data of the filtered release data that is relevant for each of the customers. The device may supplement the sets of release data with the additional data.

Abstract: Systems and methods for evaluating reliability of a model are disclosed, including a processor that may include a data augmentor and a model evaluator. The data augmentor may receive a task data pertaining to information related to a pre-defined task to be performed by the model. The data augmentor may augment the task data to obtain an augmented aspect data. The model evaluator may evaluate a trained model based on the augmented aspect data to obtain aspect evaluation metrics. The model may be an artificial intelligence (AI) model that may be trained using the task data. The evaluation may enable to assess performance of the trained model by computing a performance score based on the aspect evaluation metrics. The performance score may help evaluate the reliability of the model in a pre-defined domain.

Abstract: In some examples, stylization-based floor plan generation may include receiving, for a floor plan that is to be generated, a layout graph for which user constraints are encoded as a plurality of room types. The user constraints may include spatial connections therebetween. Based on the layout graph, embedding vectors may be generated for each room type of the plurality of room types. Bounding boxes and segmentation masks may be determined for each room embedding from the layout graph, and based on an analysis of the embedding vectors for each room type of the plurality of room types. A space layout may be generated by combining the bounding boxes and the segmentation masks. A floor plan may be generated based on an analysis of the space layout and an input boundary feature map.

Abstract: In some implementations, a device may receive, from a monitoring device, telecommunications data associated with a telecommunications network. The device may train a plurality of machine learning models with the telecommunications data to generate a plurality of trained machine learning models. The device may generate accuracy scores for the plurality of trained machine learning models based on training the plurality of machine learning models. The device may select an optimum machine learning model based on several indicators, such as the accuracy, precision, and/or the like. The device may provide the optimum machine learning model to the monitoring device associated with the telecommunications network.

Abstract: A system may facilitate a distributed ledger technology (DLT) record based (for example, blockchain-based) ballot organization. A node configured to support an organizer role may generate a ballot that designates answers, and in some cases, conditions for valid vote-value transfers. The organizer may distribute vote-value to one or more voters. The voters may then commit portions (including null portions) of the received vote value to answers using committed tokens configured to bind the voter to a particular vote-value without divulging the particular vote value while in a cryptographic form.

Abstract: Embodiments of the present disclosure provide centralized and coordinate learning techniques for identifying malicious e-mails while maintaining privacy of the analyzed e-mails of different organizations. One or more models may be generated and configured to construct feature sets that may be used to characterize e-mails as malicious or safe. Feedback associated with one or more models trained by a first organization (and other organizations) may be shared with a modelling device to modify parameters of the one or more models, where the modified parameters are configured to improve identification of malicious e-mail threats. The feedback provided by the first organization may not include e-mails received by the first organization, thereby enabling the privacy of the e-mails received by the first organization to be maintained in an confidential manner even though the updated parameters may be shared with a second organization.

Abstract: Methods and system for recommending components to a user. Implementations are directed to receiving, from a user, a user query for a design recommendation, the user query comprising a plurality of terms; determining, from the plurality of terms, a user intent including at least one query-derived design function and not including a named component for the design recommendation; receiving additional contextual information for the design recommendation, wherein the additional contextual information comprises a plurality of action attributes for the at least one query-derived design function; determining, from a database, a plurality of design recommendations, wherein each design recommendation comprises a respective recommended component and a plurality of recommended component actions; selecting, from the plurality of design recommendations, a subset of design recommendations; and providing, to the user, the subset of design recommendations.

Abstract: A multi-layer serverless sizing stack may determine a compute sizing correction for a serverless function. The serverless sizing stack may analyze historical data to determine a base compute allocation and compute buffer range. The serverless sizing stack may traverse the compute buffer range in an iterative analysis to determine a compute size for the serverless function to support efficient computational-operation when the serverless function is instantiated.

Abstract: Systems and methods for attribute-based modelling are disclosed. A system includes an attribute-based decomposition engine, which when executed using a processor, causes the engine to retrieve one or more product attributes associated with each of a set of products, an importance of the product attributes being determined based on the product sales data, product data, product parameters, and financial data associated with product. The attribute-based decomposition engine using the processor establishes, for a set of products, a relationship between a retrieved one or more product attributes and product sales associated with product, based on implementation of a non-parametric machine learning (ML) modeling on a data model. The attribute-based decomposition engine quantifies contribution of each product attribute on product sales based on an established relationship and a game theoretic framework.