Abstract: Method, data processing system, and computer-readable storage media for responding to a user query. Receiving query from user, query pertaining to request for information. Based on query, generate prompts by masking sensitive information in query. Receive responses from foundation models in response to inputting prompts. Based on responses, generate common result set. By validating common result set with sensitive information, generate response. By supplementing response with sensitive information, generate user response. Providing user response in response to query to the user.

Abstract: The present invention relates to pharmaceutical formulations of antibodies and antigen-binding fragments against human programmed death receptor-1 (PD-1)/programmed death receptor Ligand 1 (PD-L1), and method for preparing the same. The disclosed formulations stabilizes anti-PD1/anti-PD L1 antibody from lower to higher concentrations rendering it suitable for different modes of administration (subcutaneous/intravenous).

Abstract: An Artificial Intelligence (AI) based document processing and validation system identifies anomalies such as errors, fraud, and duplicates of received documents and enables automatic actions for valid documents using machine learning (ML) techniques. The received documents are processed for determining probabilities for errors, fraud, and duplicates. A validation worklist is generated with the documents arranged in descending order of the probabilities and invalid documents with higher probabilities are flagged for review while the valid documents with lower probabilities are further processed for the execution of automatic actions. The feedback from the invalid document review is used to further train the models in determining the probabilities.

Abstract: A device receives historical data associated with multiple cloud computing environments, trains one or more machine learning models, with the historical data, to generate trained machine learning models that generate outputs, and trains a model with the outputs to generate a trained model. The device receives particular data, associated with a cloud computing environment, that includes data identifying usage of resources associated with the cloud computing environment, and processes the particular data, with the trained machine learning models, to generate anomaly scores indicating anomalous usage of the resources associated with the cloud computing environment. The device processes the one or more anomaly scores, with the trained model, to generate a final anomaly score indicating anomalous usage of at least one of the resources associated with the cloud computing environment, and performs one or more actions based on the final anomaly score.

Abstract: A device may receive a request for a schedule and scheduling constraints to utilize when generating the schedule, and may process, based on the request, a first portion of the scheduling constraints and first optimization variables, with a first optimization solver model, to generate capacity data for the schedule. The device may process the capacity data, a second portion of the scheduling constraints, and second optimization variables, with a second optimization solver model, to generate shift assignment data for the schedule, and may process the shift assignment data, a third portion of the scheduling constraints, and third optimization variables, with a third optimization solver model, to generate skill and task assignment data for the schedule. The device may generate the schedule based on the capacity data, the shift assignment data, and the skill and task assignment data, and may perform one or more actions based on the schedule.

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 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: An Artificial Intelligence (AI) based document processing and validation system identifies anomalies such as errors, fraud, and duplicates of received documents and enables automatic actions for valid documents using machine learning (ML) techniques. The received documents are processed for determining probabilities for errors, fraud, and duplicates. A validation worklist is generated with the documents arranged in descending order of the probabilities and invalid documents with higher probabilities are flagged for review while the valid documents with lower probabilities are further processed for the execution of automatic actions. The feedback from the invalid document review is used to further train the models in determining the probabilities.

Abstract: A device may receive historical cloud data associated with resources of a cloud computing environment, and may receive historical customer data associated with requested resource usage by customers of the cloud computing environment. The device may determine a usage growth profile based on the historical cloud data and the historical customer data, and may determine, based on the historical cloud data and the historical customer data, usage deviation data indicating deviations between actual and planned resource usage. The device may train a model, with the usage growth profile and the usage deviation data, to generate a trained model, and may receive a request for new resource usage by a customer associated with the cloud computing environment. The device may process the request for the new resource usage, with the trained model, to generate projected resource usage data, and may perform actions based on the projected resource usage data.

Abstract: A multi-layer compute sizing correction stack may generate prescriptive compute sizing correction tokens for controlling sizing adjustments for computing resources. The input layer of the compute sizing correction stack may generate cleansed utilization data based on historical utilization data received via network connection. A prescriptive engine layer may generate a compute sizing correction trajectory detailing adjustments to sizing for the computing resources. Based on the compute sizing correction trajectory, the prescriptive engine layer may generate the compute sizing correction tokens that that may be used to control compute sizing adjustments prescriptively.

Abstract: A device may receive a computing resource request. The computing resource request may be related to allocating computing resources for a job. The device may process the computing resource request to identify a set of parameters related to the computing resource request or to the job. The set of parameters may be used to determine an allocation of the computing resources for the job. The device may utilize multiple machine learning models to process data related to the set of parameters identified in the computing resource request. The device may determine the allocation of the computing resources for the job based on utilizing the multiple machine learning models to process the data. The device may generate a set of scripts related to causing the computing resources to be allocated for the job according to the allocation. The device may perform a set of actions based on the set of scripts.

Abstract: A multi-layer compute sizing correction stack may generate prescriptive compute sizing correction tokens for controlling sizing adjustments for computing resources. The input layer of the compute sizing correction stack may generate cleansed utilization data based on historical utilization data received via network connection. A prescriptive engine layer may generate a compute sizing correction trajectory detailing adjustments to sizing for the computing resources. Based on the compute sizing correction trajectory, the prescriptive engine layer may generate the compute sizing correction tokens that that may be used to control compute sizing adjustments prescriptively.

Abstract: A device receives historical data associated with multiple cloud computing environments, trains one or more machine learning models, with the historical data, to generate trained machine learning models that generate outputs, and trains a model with the outputs to generate a trained model. The device receives particular data, associated with a cloud computing environment, that includes data identifying usage of resources associated with the cloud computing environment, and processes the particular data, with the trained machine learning models, to generate anomaly scores indicating anomalous usage of the resources associated with the cloud computing environment. The device processes the one or more anomaly scores, with the trained model, to generate a final anomaly score indicating anomalous usage of at least one of the resources associated with the cloud computing environment, and performs one or more actions based on the final anomaly score.

Abstract: A device may receive historical cloud data associated with resources of a cloud computing environment, and may receive historical customer data associated with requested resource usage by customers of the cloud computing environment. The device may determine a usage growth profile based on the historical cloud data and the historical customer data, and may determine, based on the historical cloud data and the historical customer data, usage deviation data indicating deviations between actual and planned resource usage. The device may train a model, with the usage growth profile and the usage deviation data, to generate a trained model, and may receive a request for new resource usage by a customer associated with the cloud computing environment. The device may process the request for the new resource usage, with the trained model, to generate projected resource usage data, and may perform actions based on the projected resource usage data.

Abstract: A device may receive data related to operations of a plurality of managed devices. The device may determine, after receiving the data, a multi-entity profile for the data. The device may determine, using the multi-entity profile, a set of sub-models for the data after determining the multi-entity profile. The set of sub-models may be associated with processing the data in a contextualized manner. The device may generate a model based on the set of sub-models. The device may perform one or more actions related to the plurality of managed devices or the at least one alert based on respective scores associated with the plurality of managed devices after generating the model.

Abstract: A device may receive invoice data related to multiple invoices, requisition data related to multiple requisitions, or project data related to multiple projects. The device may process the data using a feature extraction engine to identify features of the data. The device may process the data using a transformation engine to reduce a size of the data. The device may process the data using a set of machine learning models. The device may generate a set of recommendations related to at least one of: categorizing each of the multiple invoices, each of the multiple requisitions, or each of the multiple projects into one or more of multiple categories, identifying a set of possible suppliers for each of the multiple requisitions or each of the multiple projects, or identifying a set of similar projects for each of the multiple projects. The device may perform one or more actions.

Abstract: A device may receive utility usage data for multiple buildings across multiple locations. The device may process the utility usage data using a first set of models associated with performing at least one of: an intra-building anomaly detection for the utility usage data, a first grouping of the utility usage data based on characteristics of the utility usage data, or a second grouping of the utility usage data based on the multiple locations. The device may process first output from the first set of models using a second set of models associated with pre-processing the first output in association with identifying anomalies in the first grouping or in the second grouping. The device may process the first output and second output from the second set of models using a super model associated with identifying the anomalies. The device may perform, based on the score, one or more actions.

Abstract: A multi-layer compute sizing correction stack may generate prescriptive compute sizing correction tokens for controlling sizing adjustments for computing resources. The input layer of the compute sizing correction stack may generate cleansed utilization data based on historical utilization data received via network connection. A prescriptive engine layer may generate a compute sizing correction trajectory detailing adjustments to sizing for the computing resources. Based on the compute sizing correction trajectory, the prescriptive engine layer may generate the compute sizing correction tokens that that may be used to control compute sizing adjustments prescriptively.

Abstract: A device may receive data related to operations of a plurality of managed devices. The device may determine, after receiving the data, a multi-entity profile for the data. The device may determine, using the multi-entity profile, a set of sub-models for the data after determining the multi-entity profile. The set of sub-models may be associated with processing the data in a contextualized manner. The device may generate a model based on the set of sub-models. The device may perform one or more actions related to the plurality of managed devices or the at least one alert based on respective scores associated with the plurality of managed devices after generating the model.

Abstract: A device may receive a computing resource request. The computing resource request may be related to allocating computing resources for a job. The device may process the computing resource request to identify a set of parameters related to the computing resource request or to the job. The set of parameters may be used to determine an allocation of the computing resources for the job. The device may utilize multiple machine learning models to process data related to the set of parameters identified in the computing resource request. The device may determine the allocation of the computing resources for the job based on utilizing the multiple machine learning models to process the data. The device may generate a set of scripts related to causing the computing resources to be allocated for the job according to the allocation. The device may perform a set of actions based on the set of scripts.