IBM Patent Applications

POLYNOMIAL APPROXIMATION OF DEEP LEARNING MODELS

Granted: October 24, 2024
Application Number: 20240354562
An embodiment includes performing a dedicated training process on a non-polynomial neural network resulting in a trained polynomial neural network, where the training process includes performing a plurality of training iterations on the neural network, and performing, between the training iterations, loss processing that (i) minimizes a loss of the neural network and (ii) reduces a range of values to a non-polynomial layer (NPL) of the neural network. The embodiment estimates a range of…

AUTOMATED GENERATION OF TRAINING DATA FOR AN ARTIFICIAL-INTELLIGENCE BASED INCIDENT RESOLUTION SYSTEM

Granted: October 17, 2024
Application Number: 20240346306
An embodiment includes detecting incident data and resolution data in monitored data collected while monitoring an information technology (IT) environment. The embodiment correlates the incident data with the resolution data according to a detected change in health metrics data from the monitored data. The embodiment stores the correlated incident data and resolution data as a training dataset stored in a database and then trains a machine learning model using the training dataset. The…

COGNITIVE MANAGEMENT OF VIRTUAL MEETINGS

Granted: October 3, 2024
Application Number: 20240333543
An embodiment associates a virtual-meeting host designation with a first user. During the virtual meeting, the embodiment generates meeting context data that includes user characteristic data and meeting characteristic data. The embodiment uses the meeting context data to generate a predicted end time for the virtual meeting and predicts a meeting run-over condition indicative of the virtual meeting continuing past a scheduled end time by comparing the predicted end time and a scheduled…

OPTIMIZING USER RESEARCH AND OBJECT STRUCTURE OF WORKFLOWS

Granted: October 3, 2024
Application Number: 20240330829
Optimizing a user experience (UX) through improved efficiency of UX research includes using a processor to identify a candidate object, associated with parameters, for research. A current state of the candidate object is assessed by the processor based on the parameters. This assessment may include performing simulations, performed by the processor, on the candidate object using different combinations of the parameters. Research methods are selected, by the processor, from research…

MULTI-FEATURE RISK ANALYSIS

Granted: October 3, 2024
Application Number: 20240330815
An embodiment defines a risk model that generates a risk score for an asset based on a plurality of factors, including a first factor that is a first factor type and a second factor that is a second factor type. The model includes a plurality of associations, including a first association that associates a first factor weight with a specified significance of the first factor, and a second association that associates a second factor weight with a time-based metric of the second factor.…

SELECTIVE DATA RETENTION IN A GROUNDING BASED APPLICATION

Granted: October 3, 2024
Application Number: 20240330721
An embodiment includes configuring a grounding based application (GBA) structure comprising a plurality of layers, where the plurality of layers comprises a first layer and a second layer, the first layer having a first node that receives an input associated with a child node responsive to an input query, and the second layer having a second node that outputs a response to the input query. The embodiment also includes evaluating, using the GBA structure, a logical inference based on the…

ACCELERATION OF INFLIGHT DEPLOYMENTS

Granted: October 3, 2024
Application Number: 20240330327
Leveraging production deployments to accelerate inflight deployments in a computing environment. A component is extracted, which is identified in the production deployment. The identified, extracted component is analyzed to derive a set of data describing the identified, extracted component. A relationship between the data is built. The relationship is used to develop an enterprise-wide methodology that is utilized to accelerate development of an additional, inflight deployment by…

DYNAMIC MICROSERVICES MANAGEMENT AND CODE GENERATION

Granted: October 3, 2024
Application Number: 20240329944
A first function of a first microservice and a second function of a second microservice are derived from data of an application using a plurality of microservices. From the first function and the second function, an embodiment determines that the first microservice and the second microservice have above a threshold similarity with each other. An embodiment determines a set of differences between the first microservice and the second microservice. New source code of the application is…

FAST FILLING OF SOLID STATE DRIVES

Granted: October 3, 2024
Application Number: 20240329832
In one general embodiment, a computer-implemented method includes receiving specification of an amount of drive space in a solid state drive (SSD) to emulate, the specified amount being less than all of the drive space of the SSD. The SSD is formatted such that only a number of blocks that provides the specified amount of drive space are made available, and the other blocks are skipped. The available blocks are distributed substantially evenly across planes of the SSD. A presented amount…

MACHINE LEARNING MODEL RISK ASSESSMENT USING SHADOW MODELS

Granted: September 26, 2024
Application Number: 20240320541
Using data of a target machine learning model, a shadow model is generated. A predefined test is performed on the shadow model, the performing resulting in a first test result. A risk score comprising the first test result and a second test result is computed, the second test result obtained by performing a second predefined test using the data of the target machine learning model.

CROSSOVER SIMULATION AND CAUSATION DETECTION USING SIMULATION ENVIRONMENTS

Granted: September 26, 2024
Application Number: 20240320400
An embodiment includes identifying a first simulation and a second simulation such that the first simulation is within a threshold similarity of the second simulation. The embodiment generates a set of emergent simulations based at least in part on emergent hyperparameters, where the emergent hyperparameters are generated using the hyperparameters of the first and second simulations. The embodiment selects a subset of the set of emergent simulations according to a diversity metric and…

INTELLIGENT BOOKMARK CATEGORIZATION AND MANAGEMENT

Granted: September 26, 2024
Application Number: 20240320285
A method for efficiently managing bookmarks is disclosed. In one embodiment, such a method includes monitoring activities that occur in association with creating and maintaining bookmarks in an application such as a web browser. The method learns file structures and associated locations within the file structures into which bookmarks are categorized and saved. Based on this learning, the method creates a file structure template that corresponds to what has been learned. The method then…

REDUCING INFERENCE TIME PROCESSING DEEP LEARNING MODELS

Granted: September 26, 2024
Application Number: 20240320222
Various embodiments are provided herein for decreasing a central processing unit (CPU) inference time, thereby shortening processing time of a deep learning model for which run-time complexity is proportional to an output sequence length. A compacted sequence is developed that is used to train the deep learning model. An output of the trained model becomes the compacted sequence on which a post-processing method operates to create an uncompacted version of a predicted sequence.

MINIMIZATION OF INDIVIDUAL FILE-LEVEL BACKUP FOR POLICY-BASED ARCHIVAL AND EXPIRATION

Granted: September 26, 2024
Application Number: 20240320102
Embodiments for minimizing creations of individual file backups in a safeguarded copy environment include determining, by one or more processors, a policy-based requirement exists that a backup copy of a file must be maintained in storage for a predefined time period. The one or more processors search and determine that one or more immutable point-in-time copies currently residing in storage include a current backup copy of the file. Responsive to determining that the one or more…

Dynamic Container Resizing

Granted: September 26, 2024
Application Number: 20240320057
Using a regression analysis on first telemetry data of a container, an embodiment identifies a set of features predicting a resource usage of the container. The container comprises an executing application. Using a time series analysis of data of the set of features, an embodiment predicts a future resource usage of the container at a future time. The data of the set of features is extracted from second telemetry data of the container. At the future time according to the future resource…

COMBINED CLASSICAL/QUANTUM PREDICTOR EVALUATION WITH MODEL ACCURACY ADJUSTMENT

Granted: September 12, 2024
Application Number: 20240303518
Using a model executing on a classical processor, a set of classical features is scored. The scored set of classical features is divided into a set of feature groups, a number of classical features in a group determined according to a qubit capability of a quantum processor. Using a model executing on the quantum processor and a group of the scored set of classical features, a set of quantum features is scored. The score of a quantum feature is adjusted according to an accuracy of the…

GENERATING AN AI CONVERSATION MODEL USING API TEST DATA

Granted: September 5, 2024
Application Number: 20240296292
An embodiment includes generating an intent representative of a verb identified in application programming interface (API) test data associated with an API test case. The embodiment also generates a first entity representative of a first noun identified in the API test data and a second entity representative of a second noun identified in the API test data. The embodiment identifies the intent as being associated with a relationship between the first and second entities in the API test…

CLIPBOARD BASED SEARCH TERM PREDICTION

Granted: September 5, 2024
Application Number: 20240296176
Using a probability distribution and a search result history, a probability of selecting a specified number of relevant samples and a specified number of irrelevant samples from a set of contents is computed, each content in the set of contents comprising a content copied to a first system clipboard of a first device. Using the probability distribution, each content in the set of contents is weighted. Using the weighted set of contents, a set of predicted searches is generated. The set…

OPTIMIZING MEMORY MANAGEMENT USING MEMORY ACCESS HEATMAPS

Granted: August 29, 2024
Application Number: 20240289021
Embodiments of the present disclosure provide an enhanced system and methods for optimizing data placement in a memory hierarchy. A disclosed non-limiting computer-implemented method configures a counter block comprising access frequency counters mapped into an application memory space, and configures a counter map, where each entry in the counter map associates an application-defined memory region with the access frequency counters of the counter block. A memory controller identifies a…

MIGRATION PLANNING WITH AUTOMATED DISCOVERY OF SOURCE ASSETS

Granted: August 29, 2024
Application Number: 20240289308
An embodiment includes generating source inventory data representative of information technology assets associated with a source site, the source site comprising information technology infrastructure of an enterprise, the information technology assets comprising a source application database and a source peripheral entity associated with the source application database. The embodiment determines a target platform for migrating the source application database and determining a degree of…