Capital One Services, LLC

Christopher McDaniel

Matthew Louis Nowak

Michael Anthony Young, Jr

Systems and methods are disclosed herein for training machine learning models using precision data based on movement and timing of data collection. The system trains the machine learning model to predict object locations in an environment. The training data includes location data, timing data, and motion data, collection of which is triggered by a user input indicating that a particular object was located. The system generates precision parameters for the locations by assigning initial values to entries within the training data and may lower precision parameters based on the timing data indicating that an object was located faster than a threshold time or based on the motion data indicating that a rate of motion exceeded a threshold rate when a corresponding object was located. The system may update the training data with the lowered precision parameters and train the machine learning model to predict the object locations within the environment.

Training machine learning models based on movement and timing data

A method includes a system for improving machine-learning-based resource allocation by calibrating resource-related sentiments used to configure a dialogue generation model and updating a prior sentiment based on a response to a generated dialogue item, including a set of processors. Embodiments may also include a non-transitory, machine-readable media storing program instructions that, when executed by the set of processors, performs operations including retrieving a historical record associated with a user and a first natural language input provided by the user for a resource. Embodiments may also include determining, with a first machine learning model, an intermediate sentiment score based on the first natural language input. Embodiments may also include modifying, with the first machine learning model, the intermediate sentiment score based on the historical record to produce a new sentiment score.

Distributed active learning in natural language processing for determining resource metrics

Methods and systems are described herein for a resource allocation system. The resource allocation system may obtain a corresponding quantity of resources (e.g., memory, processor, storage, etc.) needed to be allocated for each resource class (e.g., for a given performance class) for a particular time period (e.g., for one month). Furthermore, the resource allocation system may track allocation of each class of resources and may predict that some classes of resources will be oversubscribed. Based on the prediction, the resource allocation system may, using a machine learning model, identify supplemental classes for each resource class predicted to be oversubscribed and generate a warning when a resource of a supplemental class is predicted to be used.

Dynamically adjusting resource allocation

In some embodiments, a computing system may monitor authentication input and modify authentication requirements based on detection of user-specific input errors. The computing system may use machine learning or other techniques to detect whether an incorrect authentication input corresponds to a common input mistake of a user. If the incorrect authentication input does correspond to a common input mistake of the user, a computing system may modify one or more authentication requirements to make the authentication process easier for the user.

Authentication based on detection of user-specific authentication input errors

Methods and systems that use a plurality of machine learning models to both monitor user-generated data entries corresponding to differences in network traffic that may be evidence of a disruption and determine severity levels based on: (i) current and historic differences in average network traffic over the plurality of communication networks; (ii) current and historic user-generated data entries; and (iii) labeled severity levels for historic differences in average network traffic over the plurality of communication networks.

Methods and systems for determining severity of disruptions in communication networks in non-homogenous environments

Disclosed herein are system, method, and computer program product embodiments for machine learning systems to predict real-time productivity changes based on prospective scheduling. A productivity predictive model is trained by a machine learning engine with meeting and productivity training data, wherein the productivity predictive model includes one or more algorithms to select a future productivity change based on a future schedule. The system receives a current schedule and current productivity measurements of a user, receives a scheduling request for the user, predicts a future productivity change and displays a graphic to a user revealing the future productivity change of the user based on accepting the scheduling request.

System and method for meeting volume optimizer

Aspects described herein may allow displaying of augmented reality content items associated with selected vehicle models, as well as price or budget information associated with the displayed vehicle to facilitate the user to make purchasing or financing decisions. For example, a computing device may detect a plurality of physical anchors attached to a vehicle husk and determine location information for each of the plurality of physical anchors. The computing device may receive one or more augmented reality (AR) content items corresponding to one or more vehicle features for the selected vehicle model and display via an AR interface, the one or more AR content items positioned relative to the vehicle husk based on the location of each of the plurality of physical anchors, as well as a price associated with the selected vehicle model having the one or more vehicle features.

Augmented reality vehicle display systems

Methods and systems are described herein for generating vehicle profiles for detected vehicles based on engine sound recordings. Based on those vehicle profiles, an enterprise is enabled to generate a user profile for customers. To generate the vehicle profile, a vehicle profiling system may be used. The vehicle profiling system may receive sound data with range information. The vehicle profiling system may input the sound data into a trained machine learning model and receive vehicle model information for the sound data. Based on the output, the profiling system may retrieve metadata associated with the vehicle model and generate a profile based on the metadata.

Growing community of inventors

Glen Allen, VA, United States of America

Christopher McDaniel