公开(公告)号：US11954177B2

公开(公告)日：2024-04-09

申请号：US17101258

申请日：2020-11-23

Applicant: Verizon Patent and Licensing Inc.

Inventor： Kushal Singla ,  Sidakpreet Singh Chawla ,  Ebenezer Bardhan ,  Pooja Khivesara

IPC: H04L12/725 ,  G06F18/20 ,  G06F18/2431

CPC classification number: G06F18/2431 ,  G06F18/285

Abstract: Systems and methods described herein provide an online constraint optimizing service that evaluates user requests and inquiries for telecommunications services in the context of a real-time constraint-based analysis. According to an implementation, a network device receives a function for an analytic event and a constraint. The function applies different user attributes for a telecommunications network. The network device generates a training data set using offline constrained optimization of the function. The network device develops a predictive model for utilization of network resources in the telecommunications network using the training data set. The network device receives a user request that corresponds to the analytic event addressed by the predictive model and conducts an online prescriptive analysis using the predictive model. The network device optimizes allocation of the network resources to the user based on the prescriptive analysis. The network device monitors the model recommendations and adapts the predictive model for concept drift while maintaining the constraint.

公开(公告)号：US20230196131A1

公开(公告)日：2023-06-22

申请号：US17559396

申请日：2021-12-22

Applicant: Verizon Patent and Licensing Inc.

Inventor： Kushal Singla ,  Subham Biswas

IPC: G06N5/02 ,  H04W16/28 ,  H04W16/22

CPC classification number: G06N5/022 ,  H04W16/28 ,  H04W16/22

Abstract: A system described herein may receive a set of outputs of a first model, which have been generated by the first model based on a set of inputs, and identify a set of historical values that correspond to the set of inputs and the set of outputs. The inputs and the historical values may be associated with the same time series. The system may train a second model based on the set of inputs to the first model, the set of outputs of the first model, and the set of historical values that correspond to the set of inputs and the set of outputs. The system may determine, based on training the second model, a set of weights associated with the set of historical values; and refine the first model based on the set of weights associated with the set of historical value.

公开(公告)号：US20230186167A1

公开(公告)日：2023-06-15

申请号：US17546132

申请日：2021-12-09

Applicant: Verizon Patent and Licensing Inc.

Inventor： Kushal Singla

IPC: G06N20/20

CPC classification number: G06N20/20

Abstract: A system described herein may provide a technique for enhanced federated learning in an environment that makes use of one or more centralized models. Different nodes may be associated with different groups. Each node may provide refinement information for a given centralized model. The modifications for particular groups may be aggregated and the model may be modified based on modifications associated with each group, as opposed to modifications associated with each node. Weights for each group may be determined based on attributes of the modifications associated with each group, which may allow for the identification, on a group basis, of bias, maliciously injected data, outliers, and/or other types of modifications which may reduce the quality of the model. As such, embodiments described herein may enhance the quality, accuracy, and predictive ability of federated learning techniques that utilize distributed or federated modifications to a centralized model.

公开(公告)号：US12169535B2

公开(公告)日：2024-12-17

申请号：US17706422

申请日：2022-03-28

Applicant: Verizon Patent and Licensing Inc.

Inventor： Vaishali Ravindranath ,  Kushal Singla

IPC: G06F16/35 ,  G06F16/335 ,  G06F18/23213 ,  G06F18/2413

Abstract: One or more computing devices, systems, and/or methods are provided. In an example, a method comprises receiving, by a device, attribute data for a region served by a telecommunications service. A cluster label is determined by the device for the region based on the attribute data. A first region persona is determined by the device for the region using a decision tree classifier model based on the cluster label and the attribute data. Recommended service parameters are implemented for the telecommunications service in the region based on the first region persona.

公开(公告)号：US20220164593A1

公开(公告)日：2022-05-26

申请号：US17101258

申请日：2020-11-23

Applicant: Verizon Patent and Licensing Inc.

Inventor： Kushal Singla ,  Sidakpreet Singh Chawla ,  Ebenezer Bardhan ,  Pooja Khivesara

IPC: G06K9/62

Abstract: Systems and methods described herein provide an online constraint optimizing service that evaluates user requests and inquiries for telecommunications services in the context of a real-time constraint-based analysis. According to an implementation, a network device receives a function for an analytic event and a constraint. The function applies different user attributes for a telecommunications network. The network device generates a training data set using offline constrained optimization of the function. The network device develops a predictive model for utilization of network resources in the telecommunications network using the training data set. The network device receives a user request that corresponds to the analytic event addressed by the predictive model and conducts an online prescriptive analysis using the predictive model. The network device optimizes allocation of the network resources to the user based on the prescriptive analysis. The network device monitors the model recommendations and adapts the predictive model for concept drift while maintaining the constraint.