公开(公告)号：US20220147825A1

公开(公告)日：2022-05-12

申请号：US17593625

申请日：2020-03-18

Applicant: BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY

Inventor： Gilbert OWUSU ,  Hani HAGRAS ,  Ravikiran CHIMATAPU ,  Andrew STARKEY

IPC: G06N3/08 ,  G06N3/04

Abstract: A computer implemented method for machine learning including training an autoencoder having a set of input units, a set of output units and at least one set of hidden units, wherein connections between each of the sets of units are provided by way of interval type-2 fuzzy logic systems each including one or more rules, and the fuzzy logic systems are trained using an optimization algorithm; and generating a representation of rules in each of the interval type-2 fuzzy logic systems triggered beyond a threshold by input data provided to the input units so as to indicate the rules involved in generating an output at the output units in response to the data provided to the input units.

公开(公告)号：US20220147887A1

公开(公告)日：2022-05-12

申请号：US17593624

申请日：2020-03-18

Applicant: BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY

Inventor： Timothy GLOVER ,  Alistair MCCORMICK ,  Andrew STARKEY ,  Anthony CONWAY

IPC: G06Q10/04 ,  G06Q10/08

Abstract: A computer implemented method of routing multiple resource carriers to exchange resources at multiple exchange points. The resource carriers have different quantity capacities for a resource and each exchange point has a geo-location. The method includes: iterating a genetic algorithm, having a stopping condition based on a characteristic indicative of a cost of the subset, modelling usage of proper subsets of the carriers. Each iteration of the genetic algorithm includes: defining, for each carrier in the subset, a set of exchange points based on geo-locations, an objective exchange point that the carrier must visit, and the carrier's capacity; evaluating the characteristic for the subset of carriers; and responsive to the characteristic, selecting the subset as a prospective optimal subset and determining, for each carrier in the prospective optimal subset, an optimum route through the exchange points including the objective exchange point. The prospective optimal subset is selected over multiple iterations of the genetic algorithm such that a current prospective optimal subset is selected as an optimal subset having associated an optimum route for each carrier in the optimal subset.

公开(公告)号：US20220094624A1

公开(公告)日：2022-03-24

申请号：US17310017

申请日：2019-12-18

Applicant: BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY

Inventor： Andrew STARKEY ,  Lewis VERYARD ,  Hani HAGRAS ,  Gilbert OWUSU

IPC: H04L45/128 ,  H04L45/28 ,  H04L45/00

Abstract: A computer implemented method of determining non-intersecting primary and secondary routes between source and destination nodes in a communications network. The communication network represented by a graph data structure of nodes and edges, the edges having a weight corresponding to a resource involved in traversing the edged. The method including: defining a population set of primary routes, wherein each primary route in the population set identifies a secondary route based on a greedy route-finding algorithm applied to the graph having edges in the primary route excluded from the graph, such that the primary and secondary routes are non-intersecting routes through the graph; applying a genetic algorithm to the population set to iteratively select and crossover one or more pairs of primary routes in the population set; and selecting, from the population set, a primary route and corresponding secondary route having a lowest aggregate weight of edges.