Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020136663 - NODE, AND METHOD PERFORMED THEREBY, FOR PREDICTING A BEHAVIOR OF USERS OF A COMMUNICATIONS NETWORK

Publication Number WO/2020/136663
Publication Date 02.07.2020
International Application No. PCT/IN2018/050892
International Filing Date 29.12.2018
IPC
G06Q 30/02 2012.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
30Commerce, e.g. shopping or e-commerce
02Marketing, e.g. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards; Price estimation or determination
G06F 15/16 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
15Digital computers in general; Data processing equipment in general
16Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
H04L 29/00 2006.1
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
29Arrangements, apparatus, circuits or systems, not covered by a single one of groups H04L1/-H04L27/136
CPC
G06Q 30/02
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
30Commerce, e.g. shopping or e-commerce
02Marketing, e.g. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards; Price estimation or determination
Applicants
  • TELEFONAKTIEBOLAGET LM ERICSSON (PUBL) [SE]/[SE]
  • SARKAR, Abhishek [IN]/[IN] (SC)
Inventors
  • SARKAR, Abhishek
  • DEY, Kaushik
  • HEGDE, Dhiraj Nagaraja
  • ROY, Ashis Kumar
Agents
  • SINGH, Manisha
Priority Data
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) NODE, AND METHOD PERFORMED THEREBY, FOR PREDICTING A BEHAVIOR OF USERS OF A COMMUNICATIONS NETWORK
(FR) NŒUD, ET PROCÉDÉ MIS EN ŒUVRE PAR CELUI-CI, PERMETTANT DE PRÉDIRE UN COMPORTEMENT D'UTILISATEURS D'UN RÉSEAU DE COMMUNICATION
Abstract
(EN)
A method performed by a node (101) for predicting a behavior of users of a communications network (10) is described. The node (101) manages an artificial neural network (105). The node (101) merges (204) a first pre-existing predictive model (131) of the behavior in a first group of users (121) with a second model (133) of the behavior in a second group of users (122). The merging (204) comprises establishing connections between the first model (131) and the second model (133). Each of the connections has a respective weight. The respective weights of the connections are learned by respective connections of neurons in the artificial neural network (105) based on data from a third group of users (123). The node (101) also obtains (206) a third model for predicting the behavior in the third group of users (123), based on the merged models and the data from the third group of users (123).
(FR)
L'invention concerne un procédé, mis en œuvre par un nœud (101), destiné à gérer un comportement d'utilisateurs dans un réseau de communication (10). Le nœud (101) gère un réseau neuronal artificiel (105). Le nœud (101) fusionne (204) un premier modèle prédictif préexistant (131) du comportement dans un premier groupe d'utilisateurs (121) avec un second modèle (133) du comportement dans un second groupe d'utilisateurs (122). La fusion (204) comprend l'établissement de connexions entre le premier modèle (131) et le second modèle (133). Chacune des connexions a un poids respectif. Les poids respectifs des connexions sont appris par des connexions respectives de neurones dans le réseau neuronal artificiel (105) sur la base de données provenant d'un troisième groupe d'utilisateurs (123). Le nœud obtient également (206) un troisième modèle pour prédire le comportement dans le troisième groupe d'utilisateurs (123), sur la base des modèles fusionnés et des données provenant du troisième groupe d'utilisateurs (123).
Latest bibliographic data on file with the International Bureau