US 11,800,379 B2
Improving immune system of site using generative adversarial networks and reinforcement learning
Leonid Mokrushin, Uppsala (SE); Selim Ickin, Stocksund (SE); and Ravi Kiran Kotty, Hyderabad (IN)
Assigned to Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Appl. No. 17/266,254
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
PCT Filed Aug. 20, 2018, PCT No. PCT/EP2018/072430
§ 371(c)(1), (2) Date Feb. 5, 2021,
PCT Pub. No. WO2020/038548, PCT Pub. Date Feb. 27, 2020.
Prior Publication US 2021/0306873 A1, Sep. 30, 2021
Int. Cl. H04W 24/02 (2009.01); H04L 41/14 (2022.01); H04L 41/16 (2022.01); H04W 24/06 (2009.01); G06N 3/045 (2023.01)
CPC H04W 24/02 (2013.01) [G06N 3/045 (2023.01); H04L 41/145 (2013.01); H04L 41/16 (2013.01); H04W 24/06 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A method for improving performance in a wireless communication network, the method comprising:
training, using a generative adversarial network, a generator model that generates real problems of a telecommunication site from latent space problems using data noise;
generating a generated problem that has not occurred at the telecommunication site and that has a non-zero probability of occurring at the telecommunication site in the future;
providing the generated problem to a virtual agent that is configured to generate a solution action to resolve the generated problem;
evaluating the solution action relative to the generated problem to determine a performance value corresponding to the solution action; and
responsive to the performance value being higher than other performance values corresponding to other solution actions for the generated problem, generating a generic problem model that corresponds to the generated problem and that is associated with the solution action.