Title:
機械学習に基づくウェブインタフェース生成及びテストシステム
Document Type and Number:
Japanese Patent JP7000341
Kind Code:
B2
Abstract:
Roughly described, the technology disclosed provides a so-called machine-learned conversion optimization (MLCO) system that uses artificial neural networks and evolutionary computations to efficiently identify most successful webpage designs in a search space without testing all possible webpage designs in the search space. The search space is defined based on webpage designs provided by marketers. Neural networks are represented as genomes. Neural networks map user attributes from live user traffic to different dimensions and dimension values of output funnels that are presented to the users in real time. The genomes are subjected to evolutionary operations like initialization, testing, competition, and procreation to identify parent genomes that perform well and offspring genomes that are likely to perform well.
Inventors:
Isco, Neil
Miklinen, Liszt
Miklinen, Liszt
Application Number:
JP2018553336A
Publication Date:
January 19, 2022
Filing Date:
January 05, 2017
Export Citation:
Assignee:
EVOLV TECHNOLOGY SOLUTIONS INC.
International Classes:
G06F3/0481; G06F40/143; G06N3/12; G06Q50/10
Domestic Patent References:
| JP2003529116A |
Other References:
Giordano Tamburrelli ほか,Towards Automated A/B Testing,ResearchGate,2014年08月04日,https://www.researchgate.net/publication/264435539_Towards_Automated_AB_Testing,[令和3年2月3日検索],インターネット,DOI:10.1007/978-3-319-09940-8_13
Attorney, Agent or Firm:
Yoshifumi Masaki
Previous Patent: Coordinated transmission management for multiple smart devices
Next Patent: Prediction and monitoring of urination
Next Patent: Prediction and monitoring of urination