Since the keyboard is the most common method for text input on computers today, the design of the keyboard layout is very significant. Despite the fact that the QWERTY keyboard layout was designed more than 100 years ago, it is still the predominant layout in use today. There have been several attempts to design better layouts, both manually and automatically. In this paper we improve on previous works on automatic keyboard layout optimization, by using a deep neural network to assist in a genetic search algorithm, which enables the use of a sophisticated keyboard evaluation function that would otherwise take a prohibitive amount of time. We also show that a better choice of crossover routine greatly improves the genetic search. Finally, in order to test how users with different levels of experience adapt to new keyboard layouts, we conduct some layout adaptation experiments with 300 participants to examine how users adapt to new keyboard layouts.

由于键盘是当今计算机上最常用的文本输入方式，因此键盘布局的设计非常重要。尽管 QWERTY 键盘布局是 100 多年前设计的，但它仍然是当今使用的主要布局。人们已经多次尝试手动和自动设计更好的布局。在本文中，我们改进了之前关于自动键盘布局优化的工作，通过使用深度神经网络来辅助遗传搜索算法，这使得能够使用复杂的键盘评估功能，否则将花费大量时间。我们还表明，更好的交叉例程选择可以极大地改善遗传搜索。最后，为了测试不同经验水平的用户如何适应新的键盘布局，