In mid 2020 people vigorously debated which Corona virus-management strategy should be implemented – ‘total Lockdown’, ‘Partial Lockdown’ or ‘do Nothing’. For success, the chosen strategy would need considerable public support. So here we demonstrate how support, or otherwise, could have been predicted using our freely available Planticipate app. It self improves by sending its users' judgements to the cloud, where learning routines formulate regression- and neural network-based relationships between thirteen, key, plan-evaluation criteria and overall plan desirability. Hence whenever any set of plans are scored on the criteria, these relationships generate forecasts of plan desirability according to a number of demographic groups of past users. Our app predicted that many community groups will regard the ‘do-Nothing’ option as statistically significantly inferior to the other two plans, and it also made several less-than-statistically-significant forecasts which were extremely thought provoking. Using innovative face charts to better interpret complicated, thirteen-dimensional data, Planticipate also suggested probable reasons for such forecasts. These included an apparent fixation upon only permissiveness and productivity by people living in North America and relative pragmatism amongst females. Such revelations immediately suggested possible modifications for making different plans more acceptable to certain community groups. Given that in reality several of these modifications were only implemented later on during the pandemic, an early application of our app would almost certainly have prompted faster, more creative and more empathetic urban management.

2020 年年中，人们激烈争论应该实施哪种冠状病毒管理策略——“全面封锁”、“部分封锁”或“什么都不做”。为取得成功，所选择的战略需要相当多的公众支持。所以在这里我们展示了如何使用我们免费提供的Planticipate预测支持或其他方式应用程序。它通过将用户的判断发送到云来自我改进，在那里学习例程在 13 个关键的计划评估标准和总体计划的可取性之间制定基于回归和神经网络的关系。因此，无论何时根据标准对任何计划集进行评分，这些关系都会根据过去用户的多个人口统计群体生成计划合意性的预测。我们的应用程序预测，许多社区团体会认为“什么都不做”的选项在统计上明显低于其他两个计划，并且它还做出了几个不太具有统计意义的预测，这些预测非常发人深省。使用创新的人脸图更好地解读复杂的十三维数据，Planticipate还提出了这种预测的可能原因。其中包括对生活在北美的人们的宽容和生产力的明显关注以及女性的相对实用主义。这些启示立即暗示了可能的修改，以使某些社区团体更容易接受不同的计划。鉴于实际上这些修改中的一些是在大流行期间才实施的，我们应用程序的早期应用几乎肯定会促进更快、更有创意和更善解人意的城市管理。