Abstract:The traditional earthquake damage degree estimation models based on geographic information system are inefficient in analyzing and processing big data, and they result in a non-ideal evaluation. Therefore, considering a big data environment, a damage degree estimation model in earthquake-prone areas is designed in the study. The model structure is composed of data service layer, business model layer, and application display layer. The model is composed of six functional structures: basic data control module, seismic hazard module, structural failure module, loss assessment module, decision control module, and document control module. The logical process and page display result of direct economic loss module are designed in the model. The module utilizes a random weight neural network to rapidly assess earthquake damage degree in a big data environment. The experimental results show that the designed model can effectively and accurately evaluate the destruction degree in earthquake-prone areas under a big data environment.