This disclosure describes techniques for generation of timely earthquake alerts based on crowdsourced user search queries that are posed in near real-time to an earthquake event. With user permission, user intent about a search query is determined based on search query keywords entered by a user. If it is determined that the user likely felt an earthquake, the user is served with a yes/no question asking whether they felt shaking. User responses from multiple users and/or other indicators such as analysis of device IMU data, social media posts, etc. are aggregated and analyzed to determine whether an earthquake event has likely occurred in a particular region and an associated confidence level, even in the absence of official information regarding the event. Based on the confidence level, other users in that location that pose search queries about an earthquake event are provided with information indicative of an earthquake event. When official earthquake information becomes available subsequently, it is provided to the user.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Rosenschein, Avi; Schlesinger, Mor; Zinger, Arbel; Graidy, Dor; and Tzur, Itai, "Real-time Updates For Earthquake Events Based On User Queries", Technical Disclosure Commons, (November 10, 2020)