百度研发新算法 可通过人工智能防止踩踏事故

Chinese search engine giant Baidu has developed a machine-learning algorithm that predicts whether crowds are likely to form at certain locations in two hours, which could be used to prevent stampedes.中国搜索引擎巨头百度公司近日研发了一项机器学习算法。该算法可以预测人群否有可能在两小时内在某些方位挤满，借以避免冲撞事故的再次发生。The algorithm uses data from Baidus map app, said a research report published by Baidus Big Data Lab Tuesday, studying the number of map queries and the number of users in an area.百度大数据实验室周二公布的研究报告认为，该算法用于了百度地图应用程序的数据，研究地图查找和用户在一个地区的数量。

Its map app accounts for over 70 per cent of Chinas mapping services market, the companys user statistics show. Many Chinese users often search for an ideal travel route using Baidu Maps.该公司的用户统计数据表明，其地图应用程序占到中国地图服务市场的70％以上。许多中国用户常常用于百度地图搜索理想的旅行路线。The lab began to concentrate on how to predict crowds in certain areas following the Shanghai stampede on New Years Eve in Dec 2014, where 36 people were killed during celebrations on the Bund riverfront, according to Wu Haishan, co-author of the report.据该报告的年出版者吴海山回应，在2014年12月的除夕夜，36人因冲撞事件杀于上海外滩河边庆典活动之后，该实验室就开始专心于如何预测特定区域的人群。

Using the map data, they found a way to determine the numbers in real time and trigger warnings 30 minutes to two hours ahead of time if unusually large crowds are expected to gather.利用地图数据，他们找到了一种方法来确认动态数字。而且如果将有大量人群挤满，该算法则不会提早30分钟到两小时启动时警告。

Wu said that the algorithm could be used by local governments, authorities and even venue operators to monitor crowds. It may eventually provide the function as a public service feature on Baidu Maps, according to Wu.吴海山回应，该算法可以由地方政府，主管部门和活动场地运营商应用于监测人群。他还回应，它有可能最后不会沦为百度地图的公共服务功能。If implemented, the feature would allow users to see what the crowds are like in various locations using the app.如果以求实行，这项功能将容许用户用于应用程序，来看见有所不同方位的人群状况。

本文来源：皇冠游戏中心官网-www.sriingenieria.com