首页> 外国专利> Adaptive matching network - requirements on the client - requirements in digital networks

Adaptive matching network - requirements on the client - requirements in digital networks

机译:自适应匹配网络-客户要求-数字网络要求

摘要

The present application relates to a computer network, a computer implemented method, a computer system and a computer program product for adaptive matching network - answers to client - requirements which are received from a requesting client device, comprising:a parser module which is arranged to– Parsing a request data bank according to data, the relevant for the client - request; and– Generating a request data object based on the data, the relevant for the client - request are;a matching - module which is arranged to– Applying a matching - algorithm to the request data object with data objects in a response data bank are stored, by a matching - value of potential service to calculate data objects; and– Generating a final result based on the calculated matching - value, wherein the final result of a list of data objects comprising a matching - value over a specified matching - threshold value have;a learning module, which is arranged to:– Applying a learning process based on the end resu and– Generating a learn result of the learning process;a learn factory, which is arranged, the matching - algorithm of the matching - module based on the result of the learning, wherein the adaptation of the matching - algorithm applying a boosting - algorithm for adaptation of the weights, the with determinants of relevant object data objects in the response data bank are associated, comprises;the requesting client device, the provider and the machine learning system are coupled via a network.
机译:本申请涉及一种计算机网络,一种计算机实现的方法,一种计算机系统和一种计算机程序产品,用于从请求客户端设备接收的自适应匹配网络-对客户端的答复-需求,包括:解析器模块,其被配置为–根据与客户有关的数据解析请求数据库;和–根据该数据生成与客户端有关的请求数据对象-请求;-匹配模块-安排为-将匹配算法应用于具有响应数据库中数据对象的请求数据对象,通过匹配-潜在服务的值来计算数据对象;根据所计算出的匹配值生成最终结果,其中包括在指定的匹配阈值之上的匹配值的数据对象列表的最终结果具有学习模块,该学习模块被安排为:基于最终结果的学习过程; –生成学习过程的学习结果;安排了一个学习工厂,根据学习结果,对匹配模块的匹配算法进行模块匹配,其中对匹配算法的自适应应用了boosting算法通过权重的调整,将响应数据库中相关对象数据的确定对象与确定对象相关联,包括:请求客户端设备,提供者和机器学习系统通过网络耦合。

著录项

  • 公开/公告号DE102015008607A1

    专利类型

  • 公开/公告日2017-01-05

    原文格式PDF

  • 申请/专利权人 SAP SE;

    申请/专利号DE20151008607

  • 申请日2015-07-03

  • 分类号H04L12/16;G06F17/30;

  • 国家 DE

  • 入库时间 2022-08-21 13:23:01

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号