首页> 外国专利> ELECTRONIC DEVICE FOR PERFORMING A PREDECTION FOR A PRICE OF A PRODUCT USING BIG DATA AND MACHINE LEARNING MODEL AND METHOD FOR OPERATING THEREOF

ELECTRONIC DEVICE FOR PERFORMING A PREDECTION FOR A PRICE OF A PRODUCT USING BIG DATA AND MACHINE LEARNING MODEL AND METHOD FOR OPERATING THEREOF

机译:用于使用大数据和机器学习模型的产品的价格对产品的价格进行预测及其操作方法

摘要

According to an embodiment of the present application, a method of operating a server includes: receiving a plurality of pieces of information for each product from an external server, wherein the plurality of pieces of information includes brand information for each product, a state for each product. Information, and price information for each product, and the status information includes at least one of a degree of discoloration, a degree of migration, a degree of tanning, a degree of scratches, a degree of abrasion, a degree of stain, a degree of lack of accessories, or a degree of repair at the time of transaction of the product. Extracting specific information for price prediction for each product based on at least one of information on a current point of time or a reputation for each product from among the plurality of pieces of information representing one; Generating a plurality of machine learning models for predicting prices for the products by using the specific information as training data; wherein each of the plurality of machine learning models includes first brand information for a specific product And identifying a connection of the electronic device to the server, configured to output price information for a specific product in response to receiving the first status information. And providing the plurality of machine learning models to the connected electronic device; including, in the electronic device, brand information on a first product and state information on the first product as the plurality of machine learning models. In response to the input, the plurality of machine learning models return price information for the first product, a method of operation is provided. Other various embodiments are possible.
机译:根据本申请的实施例,操作服务器的方法包括:从外部服务器接收每个产品的多条信息,其中多条信息包括每个产品的品牌信息,每个产品产品。每个产品的信息和价格信息,以及状态信息包括一定程度的变色,迁移程度,晒黑程度,划痕程度,磨损程度,污渍程度,程度缺乏配件,或在产品交易时的维修程度。提取每个产品的特定信息,基于当前时间点的至少一个信息或从代表一个的多条信息中的每个产品的声誉中的至少一个;通过使用特定信息作为训练数据来生成多个机器学习模型,用于预测产品的价格;其中,多个机器学习模型中的每一个包括特定产品的第一品牌信息,并将电子设备的连接识别到服务器,被配置为响应于接收到第一状态信息来输出特定产品的价格信息。向连接的电子设备提供多个机器学习模型;包括在电子设备中,作为多个机器学习模型的第一产品上的第一产品和状态信息的品牌信息。响应于输入,多个机器学习模型返回第一产品的价格信息,提供了一种操作方法。其他各种实施例是可能的。

著录项

  • 公开/公告号KR102234821B1

    专利类型

  • 公开/公告日2021-04-01

    原文格式PDF

  • 申请/专利权人

    申请/专利号KR1020200131072

  • 发明设计人 이은미;유정현;

    申请日2020-10-12

  • 分类号G06Q30/02;G06K9/20;G06N3/02;G06Q50;

  • 国家 KR

  • 入库时间 2024-06-14 21:24:37

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