发明名称 Search result ranking method and system
摘要 Search result ranking includes recording user action information on displayed objects in search results obtained using one or more query words, upon receiving a switch-page request or switch-screen request, determining a commonality level of one or more attribute characteristics in a set of objects subjected to user actions, the determining of the commonality level being based on the user action information on the displayed objects, selecting attribute characteristics that comply with predetermined requirements to serve as reference norms for ranking objects that are to be displayed or ranked, the selecting of the attribute characteristics being based on the commonality level, and adjusting rank of objects that are to be displayed or to be ranked and whose attribute characteristics comply with the reference norms.
申请公布号 US9633082(B2) 申请公布日期 2017.04.25
申请号 US201314062773 申请日期 2013.10.24
申请人 Alibaba Group Holding Limited 发明人 Li Jiasen;Su Suisui
分类号 G06F17/30;G06F7/00 主分类号 G06F17/30
代理机构 Van Pelt, Yi & James LLP 代理人 Van Pelt, Yi & James LLP
主权项 1. A search result ranking method, comprising: recording user action information on displayed objects in search results obtained using one or more query words, wherein the displayed objects relate to products or product information; upon receiving a switch-page request or switch-screen request, determining two or more commonality levels of one or more attribute characteristics in objects subjected to user actions, wherein the determining of the two or more commonality levels is based on the user action information on the displayed objects, wherein the one or more attribute characteristics include: title of a product, price of a product, image or image address of a product, number of recent transactions of a product, shipping costs of a product, area where product is located, seller's name of a product, self-defined tags provided by a product publisher, service tags provided by a product publisher, or any combination thereof, and wherein the determining of the two or more commonality levels comprises: calculating first commonality levels of attribute characteristics of objects in a selected set based on the recorded user action information on the displayed objects, wherein the selected set includes user-selected objects of the displayed objects, a first commonality level corresponding to a ratio of a number of objects having the same or similar attribute characteristic of the user-selected objects and a total number of the user-selected objects; andcalculating second commonality levels of attribute characteristics of objects in an unselected set, wherein the unselected set includes displayed objects that have not been selected, a second commonality level corresponding to a ratio of a number of objects having the same or similar attribute characteristic of the displayed objects that have not been selected and a total number of the displayed objects that have not been selected; selecting attribute characteristics that comply with predetermined requirements to serve as reference norms for ranking objects that are to be displayed or ranked, wherein the selecting of the attribute characteristics is based on the first commonality level of the calculated first commonality levels and the second commonality level of the calculated second commonality levels; and adjusting rank of objects that are to be displayed or to be ranked, and whose attribute characteristics comply with the reference norms, wherein the objects that are to be displayed or to be ranked have not yet been displayed and are on a separate page from the displayed objects.
地址 KY