User grouping method

Abstract

The invention discloses a user grouping method. The method comprises the steps of determining one or more exclusive attributes of a category according to browsing behaviors of users purchasing commodities in the category in a first predetermined browsing time range; performing traversal combination on commodity attribute values of the exclusive attributes and commodity attribute values of other exclusive attributes to obtain user groups corresponding to all combinations; and allocating users with intentions of purchasing the commodities in the category in a second predetermined browsing time range to corresponding user groups. The exclusive attribute is a commodity attribute and has multiple commodity attribute values; the multiple commodity attribute values completely cover all the commodities in the category; and the commodity attribute values of the same commodity attributes selected by the same user group in a process of browsing the commodities in the category are most concentrated and have relatively low coincidence degree with other commodity attribute values of the commodity attributes. By adopting the method, the user groups can be distinguished according to real purchasedemands of the users.

Description

technical field [0001] The invention relates to the technical field of electronic commerce, in particular to a user grouping method. Background technique [0002] In recent years, with the rapid development of e-commerce, e-commerce companies have accurately recommended products of their interest to users based on user behavior data accumulated on their own platforms, thereby facilitating users to place orders, which has become an important way for companies to increase user conversion rates. It is also a shortcut for e-commerce companies to optimize user experience and enhance user stickiness. In view of this, a batch of BI function modules such as "guess what you like" and "similar recommendation" based on user browsing and search data have been applied by various companies. [0003] Most of the existing BI functions perform user classification and product recommendation through user portraits such as the user's region, gender, and age. The data basis usually comes from ...

AI Technical Summary

Problems solved by technology

As a result, a large number of high-quality resource locations on the page have not been personalized, and these one-of-a-kind product placements will interfere with some potential purchasers, resulting in the loss of users

[0007] (2) Inaccurate personalized recommendation

Since the cost of browsing products is very low for users to shop online, the repeated display of browsed products obviously does not have the effect of improving the conversion rate

For product recommendation at the category level, since product attributes are not subdivided, it is difficult to guarantee the accuracy of the recommendation

Therefore, the only personalized resources on the page are faced with the current situation of inaccurate recommended products and unsatisfactory improvement in conversion rate

[0009] (3) Lack of induction of historical behavior data of target customers

As a result, the e-commerce platform does not know what kind of products users want to buy most, and it is impossible to make accurate recommendations and place resources for users.

Images