Session-based information pushing method and device, computer device and storage medium

Abstract

The invention discloses a session-based information pushing method and device, a computer device and a storage medium. The method compares the demand information keyword combination corresponding to the user demand information with the commodity information in the knowledge base, if there is commodity information including all the keywords in the keyword combination of the demand information in the knowledge base, pushes the commodity information including all the keywords in the keyword combination of the demand information to the corresponding upload terminal with the session information; and if there is commodity information including all the keywords in the keyword combination of the demand information in the knowledge base, pushes the commodity information to the corresponding uploadterminal with the session information; if there is no commodity information including all the keywords in the keyword combination of the demand information in the knowledge base, deletes at least onekeyword in the keyword combination of the demand information, obtains the adjusted keyword combination of the demand information, and judges whether there is a keyword combination including the demandinformation in the knowledge base is judged and returns. By using the knowledge base constructed by commodity information as the data basis of conversation information generation, the method realizesthe targeted and more accurate feedback of commodity recommendation information according to the user demand information.

Description

technical field [0001] The present invention relates to the technical field of information push, in particular to a session-based information push method, device, computer equipment and storage medium. Background technique [0002] At present, online shopping in Internet-based online shopping malls has become more and more frequent. When these online shopping malls recommend products to users, there are two kinds of product recommendation systems usually used: one is the recommended list edited by humans, and the other is the human-edited recommendation list. It is a recommendation list based on a collaborative filtering algorithm; while the user's demand for purchasing goods generally changes with time, or the user's demand is a process from abstraction to concreteness, and the existing product recommendation system cannot accurately base on the user's needs. The current actual demand responds to more accurate recommendation results in real time, which affects the recommend...

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention provides a session-based information push method, device, computer equipment, and storage medium, aiming to solve the problem that commodity information recommendation in the prior art uses a manually edited recommendation list or a recommendation list based on a collaborative filtering algorithm. Accurately respond to more accurate recommendation results in real time according to the current actual needs of users, thus affecting the recommendation process

Images