Intelligent terminal and marketing recommendation method and system for intelligent home equipment

Abstract

The invention relates to an intelligent terminal and a marketing recommendation method and system for intelligent home equipment. The method comprises the following steps: classifying all hosts by adopting a clustering algorithm according to an equipment list bound with each host; counting users under each type of hosts to form a user pool of each type of hosts; for a user pool of a certain type of hosts, obtaining a recommendation vector of each user in the user pool by adopting a time attenuation algorithm; classifying the users in the user pool by adopting a clustering algorithm; counting an equipment list bound with a host where each type of users in the user pool are located to form an equipment pool of each type of users in the user pool; and for a certain user under each type of users, recommending equipment which is not purchased by the user in the corresponding equipment pool. According to the method, the data range used during recommendation is narrowed through double clustering, and the click operation habit of the recent equipment of the user is considered, so that the similarity of similar users is higher, the recommendation accuracy is improved, and the calculated amount is effectively reduced.

Description

technical field [0001] The invention relates to a marketing recommendation method and system for smart terminals and smart home equipment, and belongs to the technical field of smart home. Background technique [0002] With the advent of the era of big data, data collection and storage equipment in all walks of life has been continuously improved, and the amount of user data is increasing rapidly both in terms of time and space. The smart home industry is a large producer of data. These data can realize the precise marketing of smart home devices and recommend suitable smart home products for users. [0003] At present, the algorithms used for marketing in the prior art include the following types: [0004] 1. Clustering algorithm. As a clustering algorithm for unsupervised learning, it is mainly divided into the following categories: partition-based clustering algorithms, hierarchical-based clustering algorithms, and density-based clustering algorithms. For example: DBSC...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a marketing recommendation method for smart home equipment to solve the problems of low recommendation accuracy, low efficiency and poor user experience in existing marketing recommendation methods; meanwhile, it also provides a marketing recommendation method for smart home equipment The recommendation system is used to solve the problems of low recommendation accuracy, low efficiency and poor user experience in the existing recommendation system; at the same time, it also provides a smart terminal to solve the problem of low accuracy and low efficiency of the recommendation of the existing smart terminal and the problems of users Problems with poor experience

Images