Personalized recommendation algorithm based on crowd sensing

Abstract

The invention provides a personalized recommendation algorithm based on crowd sensing, and the algorithm comprises the steps of collecting a large amount of data of the technological process of environmental protection equipment from a multi-source multi-mode data fusion result based on the thought of crowd sensing, and carrying out the feature analysis on the obtained data; during the recommendation process, introducing a Behavior-Intensive Neural Networking framework, wherein the Behavior-Intensive Neural Neural Networking framework comprises two parts, namely, an environmental protection equipment vector generation part and a differentiated behavior learning part; generating a standardized vector for each piece of environmental protection equipment by using a Neural Item Embedded model;and then exploring the interaction sequence of the customer by using a Discovery Behaviors Learning model to obtain the priori knowledge, so as to recommend the environmental protection equipment tothe target customer; and designing two learning modes to explore the user behaviors, namely the session-based behavior learning and the preference behavior learning, and learning the previous behaviors and historical preferences of the customers respectively; and finally, based on the vectorized environmental protection equipment, recommending the first k possible preferred environmental protection equipment to the target customer through the combination of the two learning behaviors.

Description

technical field [0001] The invention relates to a BINN framework (behavioral concentration neural network), a DBL model (distinguished behavior learning) and deep learning, and specifically relates to a personalized intelligent recommendation algorithm based on crowd perception. Background technique [0002] At present, how to accurately recommend suitable products to customers according to their needs and environmental requirements is a problem worthy of further study. [0003] Due to human participation in the data generation process, crowd intelligence big data has many new features compared with traditional sensory network data. First, crowd intelligence data is obtained through multiple online and offline participation methods of humans, and is generated in both information space and physical space. Due to the role of human beings, data in different spaces realize temporal and spatial interweaving and semantic association. Second, due to the uncertainty and spontaneity...

AI Technical Summary

Problems solved by technology

Second, due to the uncertainty and spontaneity of human behavior, swarm intelligence data often contain many errors or redundancy, and the quality varies, which poses a great challenge to the timely and accurate processing of data.

Images