A personal data analysis method based on a Bayesian network and a computer storage medium

Abstract

The invention discloses a personal data analysis method based on a Bayesian network and a computer storage medium, and the method comprises the following steps: (1) enabling personal life behavior data to be embodied as a one-dimensional vector of behaviors and behavior attributes, enabling the behavior attributes to at least comprise a time attribute, and obtaining a life behavior data record through data preprocessing; (2) learning the data through a hybrid structure learning algorithm, and constructing a life data Bayesian network; (3) parameter learning is carried out according to the lifedata Bayesian network, and a conditional probability distribution table of each network node is obtained through learning; and (4) calculating the probability of occurrence of other behaviors based on the probability of the specific behavior by using a joint tree reasoning algorithm according to the life data Bayesian network, and completing the analysis and prediction of the personal life behavior. According to the method, the Bayesian network is applied to personal behavior data analysis, and the network construction method is improved, so that the learning accuracy and the convergence of the algorithm are effectively improved, and the operation performance is improved.

Description

technical field [0001] The invention relates to a personal data analysis method and a computer storage medium, in particular to a Bayesian network-based personal data analysis method and a computer storage medium. Background technique [0002] In recent years, with the rapid development of mobile Internet technology and the rise and popularization of mobile smart terminals, the data generated by people's work, shopping, sleeping, eating, exercising and communication can be passed in real time, safely and privately. collected by mobile smart terminals. People generate such "digital traces" every day, and social networks, search engines, mobile operators, online games and e-commerce sites are all widely using these data. They will cluster and analyze the data to promote advertising and improve the performance of the service system. By analyzing the data of daily life, we can discover the potential information in these data, and make full use of this information to drive thin...

AI Technical Summary

Problems solved by technology

Due to the limitations of the collision detection method, there are some unoriented edges in the learned network structure, which affects the accuracy of structure learning.

At the same time, this type of method uses an absolute method to measure the relationship between different variables, that is, if the mutual information between variable A and variable B is greater than a certain positive number, it is considered that A and B are related, and an undirected edge can be added. However, this method is easy to lose weak joint dependent edges, which may lead to the final learned network being a disconnected graph, resulting in the learned result not being the global optimal solution.

The method based on score search can learn a better network structure, but it is easy to fall into local optimum, and some algorithms (such as K2) need to know the topological sequence of nodes in advance, a low accuracy topological sequence will lead to accurate learning results low rate

The hybrid search method (such as MMHC) reduces the complexity of the search space and also narrows the scope of the understanding space. Due to the limitation of the space structure in the scoring search stage, this error cannot be corrected, and it is easy to fall into a local optimal solution, making it difficult to learn optimal network structure

Images