User portrait description method based on big data

The invention relates to the technical field of user portrait description, and discloses a user portrait description method based on big data, comprising the following steps: S1, collecting basic identity information of a user, and storing the basic identity information of the user; and S2, according to the basic identity information of the user, associating and matching behavior characteristic data of the user online, and analyzing the associated and matched behavior characteristic data of the user. Behavior characteristic data of a user and keyword data extracted from archive information and case information of the user are collected, and then the behavior characteristic data of the user and the keyword data extracted from the archive information and the case information of the user are subjected to optimal and final processing. Therefore, the final and optimal feature data and the attribute result corresponding to the feature data are obtained, and then the final and optimal feature data and the attribute