User activity mode dividing and attribute speculating method

Abstract

The invention relates to a user activity mode dividing and attribute speculating method, and the method comprises the steps: constructing a theme model, an activity mode dividing model and a Bayesian-network-based resident attribute backstepping model based on investigation data comprising personal attributes and travel information; obtaining to-be-complements big data; carrying out the processing of big data in the theme model and the activity mode dividing model, so as to obtain activity modes of users; inputting the activity modes into the Bayesian-network-based resident attribute backstepping model, so as to obtain the social economy attribute information, corresponding to each mode, of the users. According to the invention, the number of activity modes is six, so the method can achieve the complementation of the social economy attribute information of all users, and can achieve the scientific and convenient analysis and statistics of the number of individuals on a road at each time period of a day. Meanwhile, whether each user specifically takes a bus or drives a car can be further judged through the social economy attribute information of the individuals, thereby providing the important reference basis for the urban traffic planning and traffic demand prediction.

Description

technical field [0001] The invention relates to intelligent device data analysis, in particular to a user activity pattern division and attribute estimation method. Background technique [0002] Urban user travel activity information is an important basis for urban planning, traffic management, and user activity research. It is generally obtained through traditional methods such as user travel surveys, which consume a lot of manpower, material resources, and time. With the introduction of concepts such as intelligent transportation systems and smart cities, traffic big data (such as bus IC cards, mobile phone signaling data, etc.) It has great advantages, and it has begun to be used in fields such as user travel information extraction and individual activity pattern analysis. However, although the time-stamped location information can be obtained through traffic big data to obtain the user's daily movement trajectory, due to the inherent defects of the data or privacy prote...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to provide a method that can analyze various user activity patterns and obtain user socioeconomic attribute information based on big data analysis for the problem that the content of user activity patterns obtained by big data analysis is single and the user's socioeconomic attributes are few. A Method for Classifying User Activity Patterns and Inferring Attributes

Images