A semi-supervised tourist portrait data clustering method based on density peaks and gravitation influences

Abstract

The invention relates to a semi-supervised tourist portrait data clustering method based on density peaks and gravitation influences, which comprises the following steps: calculating density values and distance values of all points of tourist portrait data through a density peak algorithm, and finding out all possible clustering center points; Calculating the distance between the tourist portraitseed points and possible clustering center points by using the provided tourist portrait seed points, voting and screening out accurate clustering center points, and pasting clustering labels on the corresponding clustering center points by using the seed label information; Randomly selecting a seed data subset with a certain proportion from all the seed data, and calculating the gravitation influence between the seed data subset and each unlabeled data point by introducing the idea of the universal gravitation law, thereby clustering all the unlabeled data and attaching corresponding clusterlabels to the unlabeled data; And randomly selecting a seed data subset for multiple times to attach a corresponding decision-making cluster label to the unlabeled data, and voting to select cluster label information of each piece of unlabeled data. The method is good in clustering effect and high in accuracy.

Description

Technical field [0001] The present invention relates to a semi-supervised tourist portrait data clustering method based on density peak and gravity influence, in particular to a semi-supervised tourist portrait data clustering method that integrates tourist portrait seed tag information on the basis of density peak and gravity influence . Background technique [0002] The so-called clustering is the process of grouping similar things together and dividing the different things into different categories. In unsupervised learning, clustering is an extremely important learning method. As a branch of statistics, clustering learning is widely used in a variety of industries, including machine learning, data mining, image processing, smart tourism, pattern recognition analysis and other current hot fields. It is precisely because clustering learning is an extremely important learning method. In the past few decades, relevant scholars have proposed a large number of clustering algorith...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortage of the existing DPC density peak clustering method, which needs to artificially select the relevant cluster center points through the decision diagram, the artificially selected cluster center points cannot accurately capture the precise cluster center, and there is only The only density peak is effective. On the contrary, when there are multiple density peaks in the cluster, the clustering effect is very poor; the clustering variance of the existing DPC density peak clustering algorithm is zero, and a certain data point is classified into the wrong cluster. In this case, other data points that follow it will also be classified into wrong clusters, thereby producing a domino effect and reducing the accuracy of clustering. The present invention provides a density peak-based Semi-supervised tourist portrait data clustering method influenced by gravitation. In the actual application scenario, there are some known related clustering information in the tourist portrait data provided by tourist attractions, and the known tourist portrait seed cluster label information is fully used to solve unknown tourist portraits. The cluster label information of the data

Images