Hospital department similarity analysis method combining binary network and text

Abstract

The invention discloses a hospital department similarity analysis method combining a binary network and text. The method comprises the following steps: step 1, collecting behavior data about multi-point practising of doctors, and constructing the doctor-department binary network; step 2, calculating network similarity among departments according to the doctor-department binary network; step 3, calculating text similarity among the departments based on a ratio text similarity algorithm; and step 4, combining the network similarity and the text similarity among the departments for department similarity analysis. According to the method, the doctor-department binary network is constructed, the network similarity among the departments is calculated, the text similarity among the departments iscalculated on the basis of the ratio text similarity algorithm, and the network similarity and the text similarity among the departments are combined for department similarity analysis. An effect ofanalyzing a department ranking situation of each city and the like according to department similarity situations can be subsequently realized.

Description

technical field [0001] The invention relates to data mining and network science technology, in particular to a hospital department similarity analysis method combining bipartite network and text. Background technique [0002] The data in the real world are generally incomplete and inconsistent, so data mining cannot be performed directly, or the mining results are unsatisfactory. Data preprocessing is one of the key technologies to improve the quality of data mining. Data preprocessing refers to the necessary processing such as review, screening, sorting, etc. before classifying or grouping the collected data. Data preprocessing technology is used before data mining, which greatly improves the quality of data mining models and reduces the time required for actual mining. [0003] In the process of data processing, it often involves how to measure the similarity between two texts. Text belongs to a high-dimensional semantic space. How to abstract it and quantify its simila...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the inadequacy of the inability to realize the department similarity analysis method in the existing technology, and to study the influence of the doctor's behavior on the department similarity

Images