A multi-target evaluation factor screening method and related equipment

Abstract

The application belongs to the field of big data technology, and relates to a multi-target object evaluation factor screening method and related equipment. The method includes: reading the result data and process data of all target objects, and extracting the information of several indicators therefrom. Including the index name; based on the eigenvectors of each index, the feature matrix representing all the indicators of all target objects is generated and input into the preset classification model based on the MLP algorithm to obtain an index set of multiple classification dimensions; the indexes in each index set are sequentially Perform data quality screening, index importance screening, and index autocorrelation screening, and use the index of screening preset conditions as the evaluation factor to obtain the evaluation factor set of multiple classification dimensions. In addition, the present application also relates to blockchain technology, in which confidential information in result data and process data can be stored. This application is divided into multiple dimensions to evaluate the target object in a more comprehensive and forward-looking manner, and dynamic evaluation can be performed at any point in time.

Description

technical field [0001] The present application relates to the technical field of big data, and in particular relates to a method, device, computer equipment and storage medium for screening evaluation factors of multi-target objects. Background technique [0002] At present, the evaluation indicators used in the evaluation of target objects such as physical institutions are insufficient and highly subjective. It is difficult to integrate the precipitated data through technical means and calculate the correlation of various indicators with the target indicators of the target object, that is, it is impossible The atomic granularity data of the target object is fully used and mined, and it is difficult to mine the forward-looking evaluation data, and the evaluation lag is strong. In addition, the existing evaluation process is difficult to systematize and automate, and it cannot be based on the target object at different time points. Dynamic evaluation of dynamic data. Conten...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiment of the present application is to propose a multi-target evaluation factor screening method, device, computer equipment and storage medium to solve the problem that the atomic granularity of the target object cannot be evaluated when evaluating target objects such as entities in the prior art. The data is fully used and mined, and it is difficult to mine forward-looking evaluation data, and the problem of strong evaluation lag

Images