A big data-based talent information analysis management method and system

By standardizing and unifying personnel identification of multi-source talent data, structured evaluation evidence and probabilistic prediction evidence are generated, and their inconsistency is calculated in parallel. This solves the problems of reliability of results and auditability of process in multi-source talent information analysis, realizes the unification and traceability of output from the unit end and the individual end, and improves data availability and management standardization.

CN122240633APending Publication Date: 2026-06-19南宁市卫生健康委员会 +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
南宁市卫生健康委员会
Filing Date
2026-03-13
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing technologies struggle to balance the reliability of analysis results with the auditability of processes in multi-source talent information analysis and management, leading to inconsistent output standards across different business units, a heavy review burden, and hindering the in-depth application of standardization and normalization in talent management.

Method used

By standardizing and unifying personnel identification of multi-source talent data, structured evaluation evidence and probabilistic prediction evidence are generated, and their inconsistency is calculated in parallel. When the credibility is low, supplementary evidence and calibration are triggered to build a set of verifiable evidence, thereby achieving unified generation and traceability support for outputs from both the unit and individual ends.

Benefits of technology

It improved data availability and cross-system reuse capabilities, reduced the cost of manual review and post-event correction, and promoted the in-depth application of digitalization, proceduralization, and standardization in talent management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122240633A_ABST
    Figure CN122240633A_ABST
Patent Text Reader

Abstract

This invention discloses a talent information analysis and management method and system based on big data. It preprocesses multi-source data in the talent information domain to generate standardized talent data and time-series event data associated with a unified personnel identifier. First and second pieces of evidence are generated in parallel using the data. The first piece of evidence is a structured evaluation evidence based on a preset evaluation mechanism, and the second piece of evidence is a probabilistic predictive evidence based on a machine learning model. The inconsistency between the two types of evidence in the output of the target event is calculated and mapped to a credibility level. When the credibility level is lower than a preset condition, a consistency handling instruction is output and executed. Based on the handling result, the two types of evidence and their credibility levels are updated, and a comprehensive evidence set is constructed. Based on the comprehensive evidence set, talent analysis information for the organization and personal development information for the individual are generated respectively. Through dual-evidence consistency assessment and correction, reliable, verifiable, and traceable data output is achieved, reducing verification costs and unifying multi-port perspectives.
Need to check novelty before this filing date? Find Prior Art