INTELLIGENT DATA ANALYSIS IN ENTERPRISE MANAGEMENT BASED ON THE ANNEALING SIMULATION ALGORITHM

Abstract

The article considers an analytical review of the annealing simulation algorithm for the
problem of efficient enterprise management. The optimization of the annealing simulation algorithm
for the problem of efficient enterprise management has been carried out. For the analysis of
cases, the optimization of the work schedule of workers in the organization was used. Established
worker scheduling model with strong and weak constraints. The simulated annealing algorithm is
used to optimize the strategy for solving the staff scheduling model. The simulated annealing algorithm
is an algorithm suitable for solving large-scale combinatorial optimization problems. It also
evaluates and obtains the optimal scheduling strategy. The simulated annealing algorithm has a
good effect on the data mining of human resource management. Big data mining can help companies
conduct dynamic analysis in talent recruitment, and the talent recruitment plan is carried out
in a quality and standard way to analyze the characteristics of various talents from many angles
and improve the level of human resource management. An algorithm has been developed that implements
the operation of the annealing simulation algorithm. The simulated annealing algorithm
makes new decisions based on the Metropolis criterion, so in addition to making an optimized
decision, it also makes a reduced decision in a limited range. The Metropolis algorithm is a sampling
algorithm mainly used for complex distribution functions. It is somewhat similar to the variance
sampling algorithm, but here the auxiliary distribution function changes over time. Experimental
studies have been carried out that show that a worker scheduling model based on strong
and weak constraints is significantly better than a manual scheduling model, achieving an effective
balance between controlling wage costs in an organization and increasing employee satisfaction.
The successful application of a workforce scheduling model based on a simulated annealing
algorithm brings new insights and insights to solve large-scale worker scheduling problems.
The results presented can serve as a starting point for studying personnel management systems
based on data mining technology.