Abstract: With the advent of the Industrial 4. 0 era,the mining industry is also actively exploring intelligent and digital
transformation. The deep integration of emerging technologies such as the Internet of Things and artificial intelligence with paste
filling technology can make the filling process and quality control more precise and efficient,reduce costs and energy consumption,
and is of great significance for further promoting the construction of green mines. Therefore,research has been conducted
on the key issue of the optimal design of the mix ratio in filling decisions,and a precise design method for bidirectional decision-
making filling based on target strength inversion has been proposed. By effectively combining the feedback of simulated annealing
optimization with the forward analysis of machine learning prediction models,as well as the flexible application of filling
strength design theory,a bidirectional decision-making paste mix ratio optimization strategy for filling strength and mix ratio has
been constructed. An optimization decision algorithm based on cost control has been designed,which reduces the most critical
cost accounting indicators in engineering practice to a target linear programming problem,and builds a cost minimization objective
function under multiple constraints,further supporting filling decision support and achieving the re-optimization and rescreening
of paste mix ratio data. Finally,taking the open stoping and subsequent filling mining method of Luodang mining area
as an example,the proposed filling decision-making algorithm was practiced and analyzed. The SLAM Studio software was used
to obtain the stope structural parameters and derive the strength design values. Through simulated annealing and cost control
decision-making,the optimized paste material mix ratio combination was obtained,which not only meets the strength requirements
and transportation conditions but also achieves the economic engineering goal. This indicates that the proposed method
can assist in filling engineering applications economically and efficiently.