Intelligent vending machine replenishment path optimization scheduling method and system based on artificial intelligence

By using LSTM time series models and multi-vehicle route optimization technology, the problems of insufficient sales forecasting and unstable route optimization in the replenishment scheduling of smart vending machines are solved, achieving efficient and balanced replenishment scheduling and service guarantee.

CN122453286APending Publication Date: 2026-07-24SHANGHAI QUZHI NETWORK TECH CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202610557797.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-24
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing smart vending machine replenishment scheduling suffers from problems such as insufficient accuracy in sales forecasting, lack of quantitative basis for replenishment priority determination, and failure to consider service reliability in route optimization, leading to operational instability and resource waste.

Method used

We use an LSTM time series model to predict product sales, calculate replenishment priority by combining stockout probability, and construct a path optimization objective function by optimizing the multi-vehicle path planning (VRPTW) problem with time windows. We also introduce a stockout penalty mechanism to perform dynamic vehicle scheduling.

Benefits of technology

It improved the accuracy of sales forecasting, enabled resources to be allocated to high-value sites, balanced transportation costs and service reliability, adapted to sudden demand, and enhanced the stability and flexibility of replenishment scheduling.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an intelligent vending machine replenishment path optimization scheduling method and system based on artificial intelligence, and the method comprises the steps: firstly collecting the historical sales data of each vending machine station, carrying out the prediction processing through an LSTM time sequence model, obtaining a commodity sales prediction result, and carrying out the calculation through combining with the stock state of the station to obtain the stockout probability. And according to the sales prediction result and the stockout probability, determining the replenishment priority of each station by using a priority scoring formula, and generating a replenishment plan. A multi-vehicle path planning VRPTW problem with a time window is converted into a quadratic optimization problem based on a replenishment plan, a target function is constructed and solved by combining vehicle capacity and time window constraints, and an optimal replenishment path is obtained. And according to the optimal replenishment path, dynamic scheduling is carried out on replenishment vehicles in combination with vehicle loads and replenishment point conditions, and task allocation and execution management and control are completed. The problems that in the prior art, sales prediction precision is insufficient, replenishment priority judgment lacks quantitative basis, and route optimization does not give consideration to service reliability are solved.
Need to check novelty before this filing date? Find Prior Art