Intelligent task allocation and personnel scheduling method and system for geographic website

Abstract

The invention discloses an intelligent visit task allocation and personnel scheduling method and system for websites with certain geographical location characteristics. The intelligent visit task allocation and personnel scheduling method comprises the following steps: respectively extracting features of a physical business website and salesmen from basic data and real-time data of an enterprise information system decision module, and modeling historical data of visited websites of the salesmen; representing the connection between the salesman and the website by using a bipartite graph so as to form a visit plan network graph; planning an optimal visit route according to the information of the environment where the salesman is located; using a reinforcement learning method to assess earnings obtained by the allocation strategy according to a preset reward or punishment generated after the salesman executes a certain action, feeding back the earnings to the deep neural network model, repeatedly updating learning parameters, and determining an optimal task matching strategy; and in the actual visiting process, adopting a reinforcement learning method for calculation, iterating a taskexecution strategy optimization method and a visiting route optimization method continuously at the same time, and comprehensively obtaining a globally optimal visiting mode.

Description

technical field [0001] The invention relates to the research field of enterprise information systems, in particular to a method and system for intelligent task distribution and personnel scheduling for geographic network points. Background technique [0002] Information systems are the brains of business operations. With the expansion of enterprise scale and the gradual deepening of enterprise information construction, the depth of management, data and information volume continue to increase. Therefore, relying entirely on manual management system information and enterprise decision-making, enterprise production is far from reaching high efficiency. In particular, there are many simple and high-frequency empirical decision-making problems in the daily operation of enterprises, and there are also a large number of empirical decision-making modules in the information system. Such problems often consume a lot of manpower and do not require too much brainpower, which increases ...

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the existing methods, and to provide a method and system for intelligent task assignment and personnel scheduling for geographical outlets, which can use the user big data accumulated by the enterprise, especially when manual experience is required. In the module of business decision-making, extract business logic rules, model the input and output data of this part of the module, and train the deep neural network, so as to use the neural network to replace manual decision-making, and overcome the high cost and low efficiency of manual decision-making. question

Images