And predicting and analyzing workflow instance time of intelligent office automation system

Abstract

The invention discloses a workflow instance time prediction analysis method for an intelligent office automation system. The invention discloses an intelligent office automation system workflow instance time prediction analysis method, which mainly comprises the following steps of: predicting and analyzing workflow instance time of an intelligent office automation system on the basis of a BPM (Service Process Managency); the method comprises the following steps: establishing an office system environment of a workflow engine, extracting workflow instance time prediction characteristics, predicting workflow instance time based on SVR (Support Vector Regression), recommending a dynamic workflow path, and analyzing and evaluating overtime risks based on a Bayesian network. According to the support vector regression based on data driving, the internal interdependence relationship of the data can be found by learning the known workflow data, so that the prediction and judgment capability ofunknown data is obtained; and the dynamic workflow path recommendation system plans an optimal flow path by using a strategy of dynamically adjusting the weight according to the dynamically changed service flow information, and further improves the working efficiency of the user in combination with risk evaluation.

Description

technical field [0001] The present invention relates to the time prediction and analysis technology of workflow instance in intelligent office automation system, mainly relates to the extraction of workflow instance time prediction feature, the workflow instance time prediction based on support vector regression, the recommendation of dynamic workflow path and the Bayesian network-based Overtime risk analysis and assessment. Background technique [0002] In recent years, with the warming up of the concept of big data and artificial intelligence, more and more enterprises have begun to pay attention to the commercial value contained in the data, and with the increasing maturity of data mining technology, machine learning is widely used in government, finance, communication, medical, The application in multiple industries such as retail is becoming more and more extensive and in-depth. Building data analysis models based on specific business objectives and historical data, and...

AI Technical Summary

Problems solved by technology

Although the existing system has changed the original document processing mode, it has not changed the process of document processing, that is to say, it has not added advanced management methods

Looking at the more commonly used products at present, the functions they can provide basically revolve around the processing of official documents, and their additional functions are far from satisfying us in terms of depth and breadth.

The fundamental reason is that these systems simply process official documents and do not make use of the processed documents, that is to say, they do not accumulate knowledge and cannot provide decision-making and analysis services for enterprises based on the existing information.

Images