Document intelligent distribution system and distribution method

Abstract

The invention provides an intelligent document distribution system and a distribution method. The method includes the steps of setting a feature set of a document; carrying out word segmentation on the document to obtain the feature items with word as a unit; constructing eigenvectors of each document by using vector space model, the eigenvectors being obtained by word frequency- inverse documentfrequency; constructing a classification model based on eigenvectors, taking the correct history distribution documents as training set and test set, the training set training the classification modeland the test set evaluating the classification model; pre-judging the new document according to the trained classification model, wherein the occurrence probability of each feature item of the new document in each distribution department is obtained through the eigenvector matrix, and the distribution probability of the new document being distributed to each department is obtained according to the priori probability of each distribution department obtained through the training. Through spark big data processing technology, the calculation speed is fast, the compatibility is good, the processing efficiency of the system is improved, and the method has high accuracy.

Description

technical field [0001] The present invention relates to the technical field of document processing, and more specifically, to an intelligent document distribution system and a distribution method. Background technique [0002] With the wide application of machine learning algorithms and deep learning algorithms, more and more fields are closely integrated with related technologies, bringing effective ways to solve a series of problems caused by manual processing. [0003] At present, official documents need to be distributed to the most relevant processing department according to the distribution unit and the specific content of the document to complete the docking and communication of job responsibilities. However, nowadays, such problems are handled through manual supervision and processing. This method strongly relies on Personal experience and knowledge, while dealing with inefficiency, will directly lead to further progress in the distribution of related official docume...

AI Technical Summary

Problems solved by technology

[0003] At present, official documents need to be distributed to the most relevant processing department according to the distribution unit and the specific content of the document to complete the docking and communication of job responsibilities. However, nowadays, such problems are handled through manual supervision and processing. This method strongly relies on Personal experience and knowledge, while dealing with inefficiency, which will directly lead to further progress in the distribution of related documents

Images