A method for automatically dispatching orders for government affairs that integrates grid semantics of processing institutions

Abstract

The present invention provides a method for automatically dispatching orders for government affairs that integrates the grid semantics of the disposal organization, including the following steps: S10. Acquisition of historical data sets of government affairs events; S20. Preprocessing of event data and extraction of semantic features; S30. Prediction of construction of event disposal methods Model: take the historical data set and the geographical location corresponding to the historical data as input, and take the disposal institution code as the final output, and use the deep neural network to construct and train the prediction model; S40. Construct the event disposal institution prediction model; S50. Use training to obtain The prediction model and the prediction model are used to make predictions, and the corresponding event mechanism code that needs to be processed for the event is output. The present invention uses a deep neural network-based model to simultaneously predict the business type and the grid where the disposal institution is located, and can obtain the final disposal institution code through the disposal institution prediction model.

Description

technical field [0001] The invention relates to the technical field of intelligent processing of government hotline events, in particular to a method for automatically dispatching orders for government affairs events that integrates grid semantics of processing institutions. Background technique [0002] With the development of the Internet and big data technology, in order to speed up the construction of a service-oriented government and improve the level of social governance, the construction of hotline service platforms such as 12345 has become an important part of the construction of the "Internet + government service" system. Various online and offline service channels, including , website, WeChat, APP, etc., provide an efficient and convenient communication bridge for the interaction between the government and the people. In a medium-to-large city, the government affairs hotline can generate millions of event data every year. The main content of these data is recorded ...

AI Technical Summary

Problems solved by technology

[0008] Chinese patent document CN108573031A discloses a content-based complaint classification method and system, although it is also a classification process for government affairs hotline texts, but only considers the distribution process of functional departments

In view of the fact that the final judgment of the disposal agency is a highly complex decision-making process, it is difficult to directly use the learning model to completely judge and predict the final disposal agency corresponding to the event based on the above information

In addition, because the existing technology does not have a joint training model that takes into account both business categories and spatial locations, the versatility of the automatic dispatch method between different cities will be limited

Images