Power material demand prediction method based on text information extraction

Abstract

The invention discloses a power material demand prediction method based on text information extraction. The power material demand prediction method includes a two-step algorithm of power material demand prediction, wherein the first step is used for processing a preliminary design document based on the text information extraction technology, and extracting the engineering attribute information which has important value for predicting the demand quantity of main equipment to realize the structural expression of the preliminary design document, and then realizing the requirement prediction of the main equipment by utilizing an SVM regression algorithm. In the second step, the dense vector expression of a primary design document is learned through a convolutional neural network by utilizing atext classification technology, the demand information of the main equipment is fused with the demand information of the main equipment, and the demand of non-main equipment is predicted through a multi-layer neural network. Compared with the existing calculation, the method can be used for predicting various types of materials. The prediction data tend to be actual, the attributes have more expression, and the method has good practicability. The material demand prediction method conforms to actual application requirements, and can be used for predicting the material requirements after the initial design is completed.

Description

technical field [0001] The invention relates to a method for predicting demand for electric power materials based on text information extraction, and belongs to the technical field of demand prediction for electric power materials. Background technique [0002] At present, with the rapid development of my country's social economy, the demand for electric energy has put forward higher requirements both in terms of quantity and quality. On the one hand, these requirements have promoted the prosperity of the power grid engineering (substation and distribution network engineering) market, and on the other hand, they have also posed greater challenges to related companies. Relevant enterprises can only adapt to the new market situation and calmly deal with these new and greater challenges only by using high-tech, especially artificial intelligence technology, to optimize enterprise management and various resource allocation, and improve resource utilization and engineering design...

AI Technical Summary

Problems solved by technology

[0005] It is easy to see from the above existing technologies that although some research and attempts have been made in the forecasting of power material demand, the common problems are that the practicality is poor, the types of materials that can be effectively predicted are limited, and the data on which the forecast is based are too large. Ideally, it is structured data expressed by a few attributes, which is far from the actual application requirements

According to the actual engineering process, material demand forecasting must be carried out immediately after the preliminary design is completed, and the information that can be relied on is only the preliminary design report, and the preliminary design report itself is an unstructured text, and a large number of reports may be embedded in the middle of the text. Extracting various attribute data (that is, obtaining structured data expression) from the text of the structure is extremely challenging, and it is impossible to do it manually

In addition, there are tens of thousands of materials needed for power grid construction, all of which are predicted objects, and it is not practical to predict only a few materials

Images