Text quality index obtaining method and device

Abstract

The invention discloses a text quality index obtaining method and device. The method comprises the steps of obtaining a name and keywords of a text, generating a text data source, adopting a preset neural network language model for training entries in the text data source to obtain multiple word vectors, determining sentence vectors of multiple sentences, and performing de-weighting on the sentence vectors of the multiple sentences, wherein P-type quality indexes are involved; saving the content corresponding to the sentence vectors of the P-type quality indexes, on the basis of random forest,determining an important degree value of the P-type quality index, and according to the content corresponding to the sentence vectors of the P-type quality indexes and the important degree value of the P-type quality indexes, obtaining details and importance ranks of the quality indexes needing to be evaluated. Sentences of open source software are quantified into the vectors, a quality index setis obtained, the follow-up ranking accuracy is improved, the important degree value of the quality indexes is obtained on the basis of random forest, and the obtained quality index result is more accurate and refined.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of sentence analysis, and in particular, to a method and device for acquiring text quality indicators. Background technique [0002] Wide application of open source software has become a trend. Due to technical maturity and security compliance considerations, the financial industry maintains a cautious attitude towards the application of open source software. Therefore, before using an open source software, a complete and scientific evaluation of the software should be carried out. Usually, open source software is evaluated by establishing an evaluation model, and open source software such as kakfa, rabbitmq, rootwrap, etc. are evaluated based on the model. In the process, we found the following problems: First of all, due to the lack of automated processes and tools, some steps are manually captured, and the selection of each evaluation indicator and corresponding content is very time...

AI Technical Summary

Problems solved by technology

Therefore, before using an open source software, a complete and scientific evaluation of the software should be carried out. Usually, open source software is evaluated by establishing an evaluation model, and open source software such as kakfa, rabbitmq, rootwrap, etc. are evaluated based on the model. In the process, we found the following problems: First of all, due to the lack of automated processes and tools, some steps are manually captured, and the selection of each evaluation indicator and corresponding content is very time-consuming and relatively subjective

The data sources under the existing schemes simply use keywords for clustering, and do not include semantics and contextual associations. Such isolated classifications are not effective in classifying objects that are more abstract or have richer representational meanings. At the same time, it is difficult to classify Longer quantities such as sentences are identified and classified

Images