Method for analyzing matching degree between demand and output result based on text semantics

Through a method based on text semantic analysis, combined with the Bert model and knowledge distillation technology, the problem of calculating the matching relationship of scientific research projects is solved, and fast and efficient project correlation calculation is realized, helping enterprises to screen high-quality projects in the bidding process and reducing resource consumption. Consumption and risk of manual judgment errors.

CN111309871AActive Publication Date: 2020-06-19PUHUA XUNGUANG (BEIJING) TECH CO LTD +1
8 Cites 13 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
PUHUA XUNGUANG (BEIJING) TECH CO LTD
Filing Date
2020-03-26
Publication Date
2020-06-19

AI Technical Summary

⚠Technical Problem

The existing technology is difficult to effectively calculate the matching relationships between scientific research projects, resulting in inconsistent research needs and pre-research project research directions, inconsistent research purposes, limited manual determination, high resource consumption, and prone to unclear identification of project relationships.

⚗Method used

Using a method based on text semantic analysis, through data set annotation, Bert model preprocessing, single-parameter model training and multi-parameter model prediction result integration, combined with knowledge distillation, cross-validation and integrated learning, to build a match between project requirements and results. Calculate the model, use the Rough-L algorithm to extract core information, and reduce overfitting through temperature adjustment and cross-validation.

🎯Benefits of technology

It realizes the quick and efficient calculation of project correlation matching degree, reduces the difficulty of project screening, reduces resource investment, and helps enterprises screen high-quality projects with high matching degree in the project bidding process.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a method for analyzing a matching degree between a demand and an output result based on text semantics. The method comprises the following steps: step 1, labeling a data set; step 2, technical document preprocessing; 3, training and predicting a single-parameter model; 4, integrating prediction results of the multi-parameter model; the method has the beneficial effects thatthe method is simple; deep learning and the NLP technology are applied to the field of project association degree calculation of enterprise project management for the first time. Calculating an association matching degree between the two projects according to project requirements and result description; the associated project positioning difficulty is effectively reduced; meanwhile, the demand side can be helped to quickly and efficiently locate high-quality projects adapting to the demand of the demand side; time and resource investment for achievement screening and matching are greatly reduced, the association matching degree between projects is calculated by means of text data of existing project achievement technical documents and project declaration guidelines, and then large enterprises are assisted in screening high-quality projects with the high matching degree in the project bidding and tendering link.
Need to check novelty before this filing date? Find Prior Art