Three-Layer Retrieval and Self-Evaluation Classification Method Based on FastText Algorithm

Patent big data serves as a valuable scientific research source for technological innovation, enabling breakthroughs beyond existing knowledge and fostering disruptive ideas. One key challenge in this field is how to efficiently obtain patent documents quickly and accurately. This is a critical focu...

Full description

Saved in:
Bibliographic Details
Main Authors: Yidan Li, Huanhuan Hong, Luhong Wen
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11003909/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850140693497905152
author Yidan Li
Huanhuan Hong
Luhong Wen
author_facet Yidan Li
Huanhuan Hong
Luhong Wen
author_sort Yidan Li
collection DOAJ
description Patent big data serves as a valuable scientific research source for technological innovation, enabling breakthroughs beyond existing knowledge and fostering disruptive ideas. One key challenge in this field is how to efficiently obtain patent documents quickly and accurately. This is a critical focus in the exploration of patent search methodologies. Our approach differs from conventional patent search processes. We have developed a three-level patent classification method that utilizes a multi-step search strategy with specific constraints, alongside an innovative classification system based on the FastText algorithm. By combining these techniques with an emphasis on recall ratio, we can test the efficacy of each level of the database boundaries. This enables swift identification of target patents and allows for focused screening in specific fields, providing robust support for technical or product innovation activities. Furthermore, we applied this method to the retrieval of DBDI patent data, which represents one of the three leading commercial direct ionization ion source technologies globally. Our classification results indicate a remarkable accuracy of 96.97%, reflecting a 21.97% improvement over the TextRNN_Att text algorithm. This effectively demonstrates the success of our proposed methodology. Overall, this study offers a theoretical framework for researching multi-level classification methods in logical retrieval and provides a practical foundation for classifying direct ionization and ionization technologies.
format Article
id doaj-art-e4ae6575fd494c2f80f45afcc0128dfb
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e4ae6575fd494c2f80f45afcc0128dfb2025-08-20T02:29:42ZengIEEEIEEE Access2169-35362025-01-0113871368714810.1109/ACCESS.2025.357010011003909Three-Layer Retrieval and Self-Evaluation Classification Method Based on FastText AlgorithmYidan Li0https://orcid.org/0009-0003-5156-4359Huanhuan Hong1https://orcid.org/0000-0002-7239-8113Luhong Wen2https://orcid.org/0000-0002-0018-7739Research Institute of Advanced Technologies, Ningbo University, Ningbo, ChinaResearch Institute of Advanced Technologies, Ningbo University, Ningbo, ChinaResearch Institute of Advanced Technologies, Ningbo University, Ningbo, ChinaPatent big data serves as a valuable scientific research source for technological innovation, enabling breakthroughs beyond existing knowledge and fostering disruptive ideas. One key challenge in this field is how to efficiently obtain patent documents quickly and accurately. This is a critical focus in the exploration of patent search methodologies. Our approach differs from conventional patent search processes. We have developed a three-level patent classification method that utilizes a multi-step search strategy with specific constraints, alongside an innovative classification system based on the FastText algorithm. By combining these techniques with an emphasis on recall ratio, we can test the efficacy of each level of the database boundaries. This enables swift identification of target patents and allows for focused screening in specific fields, providing robust support for technical or product innovation activities. Furthermore, we applied this method to the retrieval of DBDI patent data, which represents one of the three leading commercial direct ionization ion source technologies globally. Our classification results indicate a remarkable accuracy of 96.97%, reflecting a 21.97% improvement over the TextRNN_Att text algorithm. This effectively demonstrates the success of our proposed methodology. Overall, this study offers a theoretical framework for researching multi-level classification methods in logical retrieval and provides a practical foundation for classifying direct ionization and ionization technologies.https://ieeexplore.ieee.org/document/11003909/Patent retrievalmulti-step search strategytertiary classificationFastText classification algorithmDBDI
spellingShingle Yidan Li
Huanhuan Hong
Luhong Wen
Three-Layer Retrieval and Self-Evaluation Classification Method Based on FastText Algorithm
IEEE Access
Patent retrieval
multi-step search strategy
tertiary classification
FastText classification algorithm
DBDI
title Three-Layer Retrieval and Self-Evaluation Classification Method Based on FastText Algorithm
title_full Three-Layer Retrieval and Self-Evaluation Classification Method Based on FastText Algorithm
title_fullStr Three-Layer Retrieval and Self-Evaluation Classification Method Based on FastText Algorithm
title_full_unstemmed Three-Layer Retrieval and Self-Evaluation Classification Method Based on FastText Algorithm
title_short Three-Layer Retrieval and Self-Evaluation Classification Method Based on FastText Algorithm
title_sort three layer retrieval and self evaluation classification method based on fasttext algorithm
topic Patent retrieval
multi-step search strategy
tertiary classification
FastText classification algorithm
DBDI
url https://ieeexplore.ieee.org/document/11003909/
work_keys_str_mv AT yidanli threelayerretrievalandselfevaluationclassificationmethodbasedonfasttextalgorithm
AT huanhuanhong threelayerretrievalandselfevaluationclassificationmethodbasedonfasttextalgorithm
AT luhongwen threelayerretrievalandselfevaluationclassificationmethodbasedonfasttextalgorithm