An automatic classification method for patents

Xue, Changhu; Qiu, Qingying; Feng, Peng; Yao, Zhen-Nong

doi:10.1109/fskd.2010.5569326

Cited by 4 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, several parts in patent should be selected to represent the technical information. Chi Xue [8] found that selecting title, abstract and technical field as the patent innovation parts has the best classification results by the patent parts selection tests and analysis. Actually patent retrieval is similar to classification.…”

Section: Retrieval Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Patent Retrieval Method Based on Similarity Calculation of a Single Patent

Qiu¹,

Yao²,

Ji³

et al. 2017

dtcse

View full text Add to dashboard Cite

For reverse engineering or infringement avoiding design, designers have to access relevant patents efficiently and accurately based on a specific patent (referred to "the target patent" below) in hand. A retrieval method based on a single patent is proposed. A batch of patents (referred to "the preliminary patents" below) is obtained by the keywords retrieval and retrieved again using the target patent. Then the most similar patents to the target patent are acquired by similarity calculation and sorted by the values. The effect of keyword form and its location on the similarity calculation is considered. The efficiency and accuracy of the improved algorithm are verified by tests.

show abstract

Section: Retrieval Methodsmentioning

confidence: 99%

“…After adding the position weight, standardize the improved weight by the formula (4), (5) and then calculate the improved similarity through the formula (8).…”

Section: Retrieval Methodsmentioning

confidence: 99%

Patent Retrieval Method Based on Similarity Calculation of a Single Patent

Qiu¹,

Yao²,

Ji³

et al. 2017

dtcse

View full text Add to dashboard Cite

show abstract

“…Based on the analysis of patent text, it is found that the training of the automatic patent classifier can be completed by extracting a few representative contents of patent documents, which can improve the PAC efficiency while maintaining the accuracy of PAC. Relevant research results show that satisfactory accuracy can be achieved by extracting the contents of patent abstract [6] or claims [7] in the tasks of patent classification. Therefore, this paper uses the titles and abstracts of patent documents to form the input data for training, and then uses the corresponding 'sections' or 'classes' labels to construct the target samples for PAC.…”

Section: Introductionmentioning

confidence: 99%

Patent Automatic Classification Based on Symmetric Hierarchical Convolution Neural Network

Zhu

Fang

et al. 2020

Symmetry

View full text Add to dashboard Cite

With the rapid growth of patent applications, it has become an urgent problem to automatically classify the accepted patent application documents accurately and quickly. Most previous patent automatic classification studies are based on feature engineering and traditional machine learning methods like SVM, and some even rely on the knowledge of domain experts, hence they suffer from low accuracy problem and have poor generalization ability. In this paper, we propose a patent automatic classification method via the symmetric hierarchical convolution neural network (CNN) named PAC-HCNN. We use the title and abstract of the patent as the input data, and then apply the word embedding technique to segment and vectorize the input data. Then we design a symmetric hierarchical CNN framework to classify the patents based on the word embeddings, which is much more efficient than traditional RNN models dealing with texts, meanwhile keeping the history and future information of the input sequence. We also add gated linear units (GLUs) and residual connection to help realize the deep CNN. Additionally, we equip our model with a self attention mechanism to address the long-term dependency problem. Experiments are performed on large-scale datasets for Chinese short text patent classification. Experimental results prove our proposed model’s effectiveness, and it performs better than other state-of-the-art models significantly and consistently on both fine-grained and coarse-grained classification.

show abstract

“…It is usually assumed in these methods that the document set consists of general documents with flat labels. Even though these methods have also been used to select features for patent documents with IPC labels [11, 12], they still utilize general class labels with a flat structure. For example, Tseng et al [11] used categories such as ‘FED’ and ‘Device’ to calculate the value of the correlation coefficient.…”

Section: Introductionmentioning

confidence: 99%

“…For example, Tseng et al [11] used categories such as ‘FED’ and ‘Device’ to calculate the value of the correlation coefficient. Xue et al [12] classified patents into four categories: ‘controlling and regulating device’, ‘cylinder and motor device’, ‘muffle and shock absorption device’ and ‘safety device’ in their experiment. The unique hierarchical feature of the system has never previously been considered as a way to improve classification accuracy for the upper or all levels.…”

Section: Introductionmentioning

confidence: 99%

Vector space model for patent documents with hierarchical class labels

Chen

Chiu

2012

Journal of Information Science

View full text Add to dashboard Cite

A vector space model (VSM) composed of selected important features is a common way to represent documents, including patent documents. Patent documents have some special characteristics that make it difficult to apply traditional feature selection methods directly: (a) it is difficult to find common terms for patent documents in different categories; and (b) the class label of a patent document is hierarchical rather than flat. Hence, in this article we propose a new approach that includes a hierarchical feature selection (HFS) algorithm which can be used to select more representative features with greater discriminative ability to present a set of patent documents with hierarchical class labels. The performance of the proposed method is evaluated through application to two documents sets with 2400 and 9600 patent documents, where we extract candidate terms from their titles and abstracts. The experimental results reveal that a VSM whose features are selected by a proportional selection process gives better coverage, while a VSM whose features are selected with a weighted-summed selection process gives higher accuracy.

show abstract

An automatic classification method for patents

Cited by 4 publications

References 21 publications

Patent Retrieval Method Based on Similarity Calculation of a Single Patent

Patent Retrieval Method Based on Similarity Calculation of a Single Patent

Patent Automatic Classification Based on Symmetric Hierarchical Convolution Neural Network

Vector space model for patent documents with hierarchical class labels

Contact Info

Product

Resources

About