Applying Deep Learning Technologies to Evaluate the Patent Quality with the Collaborative Training

Abstract

As the country vigorously promotes the development of science and technology and tries to enhance independent innovation capabilities, more and more attention is paid on the protection of technology ownership. In recent years, China has developed rapidly in many scientific and technological fields, and the number of patent applications increased year by year. However, various patent quality problems including immature patent technology and low patent authorization rate appear. The indicators of patent quantification and quality evaluation are studied in this paper. First, we quantify the patent quality evaluation indicators and combine the content of the patent text to build a patent evaluation model. US patents with patent grade labels are used for training with multitask learning technology. Second, the evaluation model is transferred from the English patents to the Chinese patents, in which the active learning technology and transfer learning technology are used to minimize the work of manual labeling. Finally, a Chinese patent quality evaluation model based on collaborative training was designed and implemented. Methods used in this experiment have notably improved the prediction effect of the model and achieved a better migration effect. A large number of experimental results show that the Chinese patent quality evaluation model has achieved good evaluation results. This research uses deep learning and natural language processing technology to carry out research on patent quality evaluation models from different perspectives, to provide patent decision support for related companies, and to point out research directions for research institutions and patent inventors.

Evaluation and cultivation method of high-tech value patents for mechanical products

“…Weight W j of each evaluation indicator is decided by Formulas ( 11) and (12). Weights of evaluation indicators are shown in Table 5.…”

“…From the market perspective, high value patents can bring high benefit returns to their affiliated enterprises [ 11 ]. You [ 12 ] studied the patent value evaluation model from a technical perspective in combination with the content of the patent text, and the automated evaluation process using deep learning and NLP techniques can effectively reduce the workload of manual annotation. Gong [ 13 ] described the innovation value chain in terms of universities operating patents, and the study concluded that university patent commercialization activities can effectively feed back the innovation value of patents.…”

New directions of digitally driven S&T evaluation

“…The scale of big data in the science of science proliferates and gives rise to numerous data-driven S&T evaluation methods. For example, You et al (2021) introduced deep learning to evaluate patent quality. Also, Ren & Zhao (2021) applied regression analysis and heuristic algorithms to patent-based technology opportunity discovery.…”

A patent quality evaluation model based on ALBERT and BiGRU

“…Due to the difficulty in quantifying the evaluation criteria for Chinese patents and the lack of Chinese patent datasets, there has been relatively little research on the evaluation models for Chinese patent quality. Early methods for patent quality evaluation included traditional machine learning algorithms such as Support Vector Machines and Backpropagation Neural Networks [1]. These traditional approaches relied on manual feature extraction and selection, while deep learning methods have improved the accuracy of evaluation by learning the feature representations from a large amount of patent data [2].…”