In today’s knowledge-based society, industry-university cooperation (IUC) is recognized as an effective tool for technological innovation. Many studies have shown that selecting the right partner is essential to the success of the IUC. Although there have been a lot of studies on the criteria for selecting a suitable partner for IUC or strategic alliances, there has been a problem of making decisions depending on the qualitative judgment of experts or staff. While related works using patent analysis enabled the quantitative analysis and comparison of potential research partners, they overlooked the fact that there are several sub-technologies in one specific technology domain and that the applicant’s research concentration and competency are not the same for every sub-technology. This study suggests a systematic methodology that combines the Latent Dirichlet Allocation (LDA) topic model and the clustering algorithm in order to classify the sub-technology categories of a particular technology domain, and identifies the best college partners in each category. In addition, a similar-patent density (SPD) index was proposed and utilized for an objective comparison of potential university partners. In order to investigate the practical applicability of the proposed methodology, we conducted experiments using real patent data on the electric vehicle domain obtained from the Korean Intellectual Property Office. As a result, we identified 10 research and development sectors wherein Hyundai Motor Company (HMC) focuses using LDA and clustering. The universities with the highest values of SPD for each sector were chosen to be the most suitable partners of HMC for collaborative research.

Patent litigation occurs when a company’s product or service violates the scope of another company’s patent rights. When they occur, companies suffer a disruption to the sales of their products and services, thus hindering the sustainability of their business activities. For this reason, companies have established and analyzed wide-ranging strategies to prevent patent litigation. Of those, statistical and machine learning-based quantitative methods using patent big data have several advantages, such as a reduced cost and objective results. Existing quantitative methods analyze patent information and litigation based on the time of data collection. However, the values of patents and their litigation hazards change over time. In addition, the existing methods do not take into account censored data; that is, patents that may result in litigation after the data is collected. In this paper, to solve this problem we propose an integrated survival model that considers censored data and predicts patent litigation hazards over time. The proposed model is a non-parametric survival analysis method based on a random survival forest. It uses pre-trained word2vec and clustering to effectively reflect the technology fields as well as the quantitative information of the patent. The word2vec is a technique for natural language processing and enables the use of patent text information. In order to examine the practicality of the integrated survival model, an experiment is conducted with patent big data related to sensor semiconductors based on AI technology applicable to robotics. In the experiment, it was found that the litigation hazard occurred 150 months after the patent application and increase rapidly from 200 months. Furthermore, the proposed model showed better predictive performance than other survival analysis models. The proposed model could be used by potential defendants to protect their patents.

Companies and research institutes are acquiring monopolized technologies through patents to survive in a rapidly changing market. The applicant is guaranteed by law the exclusive right to the technology for a certain period. A prior art search is an essential task for this purpose. Therefore, the need for a successful prior art search is increasing. Previous studies have disadvantages because relevant fields are limited, requiring an in-depth understanding of specific technologies. This paper proposes a method to overcome these limitations using patent text and citation information. The proposed method searches for prior art using a citation network based on the shortest path derived from a breadth-first search. We examined based on experiments whether the proposed method could be applied to the industry. Based on the results, the proposed algorithm can efficiently search for prior art. Furthermore, it was possible to construct a counterstrategy based on the characteristics of the applicant. The code will be made available at github.com/lee-ju/k_step_PIC.

This paper proposes a multi-class classification model for technology evaluation (TE) using patent documents. TE is defined as converting technology quality to its present value; it supports efficient research and development using intellectual property rights–research & development (IP–R&D) and decision-making by companies. Through IP–R&D, companies create their patent portfolios and develop technology management strategies. They protect core patents and use those patents to cooperate with other companies. In modern society, as conversion technology has been rapidly developed, previous TE methods became difficult to apply to technology. This is because they relied on expert-based qualitative methods. Qualitative results are difficult to use to guarantee objectivity. Many previous studies have proposed models for evaluating technology based on patent data to address these limitations. However, those models can lose contextual information during the preprocessing of bibliographic information and require a lexical analyzer suitable for processing terminology in patents. This study uses a lexical analyzer produced using a deep learning structure to overcome this limitation. Furthermore, the proposed method uses quantitative information and bibliographic information of patents as explanatory variables and classifies the technology into multiple classes. The multi-class classification is conducted by sequentially evaluating the value of a technology. This method returns multiple classes in order, enabling class comparison. Moreover, it is model-agnostic, enabling diverse algorithms to be used. We conducted experiments using actual patent data to examine the practical applicability of the proposed methodology. Based on the experiment results, the proposed method was able to classify actual patents into an ordered multi-class. In addition, it was possible to guarantee the objectivity of the results. This is because our model used the information in the patent specification. Furthermore, the model using both quantitative and bibliographic information exhibited higher classification performance than the model using only quantitative information. Therefore, the proposed model can contribute to the sustainable growth of companies by classifying the value of technology into more detailed categories.

Outliers that deviate from a normal distribution are typically removed during the analysis process. However, the patterns of outliers are recognized as important information in the outlier detection method. This study proposes a technology trend screening framework based on a machine learning algorithm using outliers. The proposed method is as follows: first, we split the dataset by time into training and testing sets for training the Doc2Vec model. Next, we pre-process the patent documents using the trained model. The final outlier documents are selected from the preprocessed document data, through voting for the outlier documents extracted using the IQR, the three-sigma rule, and the Isolation Forest algorithm. Finally, the technical topics of the outlier documents extracted through the topic model are identified. This study analyzes the patent data on drones to describe the proposed method. Results show that, despite cumulative research on drone-related hardware and system technology, there is a general lack of research regarding the autonomous flight field.

The sustainable growth of a company requires a differentiated research and development strategy through the discovery of technology opportunities. However, previous studies fell short of the need for utilizing outlier keywords, based on approaches from various perspectives, to discover technology opportunities. In this study, a technology opportunity discovery method utilizing outlier keywords is proposed. First, the collected patent data are divided into several subsets, and outlier keywords are derived using the W2V and LOF. The derived keywords are clustered through the K-means algorithm. Finally, the similarity between the clusters is evaluated to determine the cluster with the most similarity as a potential technology. In this study, 5679 cases of unmanned aerial vehicle (UAV) patent data were utilized, from which three technology opportunities were derived: UAV defense technology, UAV charging station technology, and UAV measurement precision improvement technology. The proposed method will contribute to discovering differentiated technology fields in advance using technologies with semantic differences and outlier keywords, in which the meaning of words is considered through W2V application.