Engineering Knowledge Graph for Keyword Discovery in Patent Search

Abstract

Patent retrieval and analytics have become common tasks in engineering design and innovation. Keyword-based search is the most common method and the core of integrative methods for patent retrieval. Often searchers intuitively choose keywords according to their knowledge on the search interest which may limit the coverage of the retrieval. Although one can identify additional keywords via reading patent texts from prior searches to refine the query terms heuristically, the process is tedious, time-consuming, and prone to human errors. In this paper, we propose a method to automate and augment the heuristic and iterative keyword discovery process. Specifically, we train a semantic engineering knowledge graph on the full patent database using natural language processing and semantic analysis, and use it as the basis to retrieve and rank the keywords contained in the retrieved patents. On this basis, searchers do not need to read patent texts but just select among the recommended keywords to expand their queries. The proposed method improves the completeness of the search keyword set and reduces the human effort for the same task.

Mining and Representing the Concept Space of Existing Ideas for Directed Ideation

“…In this paper, the computer recombination was limited within the given concept space built on a specific dataset of prior ideas. In future work, a global knowledge database, such as ConceptNet and WikiData, and engineering design-focused knowledge database, such as the TKG-Technology Knowledge Graph [42][43][44], can be utilized to explore external concepts for combinations with the ones in the given concept space. Although humans do combine concepts beyond the given space as shown in the exercises of this study, the additional concepts focus on the individual human's own longterm memory and experiences rather than a global knowledge database.…”

Idea generation with Technology Semantic Network

“…In a benchmark comparison with other existing semantic network databases including WordNet, ConceptNet, and B-link (Shi et al, 2017), TechNet presented superior performances in terms of retrieval and inference tasks in the specific context of technology and engineering (Sarica et al, 2020). TechNet has been utilized to augment patent search (Sarica et al, 2019a), technology forecasting (Sarica et al, 2019b), and idea evaluation (Han et al, 2020a(Han et al, , 2020b.…”

Semantic Networks for Engineering Design: A Survey

“…In a benchmark comparison with other existing semantic network databases, including WordNet, ConceptNet, and B-Link, TechNet presented superior performances in term retrieval and inference tasks in the specific context of technology and engineering (Sarica et al, 2020). TechNet has been utilized to augment patent search (Sarica et al, 2019a), technology forecasting (Sarica et al, 2019b), idea generation (Sarica et al, 2021) and evaluation (Han et al, 2020) Table 2 summarizes the engineering design studies using semantic networks, highlighting the semantic networks employed and their applications. The (Goel et al, 2012) WordNet Concept association and expansion (Linsey et al, 2012) Executing queries (Siddharth and Chakrabarti, 2018) WordNet and FBS (Function-Behaviour-Structure) knowledge cell library Knowledge retrieval (Hu et al, 2017) WordNet and word2vec…”

“…Triplets classification (Cheong et al, 2017) ConceptNet Knowledge retrieval and reasoning (Yuan and Hsieh, 2015) Concept association and expansion (Han et al, 2018a) Knowledge retrieval and reasoning (Han et al, 2018b) Query expansion; ideation aid (Chen and Krishnamurthy, 2020) Hand-built extracting thematic relations in domain-specific knowledge Knowledge retrieval and reasoning (Georgiev et al, 2017) Total technology space map (TSM) Knowledge retrieval and reasoning (Luo et al, 2018; B-Link Cross-domain knowledge associations (Chen et al, 2019) TechNet Prior art search, design knowledge discovery and representation, idea generation and evaluation (Sarica et al, 2019a;2019b;Han et al, 2020) SAPPhIRE model ontology Knowledge retrieval (Acharya and Chakrabarti, 2020)…”