Development of a Patent Retrieval and Analysis Platform – A hybrid approach

Liu, Su-Houn; Liao, Hsiu-Li; Pi, Shih-Ming; Hu, Jingwen

doi:10.1016/j.eswa.2010.12.114

Cited by 35 publications

(21 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen and Chi [3] used the International Patent Classification (IPC) codes to weight terms by their categories. Liu et al [12] proposed to use a hybrid approach using both the text of a patent document and bibliographic data. Their results showed that the combination of the bibliographic data matching and text mining results gives the best recall result.…”

Section: Related Workmentioning

confidence: 99%

Cv-PCR

Lei

Lee

et al. 2013

Proceedings of the 22nd ACM International Conference on Conference on Information &Amp; Knowledge Management - CIKM '13

View full text Add to dashboard Cite

Patent citation recommendation and prior patent search, critical for patent filing and patent examination, have become increasingly difficult due to the rapidly growing number of patents. Unlike paper citations that focus on reference comprehensiveness, patent citations tend to be more parsimonious and refer only to those prior patents bearing significant technological and/or economic value, as they define the scope of the citing patent and thus have significant legal and economic implications. Based on the insight that patent citations are important information reflecting the value of cited patents to the citing patent, we propose a heterogeneous patent citation-bibliographic network that combines patent citations (reflecting value relation) and bibliographic information (reflecting similarity relation) together. From this network, we extract various features that reflect the value of a prior patent to a query patent with regard to the context of the query patent such as its assignee, classifications, etc. We then propose a two-stage framework for patent citation recommendation. Our idea is that by exploiting those context-specific value measures of candidate patents to the query patent, the proposed framework is able to make effective patent citation recommendations. We evaluate the proposed context-guided value-driven framework using a collection of 1.8M U.S. patents. Experimental results validate our ideas and show that those value-driven features are very effective and significantly outperform two state-of-the-art methods in terms of both the precision and recall rates.

show abstract

Section: Related Workmentioning

confidence: 99%

Cv-PCR

Lei

Lee

et al. 2013

Proceedings of the 22nd ACM International Conference on Conference on Information &Amp; Knowledge Management - CIKM '13

View full text Add to dashboard Cite

show abstract

“…Classifying patents into predesigned categories makes patent searching and retrieving much easier, which thus improves the success of technology transfer. Liu et al [23] developed the Patent Retrieval and Analysis Platform, which matches fields of patents and identifies similar patents based on bibliographic pattern discovery and text mining approaches. Shih and Liu [38] proposed a network based classification approach that firstly constructs ontology network and then identifies k-nearest neighbors and patent classes.…”

Section: Related Work 21 Technology Transfermentioning

confidence: 99%

Facilitating Technology Transfer by Patent Knowledge Graph

Deng¹,

Huang²,

Zhu³

2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Technologies are one of the most important driving forces of our societal development and realizing the value of technologies heavily depends on the transfer of technologies. Given the importance of technologies and technology transfer, an increasingly large amount of money has been invested to encourage technological innovation and technology transfer worldwide. However, while numerous innovative technologies are invented, most of them remain latent and un-transferred. The comprehension of technical documents and the identification of appropriate technologies for given needs are challenging problems in technology transfer due to information asymmetry and information overload problems. There is a lack of common knowledge base that can reveal the technical details of technical documents and assist with the identification of suitable technologies. To bridge this gap, this research proposes to construct knowledge graph for facilitating technology transfer. A case study is conducted to show the construction of a patent knowledge graph and to illustrate its benefit to finding relevant patents, the most common and important form of technologies.

show abstract

“…A number of such techniques have been used not only to generate an analytic measure of the extent to which different patents are similar in content [48,76] but also to create a visual representation of the relationships inherent in the patent data [38,72,81]. There also can be value in applying a clustering or categorization technique to the data in order to extract significant characteristics about the relationships between the different patents [10,45,74].…”

Section: Related Literaturementioning

confidence: 99%

Creating a Taxonomy for Mobile Commerce Innovations Using Social Network and Cluster Analyses

Khansa

Zobel

Goicochea

2012

International Journal of Electronic Commerce

View full text Add to dashboard Cite

Increasing numbers of people are spending time focused on "the third screen" of a mobile device. Through ubiquitous connectivity, personalization, and affordability, such mobile devices have become much more than just entertainment handsets.In particular, e-commerce has harnessed the power of wireless computing to expand to mobile commerce (m-commerce), thus providing consumers with commercial services on the go. Because such services are often driven by customer input, it is important to consider the relevance of consumers to the development of new service offerings. We therefore dissect innovations in m-commerce by conducting a textual analysis of all filed m-commerce patent applications (over 2,300 in total). By using social network analysis and cluster analysis, we subsequently capture the focal innovation areas in m-commerce and develop a corresponding taxonomy of these innovations. The results clearly illustrate the importance of consumer empowerment and co-creation in the context of m-commerce innovations.KEY WORDS AND PHRASES: Cluster analysis, co-creation, empowerment, innovation, mobile commerce, social network analysis, taxonomy.Mobile commerce, or m-commerce, is considered by many to be the next wave of electronic commerce (e-commerce) [44]. Because mobile devices such as cell phones, personal digital assistants (PDAs), and other handheld computers offer real-time communication and anytime-anywhere access, they can provide an important platform for such services as financial transactions (e.g., e-banking, buying, selling, payments, coupons), location-based queries (e.g., map services, traffic advisories), entertainment (e.g., gaming, ticketing), education, health care, inventory management and tracking, and even enterprise resource planning [25]. Skiba et al. captured this versatile nature of m-commerce by defining it as the "use of mobile devices to communicate, inform, transact" and entertain "using text and data via connection to public or private networks" [68, p. 8].As with many other new technologies, the promise of m-commerce initially outpaced the actual delivery of m-commerce applications and services. As noted by Liang and Wei in their introduction to the 2004 special issue of the International Journal of Electronic Commerce on "Mobile Commerce Applications," although m-commerce is "a promising technology for driving the second wave of e-commerce" [44, p. 15], "many attempts in m-commerce have so far failed to meet expectations" [44, p. 7]. Since that time, however, progress has been made toward fulfilling those early expectations. For example, more recent forecasts indicate that global retail m-commerce will reach $119 billion per year by 2015 (the equivalent of 8 percent of the total e-commerce market) [66].In 2003, Jarvenpaa et al. projected that "the success of m-commerce services is likely to depend on how flexible and malleable the technology is to all users to shape it to their individual and group needs in various social and business Downloaded by [New York University] at 21:

show abstract

Development of a Patent Retrieval and Analysis Platform – A hybrid approach

Cited by 35 publications

References 11 publications

Cv-PCR

Cv-PCR

Facilitating Technology Transfer by Patent Knowledge Graph

Creating a Taxonomy for Mobile Commerce Innovations Using Social Network and Cluster Analyses

Contact Info

Product

Resources

About