A Literature Review on Patent Information Retrieval Techniques

Khode, Alok; Jambhorkar, Sagar

doi:10.17485/ijst/2017/v10i37/116435

Cited by 12 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our focus, in contrast, is broader, comprising all types of visualization methods that provide benefits for the analysis of scientific documents and patents. Alok Khode et al [6] considering the various techniques and frameworks available and their limitations, there is a lot of scope in the field of patent retrieval techniques which makes room for further research to be taken up in this domain. Longhui Zhang ET AL [7] introduces the recent development in the field of patent mining, it is still far away from being explored in research area.…”

Section: IImentioning

confidence: 99%

A Survey on Patent Analysis

Deshmukh¹

2019

IJRASET

View full text Add to dashboard Cite

In competitive business patents are crucial analytical benefit. They are determined as gold mine if it is fetched, analyzed and deploy properly. Patent search and analysis are the key step in the patent process and relevant patent may cause expensive legal consequences. In today's world patent collection is enhancing speedily, retrieval of this huge knowledge and information source has become inconvenient and exhaustive. Work mainly glance at literatures dealing with retrieval of patent text and its analysis. Literature review presents various research works that have been carried out to yield better results in patent analysis task.

show abstract

Section: IImentioning

confidence: 99%

A Survey on Patent Analysis

Deshmukh¹

2019

IJRASET

View full text Add to dashboard Cite

show abstract

“…Prior art search helps patent examiners to check the novelty and validity of a claimed work [5]. Rise in the availability of patent related information and increase in the need to access this information, encourage researchers in the Information Retrieval (IR) domain to develop techniques for efficient and effective patent retrieval [6]. The retrieved information can be of help to various types of users like patent professionals, industrial and academic research communities.…”

Section: Introductionmentioning

confidence: 99%

“… Patents are multi-page, multi-topic, multi-modal, multi-language and semi-structured document. Patent retrieval is performed on diverse and large volumes of data [6].  Use of vague, domain specific terminology, inventor specific non-standard acronyms/terms, presence of synonyms, homonyms and techno-legal words in patent document make the traditional keyword based search less effective [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Effect of Technical Domains and Patent Structure on Patent Information Retrieval

Khode¹,

Jambhorkar²

2019

IJEAT

Self Cite

View full text Add to dashboard Cite

Patents are critical intellectual assets for any competitive business. With ever increasing patent filings, effective patent prior art search has become an inevitably important task in patent retrieval which is a subfield of information retrieval (IR). The goal of the prior art search is to find and rank documents related to a query patent. Query formulation is a key step in prior art search in which patent structure is exploited to generate queries using various fields available in patent text. As patent encodes multiple technical domains, this work argues that technical domains and patent structure have their combined effect on the effectiveness of patent retrieval. The study uses international patent classification codes (IPC) to categorize query patents in eight technical domains and also explores eighteen different combination of patent fields to generate search queries. A total of 144 extensive retrieval experiments have been carried out using BM25 ranking algorithm. Retrieval performance is evaluated in terms of recall score of top 1000 records. Empirical results support our assumption. A two-way analysis of variance is also conducted to validate the hypotheses. The findings of this work may be helpful for patent information retrieval professionals to develop domain specific patent retrieval systems exploiting the patent structure.

show abstract

End to End Neural Retrieval for Patent Prior Art Search

Stamatis

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This research will examine neural retrieval methods for patent prior art search. One research direction is the federated search approach, where we proposed two new methods that solve the results merging problem in federated patent search using machine learning models. The methods are based on a centralized index containing samples of documents from all potential resources, and they implement machine learning models to predict comparable scores for the documents retrieved by different resources. The other research direction is the adaptation of end-to-end neural retrieval approaches to the patent characteristics such that the retrieval effectiveness will be increased. Off-the-self neural methods like BERT have lower effectiveness for patent prior art search. So, we adapt the BERT model to patent characteristics in order to increase retrieval performance. We propose a new gate-based document retrieval method and examine it in patent prior art search. The method combines a first-stage retrieval method using BM25 and a re-ranking approach where the BERT model is used as a gating function that operates on the BM25 score and modifies it according to the BERT relevance score. These experiments are based on two-stage retrieval approaches as neural models like BERT requires lots of computing power to be used. Eventually, the final part of the research will examine first-stage neural retrieval methods such as dense retrieval methods adapted to patent characteristics for prior art search.

show abstract

A Literature Review on Patent Information Retrieval Techniques

Cited by 12 publications

References 1 publication

A Survey on Patent Analysis

A Survey on Patent Analysis

Effect of Technical Domains and Patent Structure on Patent Information Retrieval

End to End Neural Retrieval for Patent Prior Art Search

Contact Info

Product

Resources

About