About Intellectual Property IP Training IP Outreach IP for… IP and... IP in... Patent & Technology Information Trademark Information Industrial Design Information Geographical Indication Information Plant Variety Information (UPOV) IP Laws, Treaties & Judgements IP Resources IP Reports Patent Protection Trademark Protection Industrial Design Protection Geographical Indication Protection Plant Variety Protection (UPOV) IP Dispute Resolution IP Office Business Solutions Paying for IP Services Negotiation & Decision-Making Development Cooperation Innovation Support Public-Private Partnerships The Organization Working with WIPO Accountability Patents Trademarks Industrial Designs Geographical Indications Copyright Trade Secrets WIPO Academy Workshops & Seminars World IP Day WIPO Magazine Raising Awareness Case Studies & Success Stories IP News WIPO Awards Business Universities Indigenous Peoples Judiciaries Genetic Resources, Traditional Knowledge and Traditional Cultural Expressions Economics Gender Equality Global Health Climate Change Competition Policy Sustainable Development Goals Enforcement Frontier Technologies Mobile Applications Sports Tourism PATENTSCOPE Patent Analytics International Patent Classification ARDI – Research for Innovation ASPI – Specialized Patent Information Global Brand Database Madrid Monitor Article 6ter Express Database Nice Classification Vienna Classification Global Design Database International Designs Bulletin Hague Express Database Locarno Classification Lisbon Express Database Global Brand Database for GIs PLUTO Plant Variety Database GENIE Database WIPO-Administered Treaties WIPO Lex - IP Laws, Treaties & Judgments WIPO Standards IP Statistics WIPO Pearl (Terminology) WIPO Publications Country IP Profiles WIPO Knowledge Center WIPO Technology Trends Global Innovation Index World Intellectual Property Report PCT – The International Patent System ePCT Budapest – The International Microorganism Deposit System Madrid – The International Trademark System eMadrid Article 6ter (armorial bearings, flags, state emblems) Hague – The International Design System eHague Lisbon – The International System of Appellations of Origin and Geographical Indications eLisbon UPOV PRISMA Mediation Arbitration Expert Determination Domain Name Disputes Centralized Access to Search and Examination (CASE) Digital Access Service (DAS) WIPO Pay Current Account at WIPO WIPO Assemblies Standing Committees Calendar of Meetings WIPO Official Documents Development Agenda Technical Assistance IP Training Institutions COVID-19 Support National IP Strategies Policy & Legislative Advice Cooperation Hub Technology and Innovation Support Centers (TISC) Technology Transfer Inventor Assistance Program WIPO GREEN WIPO's Pat-INFORMED Accessible Books Consortium WIPO for Creators WIPO ALERT Member States Observers Director General Activities by Unit External Offices Job Vacancies Procurement Results & Budget Financial Reporting Oversight

Index of AI initiatives in IP offices

Patent prior art search

14 record(s) found.

Country / Territory InstitutionBusiness applicationDescription
AustriaThe Austrian Patent OfficePatent prior art search

In early 2018 the Austrian Patent office was trialing several commercial providers for application of AI to pre-search of patents.

CanadaCanadian Intellectual Property Office (CIPO)Patent prior art search

CIPO's Patent Branch uses commercially available semantic AI search engines (Questel, STN, Clarivate Analytics) to assist in conducting searches for prior art and citations. These tools rely on machine learning algorithms to better detect linkages between citations, applications, and the current state of the art.

Patent examiners also make use of Google's algorithms, specifically within their "Translate", "Patent", and "Scholar" tools for machine translation and access to full-text documents and claims forms from contributing international patent offices in real time with citation metrics and related scholarly publications.

For data manipulation CIPO uses the Vantage Point text-mining tool for discovering knowledge in search results from patent and literature databases while providing methods to refine, automate, import, etc. the raw data produced.

ChinaState Administration for Industry and Commerce (SAIC)Patent prior art search

In 2021, CNIPA launched the new intelligent search system and the intelligent semantic search technology was applied in the system. The intelligent search function mainly provides 2 search modes. The first one is the automatic search mode. When the examiner clicks on the "Semantic Search" button,the system will push similar documents, which are sorted by similarity.

The second search mode is semantic sort to Boolean search results. The examiners could do Boolean search and get the results in the first step, and then conduct the semantic sort based on the results. This may help the examiner to view the closest documents, and improve the efficiency of finding reference documents.

European UnionEuropean Patent Office (EPO)Patent prior art search

The EPO has been active in developing business solutions using machine learning and AI for patent searches at various degrees of implementation: Automatic Search of prior art for incoming patent applications; and Automatic generation of queries.

The EPO has generated its own reference data (gold standards) and system for measuring the performance of automated search tools.

The EPO also makes use of commercial products in the automatic annotation area through software providers in different projects.

Related links

FinlandFinnish Patent and Registration Office (PRH)Patent prior art search

A patent search system by Finnish startup IPRally Technologies Ltd. was deployed for all patent examiners at the Finnish Patent and Registration Office in March 2020. We chose the system after comparing it to other AI based patent search systems that could be installed on our own servers, such as IPScreener and Teqmine. The search system by Teqmine Analytics Ltd. was installed on our servers previously (from late 2017 until early 2020), but it was never deployed for all examiners. In addition, we have previously tested other systems, such as InnovationQ Plus.

IPRally's system builds a graph from an input text that typically includes the claims and description of a patent application, where the dependencies between concepts are modeled by the structure of the graph. This graph is input into a Graph Neural Network (GNN), which produces a high-dimensional vector that can be compared to vectors produced from prior art patent documents. The system is trained using a large amount of search report data for patent publications. The output format from the system was customized so that it can be easily transferred into our existing search tools. An examiner can thus analyze whether the prior art publications represented by the closest vectors, i.e. top ranked documents, are actually relevant prior art.

The system performs better than the systems we have previously tested. In real world testing, a prior art document that was eventually used by an examiner to deny novelty or inventive step in the first office action was found among the top 20 ranked documents in more than 40 per cent of the cases. At least in some cases, using the system may thus allow for a faster search or for a better quality search.

The system can also be used to find possible classifications for a patent application by determining the most common classification symbols for the top ranked documents.

GermanyGerman Patent and Trade Mark Office (DPMA)Patent prior art search

In 2016 the DPMA initiated a project for the implementation of a central service for the prior art search in various data sources of the DPMA (e.g. electronic file, specialist databases, etc.). The central service uses algorithms to improve textual similarity search.

JapanJapan Patent OfficePatent prior art search

The JPO is validating its systems to verify possible uses for AI to support conducting prior art searches. (1) Using text data of examined patent documents and the retrieval history of search queries used in the examinations, the JPO is validating a function to suggest keywords and patent classifications that should be included in search queries. (2) Using image data of already filed documents, the JPO is validating functions to retrieve (i) images similar to designated patent image and (ii) images which are of specific types (like flowchart or circuit diagram). (3) Using past results in prior searches of patent, the JPO is validating a function to sort retrieved documents so that examiners can check the most related document first.

(Updated November 2023)

Related links

MoroccoMoroccan Industrial and Commercial Property Office (OMPIC)Patent prior art search

Since 2011, OMPIC uses Orbite Intelligence, a commercially available AI-powered patent analytics tool to searche global patent applications by technical domain or keywords. The map-based tool was introduced to meet the needs of the Moroccan Technology and Innovation Support Center network for searching the state of the art and the precedence of patents.

PhilippinesIntellectual Property Office of the Philippines (IPOPHL)Patent prior art search

IPOPHL uses a third-party search engine called DTSearch for its patent search operations. Similar to all other search engines, the system has the capability to perform incremental index, fuzzy search, and other functions. Although the said system is a low-end of AI, it is more powerful than the traditional database search.

Republic of KoreaKorean Intellectual Property Office (KIPO)Patent prior art search

In April 2017, KIPO established an AI agreement with the Korean Electronics and Telecommunications Research Institute (ETRI). Together they are working to build a patent knowledge base for AI learning and cooperate on research for applying their developed AI system in IP administration.

A pilot model for intelligent patent search is under development with plans to be finalized by 2019. This model enhances the quality of prior art search by moving away from keyword search to a search system based on syntax and semantics.

Related links

Russian FederationFederal Service for Intellectual Property (Rospatent) / Federal Institute of Industrial Property (FIPS)Patent prior art search

Initiatives on the implementation of AI for search were launched in 2017. In 2018 it was put into operation for the examination of applications for inventions and utility models. Patent documents similarity search function implemented in the PatSearch system is being performed through a set of AI methods and techniques in combination with the best world information search practices. Currently the similarity search function operates in the database of Russian patent documents. A neural network trained on Russian patent documents on the criteria that take into account the complexity of the examination procedure and experts' experience is used for the establishment of the Russian distributional thesaurus.

Related links

United KingdomIntellectual Property Office (UKIPO)Patent prior art search

The UKIPO trialed Derwent Innovation, a commercially available patent search tool. The tool comprises a semantic/smart search functionality that allows large amounts of plain text (e.g. claims, description) to be used as a search input. The search tool also has the ability to search non-patent literature alongside patent documents. Further features include the ability to manually set weightings of individual search terms in order to rank results in an answer set.

Related links

United States of AmericaUnited States Patent and Trademark Office (USPTO)Patent prior art search

United States Patent and Trademark Office (USPTO) recently added the new artificial intelligence (AI)-based “Similarity Search” feature to examiners’ Patents End-to-End (PE2E) search suite. This new tool will support the USPTO’s goal to grant more robust and reliable patents by further assisting patent examiners as they search for prior art during the examination process.

United States of AmericaUnited States Patent and Trademark Office (USPTO)Patent prior art search

In early 2018 the USPTO was delivering a proof of concept, Sigma, using machine learning/AI algorithms to search whole documents against a corpus of documents. For this version of Sigma, patent applications were searched against granted patents and pre-grant publications (US only).

Related links