Skip to main content
ex. data visualization, research paper
  • Social Network Analysis using PatentsView and NetworkX

    The USPTO's Office of Chief Economist developed the InventorAnalyze package for bibliometric (and other) researchers studying the social networks of inventors, i.e., the community of inventors who collaborate on jointly invented patents. The InventorAnalyze package combines disambiguated patent data from the United States Patent and Trademark Office's PatentsView project with social network analysis tools from the Los Alamos National Laboratory's NetworkX library.  PatentsView uses a statistical algorithm for disambiguating patent inventor names, so that multiple variants of a name are assigned a common identifier and distinct inventors having a similar name are assigned separate identifiers. Such entity resolution is critical to identifying inventors and their collaborators over millions of distinct patents.

    By importing disambiguated inventor data from PatentsView into NetworkX, InventorAnalyze enables researchers to more accurately study the entire inventor social network. Moreover, the package facilitates analysis of specific inventor network subgraphs generated via PatentsView API-based queriesInventorAnalyze then leverages NetworkX functionality to study the structure, dynamics, and functions of these inventor subnetworks.

    The team provides two examples of the type of inventor social network analysis facilitated by InventorAnalyze. The first example demonstrates some of the network-level analysis capabilities that InventorAnalyze facilitates. The second example shows the potential information that network-based metrics can convey about individual inventors and their influence.

    The package is a Python script authored by Jesse Frumkin at USPTO and available on GitHub. The full report is here.

  • Accessing patent data with the patentsview package

    Chris Baker, data scientist at the Virginia Tech Applied Research Corporation, developed the patentsview R package that is a wrapper around the PatentsView API. It contains a function that acts as a client to the API (search_pv()) as well as several supporting functions. Full documentation of the package can be found on its website.

    The library offers ways to query the API, process the data, and develop visualizations to track interesting patterns in patenting activity. For analysis examples that go into a little more depth, check out the data applications vignettes on the package's website.

    The R Open Science blog has more details.

  • Patent Data Show That Companies Invent in Very Different Ways

    Scientific American published an article on November 1, 2016, using PatentsView data and visualizations developed by Periscopic who are behind the PatentsView visualization interface and other tools. The U.S. Patent and Trademark Office analyzed patents for employees at three large tech companies: Tesla, Facebook, and Intrexon. The analysis reveals different patterns of collaboration in inventor teams and demonstrates there is more than one way to create success.


  • Worldwide Innovation in Cancer-Related Fields

    The USPTO has developed a new dataset to describe patents and patent applications in cancer-related fields, in support of the US Cancer Moonshot.  By harnessing the power of patent data, and accelerating the process for protecting the intellectual property that lead to cancer research breakthroughs, the USPTO is standing up and doing its part to help bring potentially life-saving treatments to patients, faster.

    The USPTO Cancer Moonshot Patent Data consists of 269,353 patent documents (published patent applications and granted patents) ranging from 1976 to 2016.  USPTO is sharing this dataset with researchers and policy makers, so they might gain insight into innovations in cancer-related research and development.  

    PatentsView is a patent data dissemination platform that uses advanced algorithms to identify inventors and their organizations and locations across 40 years of US patent data.  The PatentsView team used the Cancer Moonshot Patent Data to identify a subset of cancer-related granted patents from their database.   

    The PatentsView team then developed an interactive map to visualize geographic trends in cancer-related innovations over time. Specifically, the map presents the numbers of inventors and patents in cities worldwide, year by year.  It represents 108,923 patents granted between 1976 and 2016 and 127,076 worldwide inventors listed on those patents.

    More information is available at the USPTO Developer Site.

Button sidebar