Seravia » Technology API

Many of our clients need to find people and companies based on a specific academic field, technology or skillset. This helps them recruit, find partners and monitor competitors.

Unfortunately searching for a particular technology is more complex than just entering a keyword. Technologies can be described by many terms and many high-level technologies are composed of other technologies. For this reason we have clustered inventions around common technology terms. This allows clients to perform sophisticated searches without iterating through many keywords.

We have mined government documents to identify millions of technologies, their related technologies, their owners and their inventors.

We are now making these details available for use in other applications or data research projects through an easy-to-use Technology API.

Overview

Let’s say you wanted to find out more about graphene, a promising nanotech material. Specifically you want to find companies who are working on it (e.g. “Samsung”), important researchers (e.g., “Hyeon Jin Shin”), important academic institutions (e.g. “University of California”) and publications (e.g. “Formation of Carbon-Containing Material”).

Using the Technology API you can submit a technology phrase and get in return a list of companies, people, related technologies and publications.

Request

All of the Data APIs are RESTful and return JSON.

Domain

Each Data API uses our company domain and a dedicated “api” subdomain:

http://api.seravia.com

Version

Our Data APIs will roll out gradually and the semantics are likely to change as we add features and increase the datatypes we support. For this reason all current requests should use the “v1″ prefix:

http://api.seravia.com/v1

Action

The Technology API uses a single action called “techs”. This will return related technologies, companies, people and publications for a single technology.

http://api.seravia.com/v1/techs

Parameters

name	Required	This is the full name of the tech you are looking for. The Tech API will return related names to help you find the exact one (or more) you are looking for.
key	Required	Each application requires a key. Check here for details on getting a key.

Note: parameters must be URL encoded, including replacing blank spaces with %20.

http://api.seravia.com/v1/techs?name=machine%20learning&api_key=XYZ

See the Examples sections for variations.

Response

The Technology API returns up to seven types of data related to the technology name submitted. A typical response looks like:

{
  "aliases": [
    "artificial intelligence",
    "AI"],
  "companies": [
    "Google Inc",
    "Microsoft Corp"],
  "people": [
    "Larry Page",
    "Sergey Brin"],
  "publications": [
    "Retaining wall masonry block",
    "System and method for reorganizing data storage in accordance with usage frequency",
    "Methods and apparatus for serving relevant advertisements"]
}

Aliases

Aliases includes various other names that may be alternatives or related technologies. For instance, “machine learning” returns “artificial intelligence” and “AI”.

We identify and score unique technologies by mining millions of publications and factoring in word frequency, patent classifications, inventors and other signals. This is a non-trivial problem and requires a large number of frequent but not useful terms to be filtered out.

Each alias may be called separately to return related entities and publications associated with that name. In subsequent versions we will add the ability to include/exclude any of these aliases.

Companies

Companies includes companies or institutions such as subsidiaries with which this technology has been affiliated. For instance, “machine learning ” returns “Google Inc” and “Microsoft Corp”.

Companies are not always explicitly identified as being a company. We look at entity type, role on the filing and inclusion of certain keywords in the name to determine if it is a company. These are not always correct.

Each company may then be looked up using the Company API.

People

People includes people with whom this technology has been affiliated. For instance, “machine learning” returns “Simon Tong” and “Mark Pearson”. These people are generally inventors or authors that have appeared on documents associated with the technology.

Publications

Publications are all those documents on which the person appears. The full list of document types appears here.

Examples

Datasources

In the first version this information comes largely from ~55 million worldwide patents. Scholarly journals will be added in subsequent versions.

Obtaining a Key

If you are interested in advance access, please contact us at [email protected].

Seravia | Data Scientists

Technology API