Supporting Vendor

DorothyAI

DorothyAI
Summary
Provider:

Three10 Solutions, Inc. d/b/a DorothyAI

Description:

DorothyAI was founded by patent lawyers with nearly 50 years of combined experience who saw the value of patent searching and knew there was a better, more secure way to find relevant patent information than outsourcing. We use cutting edge natural language processing and machine learning to query the world’s patent database and identify relevant patent publications using an intuitive user interface.

Our mission is simple: produce affordable and efficient patent search products that work for practitioners, save outsourcing costs, and give time back to practitioners to work on high value projects that generate profits and impress clients. We are committed to producing user friendly products, and providing excellent user support to back them up.

Categories:
Fee:

Pricing is based on contract type (i.e. length,individual or bundled products) starting at $50 per user per month for accessto the basic DorothyAI patent search platform.

Website:
http://www.dorothyai.com
Included Data
Data:

Global Patent Data

Type:

Natural language processing

Machine learning

N-gram

Synchronization

Methods Used
Methods:

The platform uses an ensemble of AI algorithms and more traditional search models including:

●     Natural language based search queries are deconstructed using a natural language processing(NLP) model and plotted against the world’s patent literature.

●     Machine learning algorithms are used to index the patent database and compile a thesaurus ofsynonyms that is constantly updated. Words in the query are tokenized and replaced with all or a subset of synonyms based on user input via a slide bar.

●     Every query isclassified based on the collaborative patent classification (CPC). Our classifier is better than any published classifier to date.  

●     Returned results from each of the ensemble of search models are processed to remove duplicates,assign a relevancy score to each reference by comparing the references to search query, and order the references by relevance before they are returned to the user interface.

●     An NLP model identifies “Key Phrases” from the text of each document and returns these results to the user interface.

●     Advanced Filters uses an NLP based model to weight phrases, sentences, and paragraphs in returned references that include specific “Facet Terms,” and reorder return results based on their use of selected facet terms and, in some cases, synonyms of the selected facet terms.

Value Added Data
Data:

DorothyAI provides full text patent applications, related images, and highlights key phrases/synonyms based on the user’s inputted search text.

Interface
API Available:

Yes, access is available upon request depending on contract.

API Link:
Analysis Included
Details:

Search results are ranked and returned by relevancy. Key terms and their synonyms are extracted and highlighted in search results. Please see “Methods Used”     section.

Data Export
Details:

Unlimited data can be exported in CSV format at no additional charge. Users can also share search results and projects, including commenting and editing functionality, with internal users and nonusers/clients.

File Support
File 2:
File 3:
File 4:
File 5:
No items found.

Sign Up for the Newsletter

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

©Copyright ML4Patents | Powered By Patinformatics