ClearAccessIP is a patent strategy and management platform providing an automated docketing system and machine learning analytics.
A Deal Room is an entity used for summarizing and aggregating/grouping patent records in a portfolio. When creating a deal room, one can enter a portfolio's title, licensing(sales, pool, cross-licensing, strategy, internal review), asset value, terms, primary market sectors, products and services, companies that may perceive benefits, brokers and marketplaces, contract URL and summary. Patent records (Patents, Patent Applications, Provisional Applications, Foreign Patent Applications and Invention Disclosures) can be added to/removed from a deal room as needed.
It can be shared publicly by copying and pasting a link containing an encrypted token. A copy of the deal room can be downloaded in PDF format.
When a deal room contains Patents, Patent Applications and/or Invention Disclosures, the machine learning toggle can be enabled and the patent objects then get sent to the machine learning analyst.
Once our machine learning analyst finishes, you can click on "IP MAP" symbol on upper left corner to navigate through results of relevant patents in the Neural Net
and Field of use
tabs.
Semantic search (Neural Net) seeks to improve search accuracy by understanding searcher intent and the contextual meaning of terms as they appear in the searchable dataspace, whether on the Web or within a closed system, to generate more relevant results.
Keyword search (Field of Use) is a type of search that looks for matching documents that contain one or more words specified by the user.
For document similarity search, a method to featurize documents based on the contents (words) present. One important and desirable property of any document search system is that semantic similarity, rather than relying on exact word matches or simple word-to-word comparisons between documents. By way of analogy, a web search for the term “laptop” might return a result with the text “notebook pc” (and not containing the word “laptop” at all) due to the semantic similarity between the terms. In order to capture semantic similarity between words, we will utilize embeddings (vectors) produced by the Word2Vec model, which has proven to be good at capturing semantical similarities/differences for words based on context windows. The Word2Vec model is trained (in an unsupervised manner) on a patent corpus.
Another method for document similarity is Keyword based search where if you put any patent as input, our machine learning analyst will grab most important keywords from it and then we will search for similar patents based on them. Keyword based search will be useful when you want to find patents infringement.
- Once you are done with IP Map, you can go back to deal room dashboard. Here you'll find
SUGGESTED COMPANIES
panel.
- If you click on any of the links then a modal with patents will pop up where you can see patents related to your input patent(s) categorized by assignees.
- Semantic Searches on Patents
- Keyword Searches on Patents
- Suggested Companies
- Snippet of IP Map Results
- Suggested Products
- Drafting a new Patent from Invention Disclosure
- Prediction of Asset Value