Patent Search & Analytics

Two Patent Database Search Techniques Are Better Than One

By June 30, 2020April 6th, 2021No Comments

For many patent professionals, it’s hard to know when you’re done with a patent search. Striking a balance between efficiency and quality is essential when missing important prior art can have serious consequences.

Employing one patent database search technique limits the thoroughness of your search and exposes you to application rejection, as well as future claims of infringement or invalidation. To mitigate the risk of missing relevant technologies, we recommend pairing the power of both semantic and Boolean search in a two-pronged database search strategy.

Using both semantic and Boolean search tactics to sort technical literature makes it more likely your patent search will include every relevant keyword, translation, synonym and phrase. Together, natural language search and Boolean search reduce the risk of missing a relevant piece of prior art.

Natural Language Search vs Boolean Search

To understand why it’s so important to use both database search techniques, we need to understand the differences between Boolean and semantic, or natural language, search.

Boolean search is logic-based. The search engine delivers results based solely on keywords strung together with operators such as “and” and “or.” Many patent searches simply whittle down results using filters and Boolean logic. Maybe you use keywords, classifications and assignees until the list of patents and non-patent literature is both relevant and reviewable.

All of the results need to be reviewed because there’s no real way to know which ones are most important. This makes the number of search results critical—you can’t possibly review a million patents. How do you know that while whittling down your results to a manageable number, you aren’t discarding important prior art?

Semantic search, on the other hand, uses the essence of a conversational search query to return relevant results based on your search intent. This database search technique uses a relevance scale to deliver the most pertinent results. Rather than whittling down results based on filters, a semantic search engine understands the concept of your query and finds results with shared concepts. The more shared concepts between your search and a specific piece of literature, the higher the relevance.

We expect to see a lot of results because many patents may be related to your search in some way. InnovationQ Plus® uses a star ranking system to provide insight into relevancy. Four and five star results are most important; they match most or all the concepts from your query. If you are assessing the novelty of a new invention, four and five star results should be reviewed for potential knockout art. Three star results might only include some of the concepts or features from your query and might be important for §103 nonobviousness or if you are researching tangential technology.

Pairing Semantic and Boolean Patent Search

Semantic search can be coupled with Boolean search in a variety of ways to gain efficiency and thoroughness. We recommend starting with semantic search to boost your Boolean-based results.

Start with Semantic

When we start a patent search with a conversational query, we find results that go beyond exact match keywords or classifications. Instead, we discover documents based on the meaning of our search. This database search technique can even find significant prior art in foreign languages and with non-descript or misleading language.

For example, when we use a semantic patent search to learn more about hydrofracking technology, we see similar patents in the medical field. This is the beauty of a semantic database search—it digs up unexpected applications and valuable opportunities for your innovations.

A natural language search helps us find what we’re looking for quickly and efficiently without sacrificing quality. Starting with semantic alerts us to important literature we could have missed with a Boolean search alone and gives us additional keywords to use in our Boolean search.

Boost Your Boolean

Embracing semantic search doesn’t necessarily mean abandoning Boolean. When we begin with a semantic search, our Boolean search is more effective and comprehensive. Searching using conversational queries helps us build a comprehensive list of specific keywords to use in our Boolean search, including new terms from unfamiliar industries.

We then use our keyword list in our Boolean search, making the process more efficient, effective and comprehensive. This gives us the additional benefits of precision, in addition to the relevance delivered by our semantic strategy. Using two patent database search techniques, we improve the thoroughness and relevancy of our findings, further reducing the risk of missing important prior art.

Implementing This Technique in InnovationQ Plus

Pairing semantic and Boolean search is a great way to get the most out of InnovationQ Plus. We recommend using this two-pronged database search strategy in all your searches! These are three of the most accessible ways to use semantic searches to improve Boolean logic, even if you haven’t quite embraced natural language searching.

1. Learn About a New Technology

Run a semantic search with a simple natural language description of what you’re looking for. View the top results and visualizations to understand the space and learn important keywords, which can be used in Boolean queries.

This is especially helpful in new areas with unfamiliar terminology. Broad concept searches can help you learn more about an unfamiliar space and add focus to follow-up searches. This method can be a fast and easy first step to aid in crafting queries.

2. Identify Relevant Classifications and Assignees

Enter the main concept for a semantic search using natural language. View the results as visualizations and review the most common CPCs, IPCs, assignees, and inventors. Charts are shown by relevance to show not only who the biggest players or what the most common classifications are, but also which are linked to the most relevant documents. This ensures your Boolean filters aren’t missing any small but important players or classifications.

3. Review Results by Relevance

Enter a Boolean query as usual and add the most important keywords as the main concept. Adding even a broad concept will apply relevance scores to the results and visuals.

A difficulty in Boolean searching is that you must review all the results, whether they are first or last. By adding a concept, the results will be sorted by relevance so you can review results starting with the most important. Not only can you focus your time on the most relevant documents, but you may also find a point on the list where the results are no longer (as) relevant and require less review time.