How does TechDiscovery differ from Semantic Search?
What it is
TechDiscovery allows you to quickly get to the list of the most relevant patent families for your patent research or analysis and easily refine these if necessary. Skip the search part, and get straight to the data and analysis you require.
You can use either patent numbers, family representative patent numbers or text, to begin a search. The text can be either a simple description of the technology, longer form technical information (e.g. your own unpublished patents), or even product descriptions/patent paragraphs from competitors. You can also use a combination of both patent examples and text (where possible).
How it can help you
If you want to quickly explore a patent landscape for a specific technology space or look for patents that are similar to your examples, TechDiscovery is the right tool for you. Similarly, if you’d like to quickly retrieve a set of relevant patents to better understand the latest innovations in your research field, but you’re not sure where to start, Tech Discovery can help you to start your search.
The purpose of this type of search is to find a set of relevant patents to the technology or invention. These patents can then be useful for starting the patent research (for R&D or legal purposes) or as a first step of the patent analysis, to quickly and easily evaluate the largest players and trends within a tech space for example.
You may be a patent search expert wanting to verify your search query and results, or to identify potentially missed concepts or patents using TechDiscovery. You can then sort by most relevant results using the similarity score.
Alternatively, you may be an Innovator or R&D engineer looking for a way to start your search as a non- search expert. TechDiscovery can be used to easily find patents in your technology area by simply inputting a short piece of text or an example patent.
TechDiscovery can be used to:
- Conduct a Knock out search to quickly identify potential Prior Art. Have a quick and inspirational start for your Patentability Search, Freedom to Operate Search, or your Invalidity Search.
- Quickly explore a tech area to see what patents currently exist within the space, to explore current competitors or collaborators.
- Perhaps you know very little about the technology area and you want to understand who the innovators are in that area. TechDiscovery doesn’t just give you an easy starting point, but it also inspires your research and may support you to uncover what “you don’t already know”.
- You may have a lot of wide ranging questions from the business that you want to answer quickly. Tech explorer allows you to quickly explore a technology area with as little as one word.
- You may want to look for patents that are similar to examples that you already have. Using generative AI and cyphers machine learning algorithm to vectorize patents tech explorer is able to bring back similar patents to the technology area.
Get to a list of the most relevant patent families for your analysis, refine these, and get straight to the data and analysis you require within minutes.
How does TechDiscovery work?
Similarity searching starts with vectorising every patent family in the universe (think of this like giving each patent family a unique fingerprint). Each patent family can then have its vector (fingerprint) compared against others to identify vectors (patent families) that is closest to it, returning the closest results based on the chosen sample size (50, 100, 1000 etc.). The product's deep learning model (“algorithm”) is specifically designed for patent linguistic tasks and uses the patent title, abstract and claims to generate a vector for each individual patent family. The product uses generative AI to assist the vectorisation (or fingerprinting) of information when you have very little information e.g. a technology name or brief description.
How does TechDiscovery differ from Semantic Search?
Here are the key differences to semantic searching/boolean searching in TechDiscovery:
- The results are much better (more relevant results, more results found).
- You can search based on patent numbers.
- You can use whole paragraphs of text.
- The search is specific to patent text, not 'general text similarity'.
- You can combine multiple inputs into one search for example, patents, blocks of text, and technology names.