Is Ambercite Ai better than semantic searching?
Patents are commonly searched using a combination of keyword or class code searching. More recently semantic searching has become available, which finds similar documents by looking for similar language.
In contrast, Ambercite Ai uses advanced citation analysis to find similar patent families to relevant patents you are already know about - regardless of language used or classification codes.
Which raises the questions:
- So how does Ambercite Ai compare to semantic analysis?
- How would you compare them?
To cut to the chase, the case study below discussed below did find that Ambercite Ai is better than than semantic or conventional searching:
So how did we determine this? This is covered in the next section.
How DID WE compare Ambercite Ai to semantic and traditional searching?
In such a match, the choice of patents being analysed can make a big difference. It is possible to 'cherry pick' patents to prove or disprove any hypothesis, or make any approach look great. In an ideal world we might randomly pick say 100 patents, but you probably don't have time to read the results from such a study, and we certainly don't the time to report them.
An alternative approach I have used before is to pick 'round number' patents, where the subject matter is determined by the allocation of patent numbers by the USPTO. In this case, the last big round number granted by the USPTO was US9,000,000 for a Windscreen Washer Conditioner - which claims an aspect of using rainwater to refill your car windscreen washer. This is a patent that should be easy to search using any technique, with relatively simple and commonly used keywords.
So having set up a contest of 'who can find the most similar patents', we need some contestants. It can be bad form in marketing to directly disparage your competitors (not that they really are competitors - we tend to think of them instead as complementary techniques as we will discuss further below), so I will avoid naming them. Instead we will list them as follows:
- Ambercite Ai
- A semantic patent search engine - that can search for similar patents based on patent numbers
- A very commonly free patent engine - that has a 'similar documents' function
- A commonly used subscription search engine - that has a built in semantic search function
- The patents listed by the examiner for US9,000,000
And the test? For each of these search engines, I will ran a search using US9,000,000 or its abstract, and list in order the most similar patents found.
The results will be provided below. But before we look at the results, we should take a closer look at patent US9,000,000.
The abstract for this patent is:
A system and method of collecting and conditioning rainwater and other moisture, such as dew, from a windshield of a vehicle and utilizing the collected fluid to replenish the fluids in the windshield washer reservoir. A collection funnel is positioned on a vehicle in order to collect rainwater and other moisture. Rainwater and other fluids from the collection funnel are directed to a conditioning cartridge where the water is de-ionized and windshield washer fluid is added. The cartridges are designed to be single replaceable units. The mixed fluid from the mixing cartridge is directed to the pre-existing windshield washer reservoir.
What we found
The results in the chart at the beginning of this blog shows that Ambercite Ai found the most number of relevant features – which is not surprising as Ambercite Ai applies the collective wisdom of all of the examiners and applicants in an area to find the most relevant patents – irrespective of language uses.
Having said, ultimately the strength of Ambercite Ai that it uses a different approach – to find different patents. So we tend to advise clients to use Ambercite Ai alongside their existing preferred approaches…because, in our opinion ‘no search is complete without it’.
The detailed results to support this analysis are shown here