What are the most innovative IT fields? The patent classification system can sometimes be hard to grasp. Additionally, the Patent and Trademark Office has recently finished the transition from one system to another. However, this doesn’t help us follow the hottest topics either. The mapping is available on the official website, but it is purely statistical. This means that you can’t really compare different classifications.
Another approach that we used was determining the topics ourselves. We based our method on applying the Latent Dirichlet Allocation algorithm to the (parsed and stemmed) application abstracts. Granted, this approach is relatively computationally expensive. The results are quite consistent with the original classification, but are, in fact, universal.
Here are the top five topics, based on the entire corpus of IT patent grants.
Electronic health (or simply e-health) can be defined as a range of healthcare-related digital services and devices. These types of services can be used for prevention, diagnosis, treatment and personal health monitoring.
Let’s take a look at the results of a recent survey (as of March 2017) regarding American adults’ awareness of the e-health field. Approximately 10 percent of respondents in the 18-29 age group had some knowledge about e-health. Knowledge about e-health was slightly higher among the 20-45 age group than others (13 percent). Around 9 percent of those surveyed in the 46-60 age group replied, “Yes, I know what e-health is.” The lowest percent of e-health awareness was found among people aged 61 years and older.
The United States of America is one of the largest markets for leading sport equipment manufacturers. According to statistics illustrating the number of people who bought sports equipment within the last 12 months in the country from spring 2010 to spring 2015, last year about 36.78 million people purchased sports equipment. This rate was quite similar in autumn 2014, with 36.81 million buyers. In spring 2014, there were about 37.24 million people who bought at least some type of sporting equipment. Overall the total number of buyers in 2013 was approximately 75 million people, compared to 74 million people in 2012.
Exploring utility patents is no easy task. The system that is currently in place, Cooperative Patent Classification, has its issues. For example, many patent applications include multiple classifications only partially related to the invention itself. This proves useful if you are searching for something specific — on the other hand, it is not as helpful if you are interested in patent mining or visualization.
Luckily, one can easily accomplish most of these tasks with the help of advanced computational techniques. The most promising approach is the use of Natural Language Processing to classify and visualize patents based on their abstracts.
Let’s take a look at the algorithm known as Latent Dirichlet Allocation (or LDA for short). Its primary goal is to find the number of topics that are best suited for classifying a corpus of documents (patents, in our case).
The geographic properties of an area often dictate the type of businesses that can locate there. For example, you can’t have an inland naval base. Farms and agriculture, in general, are less likely to prosper on rocky mountains than on sunny plains. But today, with all the technological advancements we have, many jobs in intellectual labor, including IT and finance, hi-tech manufacturing and other new industries seem less likely to depend on climatic features.
To summarize climate features of a territory, we used the existing climate zones classification prepared by the U.S. Department of Energy. Each county is assigned to one of eight climate zones. Definitions of these zones depend not on temperatures, but rather on accumulated heat (the unit is called “degree-days”). Zone 1 has the warmest climate, while zone 8 has the coldest – in the U.S., only certain parts of Alaska belong to this climate zone. We present a map of the climate zones below; you can click to zoom in on a state of interest.