First off- WHOA THIS IS AWESOME! I’m jumping up and down right now!
As a software engineer at Amazon, my colleague Weiwei and I are thrilled to have recently been awarded two patents for our work in topic modeling. It is an honor to be recognized for the hard work and dedication we have put into this and I am especially grateful to have had the opportunity to partner with my colleague Weiwei Cheng. Weiwei and I were also awarded Amazon’s puzzle piece awards, which are given to employees when their patents are officially approved.
The first of our patents (US 10,558,657) covered a mechanism for progressive topic modeling is disclosed to facilitate document content analysis. Input documents can be sorted and divided into multiple groups. Topic modeling is performed for each group, where the topic modeling for one group is based on the generated topic model from a previous group, if available. The vocabulary used in the topic modeling process can also be updated for each group of documents. The generated topics can be presented in a user interface to facilitate a user in analyzing the documents. The topic modeling mechanism can also be utilized to enhance a document search experience by generating topics from documents contained in search results and presenting topic words to a user as suggested search terms.
Our second patent (US 10,255,283) relates to simplifying the purchase experience by generating topics from multiple customer reviews using topic modeling. The customer reviews are sorted and divided into several groups. Topic modeling is performed through multiple stages with one stage processing one group of documents. At a given stage, the topic modeling is performed based on the topic model obtained from a previous stage. This progressive topic modeling can significantly reduce the use of computing and storage resources by working on smaller documents at each stage. Also, the topics generated at different stages have one-to-one correspondence, which can help stakeholders analyze the topic evolution in the documents. The topic modeling can be used to enhance a document search experience, where topics generated from the search result can be provided to a user to modify his/her search. With the help of the topic modeling, a user can search for topics that are previously unknown to him/her.
Receiving these patents is a testament to the incredible team of engineers and researchers at Amazon who are working tirelessly to push the boundaries of AI and machine learning. I am truly excited about the future of AI and the many ways in which it will continue to revolutionize the way we live and work.
At Amazon, we are fortunate to be at the forefront of this exciting field, and I am grateful for the opportunity to contribute to such important work. I’m grateful for the opportunity to have worked on these exciting projects, and for the support and collaboration of my colleagues, particularly Weiwei Cheng. As we continue to explore the potential of machine learning and AI, I am excited to see what new discoveries and innovations we will be able to uncover, and to be a part of this incredible journey.