Rakuten Kobo Inc.

Jordan Christensen

Darius Braziunas

Neil Isaac

Yingbo Miao

Joshua Sumali

Inmar Ella Givoni

Content Based Similarity Detection. A computer implemented method includes computing a hash of each word in a collection of books to produce a numerical integer token using a reduced representation and computing an Inverse Document Frequency (IDF) vector comprising the number of books the token appears in, for every token in the collection of books. The method also includes creating a token occurrence count vector for each book in the collection and normalizing the token occurrence count vector using the IDF vector to create a Term Frequency-Inverse Document Frequency (TF-IDF) vector. Further, the method includes reducing each TF-IDF vector by using random projections to obtain a final signature representing each book in the collection, reducing each TF-IDF vector by using random projections to obtain a final signature representing each book in the collection and using a trained machine learning algorithm, determining whether each of the list of candidate books is similar to the target book.

Content based similarity detection

A system and method for automatically identifying an electronic document. The method includes accessing, within an electronic device, an electronic document and extracting text from the electronic document. A signature is then determined based on the text of the electronic document and the signature is communicated over a communication channel. The method further includes receiving an identifier of the electronic document over the communication channel. In one embodiment, the identifier is determined by a server matching the signature against a signature library. The method further includes receiving a bookmark associated with the electronic document.

System and method for automatic electronic document identification

Systems and methods for automatically generating replacement query terms that offer improved search efficiency. Recommended search query terms are generated based on statistic information derived from empirical data recording prior search sessions with respect to searching on a search engine. A query term entered later in a search session is treated as a possible replacement term for a query term entered earlier in the same session. Upon receiving an initial query term in a new search session, the replacement terms of the initial query term are identified from the empirical data and evaluated as candidates for replacing the initial query term in the new search session. The evaluation is based on the respective occurrence rates that the candidates are used as replacement terms for the initial query term in the empirical data, and based on the respective conversion rates of the candidates.

Growing community of inventors

Toronto, Canada

Jordan Christensen