Abstract: A method is disclosed, involving converting each structured text document stored in a database into one or more vectors, using the vectors of the structured text documents stored in a database to create a similarity search index, then for each structured text document from the database, searching the search index using the one or more vectors of the structured text document in order to generate a list of N other structured text document from the database similar to the structured text document based on said search; an storing each list of N other structured text document from the database similar to the structured text document in a table.

Abstract: A method is disclosed, involving converting at least one structured text document stored in a database into one or more vectors, training a machine learning model to associate the at least one vector with the editors for that structured text document, training a machine learning model to associate the at least one vector with the editors for that structured text document, receiving a second structured text document and converting said second structured text document into one or more vectors, then processing the one or more vectors of the unpublished structured text documents through the trained machine learning model to identify appropriate editor teams, before finally sending the unpublished structured text documents to a computer device associated with an editor.

Abstract: A method is disclosed, involving converting each structured text document stored in a database into one or more vectors, training a machine learning model to associate structured text document vectors with the journals said structured text document were published in; receiving an additional structured text document, converting said additional structured text document into one or more vectors, and processing the additional structured text document through the trained machine learning model to identify an appropriate journal for publication. Systems and computer-readable media implementing the method are also disclosed.

Abstract: A method is disclosed, involving converting each structured text document stored in a database into a vector, building a search index using the one or more vectors of the structured text documents stored in the database, then receiving a new structured text document, converting the structured text document into a vector, then searching the search index using the one or more vectors of the new structured text document, and generating a list of N structured text document from the database similar to the new structured text document based on said search

Abstract: In some embodiments, a computer-implemented method for selecting a polymer for an intended use. The method may include: training a selection model based on a graphical dataset, the graphical dataset comprising a node-edge graph identifying relationships between uses and properties of a polymer; receiving, via a user interface, a request comprising the intended use; based on the selection model, determining a polymer for the intended use; and outputting the determined polymer via the user interface.

Abstract: In some embodiments, a computer-implemented method for retrieving a similar document from a corpus of documents is provided. The method may include receiving a search document comprising a set of words; applying a first encoder to generate a first vector; applying a second encoder to generate a second vector; determining a first similarity between the first vector of the search document and the first vector of each document of the corpus of documents; determining a second similarity between the second vector of the search document and the second vector of each document of the corpus of documents; generating a first ranked list of documents based on the first similarity; generating a second ranked list of documents based on the second similarity; applying a voting algorithm to determine a score associated with each document; and outputting a third ranked list of documents based on the determined score.

Abstract: Systems and methods are provided for query and index optimization for retrieving data in instances of a formulation data structure from a database. The methods include presenting an information source for searching for the presence of formulations and generating formulation data from field entries. The formulation data is associated with found formulations. The methods include generating an instance of a formulation data structure. The instance of the formulation data structure associates the information source with the found formulations. The methods include creating optimized index data from retrieved data in the instance of the formulation data structure. The optimized index data includes a mapping between potential search-field terms and the formulation data, and is grouped based on a predicted access pattern.

Abstract: Systems and methods are provided for evaluating composition of a first file representing a document to be evaluated. An evaluation method transforms the first file to a second file. The second file includes a plurality of objects corresponding to the composition of the first file. The evaluation method also determines parameters based on the plurality of objects; evaluates the parameters based on a plurality of composition rules provided by a rule engine; generates evaluation findings and stores the evaluation findings; and generates an evaluation conclusion based on the evaluation findings. The evaluation conclusion indicates compliance of the document according to the composition rules.

Abstract: Systems and methods are provided for evaluating composition of a first file representing a document to be evaluated. An evaluation method transforms the first file to a second file. The second file includes a plurality of objects corresponding to the composition of the first file. The evaluation method also determines parameters based on the plurality of objects; evaluates the parameters based on a plurality of composition rules provided by a rule engine; generates evaluation findings and stores the evaluation findings; and generates an evaluation conclusion based on the evaluation findings. The evaluation conclusion indicates compliance of the document according to the composition rules.

Abstract: An information retrieval system for storing and searching Markush formulations is described. All implicit specific structures (ISSRs) of the Markush formulation are stored as a specific multiple-connectivity node representation (SpMCN) by allowing the appropriate atoms to expand beyond their normal valance and accommodate all substituents of the Markush structure. The SpMCN is simplified by using a generic group hierarchy to reduce common structural features to an associated generic multi-connectivity node representation (GnMCN) that contains within it implicit generic structures (IGSRs) corresponding to each ISSR. Attributes such as ring size and hetero atom identification are also associated with each generic feature whenever possible. The SpMCN and GnMCN are further simplified by storing their associated structural characteristics as bit strings.