International Business Machines Corporation

Anna Rosa Coden

James William Cooper

Michael Stephen Schwartz

JoAnn Piersa Brereton

Stephen Kane Boyer

Robert Lawrence Mack

Disclosed is a method, a computer program product and a system for processing documents that contain chemical names. The system has a unit to partition document text and to assign semantic meaning to words; a unit to recognize any substructures present in the chemical name fragments; and a unit to determine structural connectivity information of the chemical name fragments and recognized substructures and to store the determined structural connectivity information in a searchable index. The system further includes a unit to search a text index using at least one of a fragment name and a substructure name and to search the structure index by at least one of fragment connectivity and substructure connectivity. At an intersection of the search results from the structure index and the text index, the system operates to identify at least one document that contains a reference to a corresponding chemical compound.

System and method for the indexing of organic chemical structures mined from text documents

This invention provides a method, a system and a computer program for recognizing technical terms. In the preferred embodiment the technical terms are chemical names, and in a most preferred embodiment the technical terms are organic chemical names. A computer program product stores in a computer readable form a set of computer program instructions for directing at least one computer to process a text document. The set of computer program instructions include instructions for assigning corresponding associated parts of speech to words found in the document. The instructions for assigning include instructions to apply a plurality of regular expressions, rules and a plurality of dictionaries to recognize organic chemical name fragments, to combine recognized organic chemical name fragments into a complete organic chemical name, and to assign the complete organic chemical name with one part of speech. The regular expressions include a plurality of patterns, individual ones of which are comprised of at least one of characters, numbers and punctuation. For example, the punctuation can comprise at least one of parenthesis, square bracket, hyphen, colon and semi-colon, and the characters can comprise at least one of upper case C, O, R, N and H, and further comprise strings of at least one of lower case xy, ene, ine, yl, ane and oic.

System and method for the recognition of organic chemical names in text documents

Query objects are created by a client process. The query objects have one or more sub-query objects and one or more execute methods that are capable of operating on their respective query object to produce one or more query expressions. All of the execute methods are capable of producing the respective query expression that is compatible with a structured query language. A compound query contains one or more boolean expressions of one or more of the query objects. The compound query has one or more compound execute methods which invoke one or more the execute methods of each of the query objects. Each of the execute methods returns their respective query expression and the compound execute method uses one or more common table expressions to combine the query expressions to form a single compound query expression that represents the boolean expression. This single expression can be execute against a database to return a result without executing any of the query expressions against the database individually.

System and method for performance complex heterogeneous database queries using a single SQL expression

A computer system has an interface to one or more databases, one or more base query objects, query objects, compound queries, annotator objects and graphical user interfaces (GUI's). The base query objects have one or more base query object methods, base variables, and base objects, the base query object methods being specific to the specific database and capable of querying the specific database. Each of the query objects derived from one of the base objects, and has a query type, one or more query object methods, query object variables, and query object objects. Each query object method is capable of querying a specific database to obtain a type result having the respective type. The compound query has one or more compound query methods, compound query variables, and compound query object objects. The operator objects, are derived from one of the base query objects that are used with the specific database. (GUI) has one or more query elements with one or more operators. The query elements, operators, and conditions are user selectable. Each query element, operates on the query object with the same type as the query element to create an instance of the query object with the query element. The compound query object instance uses the instances and the operator object instances to create an a query expression for the specific database. Therefore the input in the GUI is translated into a single compound query object.

Object oriented query model and process for complex heterogeneous database queries

A method and data processing system are disclosed for translating an ad-hoc user input string into Structured Query Language. A user input string is parsed placing joiner objects and left parentheses into a temporary pushdown stack and placing query clause objects into a postfix queue. After encountering a query clause object or a right parenthesis, the next item in the pushdown stack is placed in the postfix queue if it is a joiner object. Once the input string is parsed, objects in the postfix queue are placed into a second temporary pushdown stack and also used to form common table expressions using adjacent items in the second pushdown stack. Finally, an SQL SELECT statement is formed using a JOIN on the ids returned by the common table expressions.

Growing community of inventors

Riverdale, NY, United States of America

Anna Rosa Coden