Gm Global Technolgoy Operations, Inc.

Alexander P Morgan

Michael A Sowa

Frederick J Vondrak

Diane I Gibbons

Lawrence M Quinn

Stephen L Falko

Gulcin Sengir

Thorsten W Rommel

A method transforms unstructured text into structured data in a domain-specific ontology. The method includes recording an input block of text using an information extraction module (IEM), accessing a domain-specific ontology and supplemental data in a knowledge source(s) via the IEM, processing the input text block, and using the IEM to generate a plurality of nodes in the domain-specific ontology. Each node classifies the unstructured text to corresponding objects of interest, thereby transforming the unstructured text into the structured data. An IEM is also provided having a computer device and an algorithm executable thereby to transform unstructured text into structured data in a domain-specific ontology. The IEM is adapted for recording a text phrase using the computer device, accessing and retrieving the domain-specific ontology and supplemental data from a knowledge source(s), and processing the text block using the computer device to generate a plurality of nodes in the domain-specific ontology.

Method and system for maximum-informativeness information extraction using a domain-specific ontology

A computer implemented method for using case-based reasoning (CBR) information retrieval processes is provided. The method includes: accessing a data model including symptom attributes and solution attributes; receiving a query from a requestor specifying one or more values for one or more of the symptom attributes; executing the query including searching a database of archive records that are not structured to facilitate CBR for the specified symptom attribute values and receiving a subset of the archive records that include the specified values; determining values associated with one or more of the solution attributes for each of the records in the subset; and creating a temporary case record for each of the records in the subset, each of the temporary case records comprising a pointer to the corresponding record in the subset and a heading section including the symptom attributes, the specified symptom attribute values, the solution attributes, and the solution attribute values associated with the corresponding record in the subset, thereby creating a temporary case base from archive records in real time in response to the values specified in the query.

Retrieving case-based reasoning information from archive records

A method for vehicle diagnostic knowledge delivery comprising receiving a search request from a user system and accessing a database of case records in response to the search request. Each of the case records includes a case-record number attribute, a set of vehicle-description attributes, a set of bookkeeping attributes, a set of system attributes, a set of symptom attributes, and a set of action attributes. The method further comprises searching the database of case records for a case record responsive to the search request. If a case record responsive to the search request is located, it is transmitted to the user system.

Vehicle diagnostic knowledge delivery

A method for vehicle diagnostic record mapping comprising receiving a vehicle service record. A target record is created in response to receiving the vehicle service record. The target record includes a target-record number attribute, a set of vehicle-description attributes, a set of bookkeeping attributes, a set of system attributes, a set of symptom attributes, and a set of action attributes. Vehicle description data is mapped into the set of vehicle-description attributes in response to locating the vehicle description data in the vehicle service record. Bookkeeping data is mapped into the set of bookkeeping attributes in response to locating the bookkeeping data in the vehicle service record. Vehicle system data is mapped into the set of system attributes in response to locating the system data in the vehicle service record. Symptom data is mapped into the set of symptom attributes in response to locating the symptom data in the vehicle service record. Action data is mapped into the set of action attributes in response to locating the action data in the vehicle service record.

Growing community of inventors

Birmingham, MI, United States of America

Alexander P Morgan