Generating risk assessment software
AssigneeInternational Business Machines Corporation
InventorsKelly A Argyros, Donna K Byron, Lakshminarayanan Krishnamurthy, Joan W Tomlinson
Life of this patent
Estimating the term…
Abstract
One or more portions of a text corpus indicative of operational risk from a set of risk assessment documents is identified. Contextual features from the one or more portions of the text corpus are determined by applying a natural language processing (NLP) algorithm on the one or more portions. Risk identifiers are extracted based on the determined contextual features. A risk assessment software is generated based on the extracted risk identifiers and an operational risk category.
Claims25
A method of generating risk assessment software, the method comprising:
- identifying one or more portions of a text corpus indicative of operational risk from a set of risk assessment documents;
- determining contextual features from the one or more portions of the text corpus by applying a natural language processing (NLP) algorithm on the one or more portions;
- extracting risk identifiers based on the determined contextual features;
- and
- generating a risk assessment software based on the extracted risk identifiers and an operational risk category.
A computer program product for generating risk assessment software, the computer program product comprising one or more computer readable storage medium and program instructions stored on at least one of the one or more computer readable storage medium, the program instructions comprising:
- program instructions to identify one or more portions of a text corpus indicative of operational risk from a set of risk assessment documents;
- program instructions to determine contextual features from the one or more portions of the text corpus by applying a natural language processing (NLP) algorithm on the one or more portions;
- program instructions to extract risk identifiers based on the determined contextual features;
- and
- program instructions to generate a risk assessment software based on the extracted risk identifiers and an operational risk category.
A computer system for generating risk assessment software, the computer system comprising one or more processors, one or more computer readable memories, one or more computer readable storage medium, and program instructions stored on at least one of the one or more storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, the program instructions comprising:
- program instructions to identify one or more portions of a text corpus indicative of operational risk from a set of risk assessment documents;
- program instructions to determine contextual features from the one or more portions of the text corpus by applying a natural language processing (NLP) algorithm on the one or more portions;
- program instructions to extract risk identifiers based on the determined contextual features;
- and
- program instructions to generate a risk assessment software based on the extracted risk identifiers and an operational risk category.
A method of generating a risk assessment software, the method comprising:
- identifying one or more portions of a text corpus indicative of operational risk from a set of risk assessment documents;
- parsing the one or more portions of the text corpus through a natural language processing (NLP) algorithm to construct text tokens indicative of an operational risk;
- transforming the text tokens into risk identifiers, each of the risk identifiers being assigned with a metadata tag indicative of an operational risk category;
- and
- selecting a set of software structs based on the transformed risk identifiers, wherein the set of software structs is used to generate a risk assessment software.
A method of generating a risk assessment software, the method comprising:
- identifying one or more portions of a text corpus indicative of operational risk from a set of risk assessment documents;
- determining contextual features from the one or more portions of the text corpus by applying a natural language processing (NLP) algorithm on the one or more portions;
- receiving an operational risk category and an activity description from a user, wherein the activity description includes unstructured text stream;
- extracting risk identifiers based on the determined contextual features;
- selecting a subset of the extracted risk identifiers based the on operational risk category and the activity description;
- and
- generating a risk assessment software based on the subset of the extracted risk identifiers.
Dependencies are inferred from the claim text.