Back to results
US 2024/0403769 A1Published application
Adaptive risk engine
OwnerArmando Lemosinventor
Life of this patent
Estimating the term…
Abstract
Based on data elements from different sources, including risk metrics, control description, policy data, authoritative sources, regulatory input and requirements described in natural language, applied combinations of data correlation principles create an adaptive data technology solution using statistical and logical computational methods to identify natural language correlation between different data categories such as process definitions, risk statements, and control data points to create applicability indexes and cross-walk lineage vectors to help risk identification and remediation.
Claims20
A system for managing risk, comprising:
- one or more processors;
- and
- non-transitory computer-readable storage encoding instructions which, when executed by the one or more processors, causes the system to:
- receive data associated with rules from one or more data sources;
- parse the data into individual data elements;
- associate the individual data elements with category types, including to:
- process the individual data elements using a natural language processing module to identify one of the category types;
- generate a model using the one of the category types identified by the natural language processing module;
- and
- based on the one of the category types, create a lineage vector in an n-dimensional vector space, where each dimension of the lineage vector represents a distinct attribute or characteristic relevant to a lineage of each of the individual data elements, including an origin, a transformation, and a relationship of each individual data element to other data elements;
- train the natural language processing module to classify later received data based on at least the lineage vector;
- generate an action associated with the model, wherein the action is subjected to a validation process according to one or more authentication standards to verify compliance with the rules from the one or more data sources;
- and
- automatically perform the action associated with the model based on the one of the category types.
11 more elements
(canceled)
A computer-implemented method of performing risk assessment, comprising:
- receiving risk-related data associated with rules from one or more data sources, wherein the one or more data sources contains risk metrics;
- parsing the risk-related data into individual data elements;
- associating the individual data elements with at least one risk category type, including:
- processing the individual data elements using a natural language processing module to identify the at least one risk category type;
- generating a model using the at least one risk category type identified by the natural language processing module;
- and
- based on the at least one risk category type, creating a lineage vector in an n-dimensional vector space, where each dimension of the lineage vector represents a distinct attribute or characteristic relevant to a lineage of each of the individual data elements, including an origin, a transformation, and a relationship of each individual data element to other data elements;
- training the natural language processing module to classify later received data based on at least the lineage vector;
- generating an action associated with the model, wherein the action is subjected to a validation process according one or more authentication standards to verify compliance with the rules from the one or more data sources;
- and
- automatically performing the action associated with the risk assessment based on the at least one risk category type displayed on a dashboard for reporting.
8 more elements
A system for managing a risk assessment for a financial industry, comprising:
- one or more processors;
- and
- non-transitory computer-readable storage encoding instructions which, when executed by the one or more processors, causes the system to:
- receive financial data associated with requirements from one or more data sources, wherein the one or more data sources include a financial institution;
- parse the financial data into individual data elements;
- associate the individual data elements with one of a plurality of financial category types, including to:
- process the individual data elements using a natural language processing module to identify a financial category type of the plurality of financial category types;
- generate a model using the financial category type identified by the natural language processing module;
- and
- based on the financial category type, create a lineage vector in an n-dimensional vector space, where each dimension of the lineage vector represents a distinct attribute or characteristic relevant to a lineage of each of the individual data elements, including an origin, a transformation, and a relationship of each individual data element to other data elements;
- train the natural language processing module to classify later received data based on at least the lineage vector;
- generate an action associated with the model, wherein the action is subjected to a validation process according to one or more authentication standards to verify compliance with the requirements from the one or more data sources;
- and
- automatically perform the action associated with the risk assessment based on the one of the plurality of financial category types displayed on a graphical user interface on a financial institution device.
11 more elements
Dependencies are inferred from the claim text.