| CPC G06Q 30/0282 (2013.01) [G06F 16/383 (2019.01); G06F 16/84 (2019.01); G06F 40/20 (2020.01); G06F 40/295 (2020.01); G06F 40/30 (2020.01)] | 16 Claims |
|
1. A computer system comprising:
one or more processing devices and at least one memory device operably coupled to the one or more processing devices via a communication bus, the computer system is configured to:
identify, by a structured data search sub-module embedded within a due diligence module executed by a due diligence engine included in the at least one memory device of the computer system, one or more structured data sources, wherein the one or more structured data sources include at least a portion of structured data, wherein the structured data is directed to one or more subject business entities;
extract, by the structured data search sub-module, the at least a portion of the structured data directed toward the one or more subject business entities;
transmit, by the structured data search sub-module, the at least a portion of the structured data to an unstructured data search sub-module of the due diligence module;
identify, by the unstructured data search sub-module using the at least a portion of the structured data, one or more unstructured data sources, wherein at least a portion of the one or more unstructured data sources are directed to the one or more subject business entities, wherein the at least a portion of the structured data includes information for locating the one or more unstructured data sources;
search, by the unstructured data search sub-module using the information for locating the one or more unstructured data sources, the one or more unstructured data sources to identify one or more documents from the one or more unstructured data sources that have information directed to the one or more subject business entities embedded therein, wherein the one or more documents directed to the one or more subject business entities identify unstructured data, wherein the unstructured data is directed to the one or more subject business entities;
determine, by a data integration sub-module of the due diligence module using a mapping of the at least a portion of the structured data and the identified unstructured data, one or more relationships between the at least a portion of the structured data and at least a portion of the unstructured data;
transmit, by the data integration sub-module, each relationship of the one or more relationships to an unstructured data scoring sub-module of the due diligence module;
score, by the unstructured data scoring sub-module, each relationship of the one or more relationships;
rank, by the unstructured data scoring sub-module, each document of the one or more documents from the one or more unstructured data sources directed to the one or more subject business entities as a function of the score of each relationship of the one or more relationships;
analyze the one or more documents from the one or more unstructured data sources directed to the one or more subject business entities using one or more natural language processing (NLP) processes; and
execute both of:
a sentiment analysis of at least a portion of the unstructured data within a plurality of documents of the unstructured data, thereby determine one or more sentimental associations between at least a portion of the plurality of documents of the unstructured data and at least a portion of the structured data; and
a co-referential analysis of at least a portion of metadata within the plurality of documents of the unstructured data and the at least a portion of structured data, thereby establish a syntactic relationship between a plurality of expressions in a least a portion of text of the unstructured data and the structured data; and
determine a risk of establishing a business relationship with the one or more subject business entities based on the rank of each document of the one or more documents, wherein the computer system is further configured to execute the scoring each relationship of the one or more relationships comprising:
re-evaluate, through a plurality of iterative scorings, the score of each document of the unstructured data comprising one or more of:
generate, by the data integration sub-module, a query for searching the one or more unstructured data source documents; and
search, by the unstructured data search sub-module using the query, the one or more unstructured data sources to identify one or more additional documents from the one or more unstructured data sources that have additional information directed to the one or more subject business entities embedded therein, wherein the one or more additional documents directed to the one or more subject business entities identify additional unstructured data, wherein the additional unstructured data is directed to the one or more subject business entities.
|