Creation, Use And Training Of Computer-Based Discovery Avatars

A method comprising:

• analyzing extracted data features from a tokenized data source to identify a data cluster,
• wherein the data cluster includes a plurality of data elements associated with identifiers and extracted data features that share an attribute;
• presenting, to an analyst, a first source datum for review, from the plurality of data elements from the tokenized data source, based at least in part on the identifiers within the data cluster;
• scoring the first source datum based at least in part on relevance of the first source datum to a substantive topic;
• presenting, to the analyst, a second source datum from the plurality of data elements from the data cluster,
• wherein the second source datum is selected based at least in part on the identifiers within the data cluster;
• scoring the second source datum based at least in part on relevance of the second source datum to the substantive topic;
• comparing the score of the first source datum to the score of the second source datum;
• and
• generating a computer-based discovery avatar by optimizing a mathematical model based at least in part on the comparison of scores.

A method comprising:

• analyzing, using a natural language processor, data features extracted from a data source to determine a one or more data clusters,
• wherein the one or more data clusters include extracted data features that share an attribute that is related to a super-set topic, and
• wherein the one or more data clusters include identifiers that are associated with a plurality of data elements from the source data;
• presenting, to one or more analysts, data elements from the one or more data clusters for review and scoring,
• wherein the data elements from the one or more data clusters are selected based at least in part on the identifiers relating to the super-set topic;
• generating a computer-based discovery avatar parent, by optimizing a first mathematical model, based at least in part on a comparison of scores of the data elements provided by the one or more analysts;
• generating a computer-based discovery avatar child, by optimizing a second mathematical model, based on a second set of extracted data features that share a second attribute that is related to both the super-set topic and a subset topic;
• and
• generating a graphical user interface to receive, from the one or more analysts, a search request and present, to the one or more analyst, the source data based on the computer-based discovery avatar parent and the computer-based discovery avatar child in response to the search request.