Computerized methods and systems for grouping data using data streams

A non-transitory computer-readable medium storing computer-executable instructions that when executed by a processor of a computer causes the processor to:

• publish a plurality of incident reports received over a network from a plurality of client devices into a data stream according to a document format;
• in response to a threshold number of incident reports being published into the data stream over a time slice window, evaluate phrases within the incident reports in the data stream to identify a set of features having divergence amongst the incident reports above a divergence threshold;
• compute a model correlating incident reports to the set of features;
• apply the model to a first incident report and a second incident report to compute a first feature vector for the first incident report and a second feature vector for the second incident report;
• compare the first feature vector and a second feature vector to determine a similarity between the first incident report and the second incident report;
• group the first incident report and the second incident report in response to the similarity exceeding a similarity threshold;
• and
• render a user interface populated with the first incident report and an indication that the second incident report is similar to the first incident report.

A computer-implemented method, the computer-implemented method involving a computing device comprising a processor, and the computer-implemented method comprising:

• creating, by a processor, a data stream from a plurality of communications received from one or more network channels, wherein the plurality of communications includes incident reports;
• for a time slice window of the data stream, deriving, by the processor, a plurality of features from the data stream by at least analyzing text from the incident reports;
• constructing, by the processor, feature vectors for a plurality of incident reports by at least analyzing text from the plurality of incident reports to determine whether the text corresponds to features within the plurality of features, wherein a feature vector of an incident report comprises a plurality of bits representing the plurality of features, wherein a bit representing a feature is set to either a first value to indicate that the incident report has the feature or a second value to indicate that the incident report does not have the feature;
• determining, by processor, amounts of similar values of bits within feature vectors to group incident reports that comprise similar features, wherein a first incident report group of one or more similar incident reports is created based upon similar values of bits between the one or more similar incident reports being greater than a threshold;
• and
• controlling, by the processor, a display to render a user interface defining the first incident report group on the display of a computing device.