Using machine learning and free text data to detect and report events associated with use of software applications
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12271446-B1
Publication Date
2025-04-08
Expiration Date
Abstract
Aspects of the present disclosure are directed to systems, methods, and computer readable media for executing actions for events associated with use of applications. A computing system can identify free text associated with an application to be evaluated for at least one of a plurality of events associated with a use of the application. The computing system can apply the free text to a machine learning (ML) architecture. The computing system can determine, based on applying the free text to the ML architecture, a value indicating a likelihood of occurrence of an event associated with the use of the application. The computing system can provide to a generative ML model, a model input based on the free text and the value, to obtain data for an electronic document characterizing the event. The computing system can execute an action using the data for the electronic document.
Core Innovation
The invention relates to executing actions for events associated with use of applications. Free text associated with an application is identified for evaluation for at least one of a plurality of events associated with the use of the application, and the free text is applied to a machine learning architecture trained using a plurality of sample texts indicative of at least one of the plurality of events. A value indicating a likelihood of occurrence of an event is determined based on that applying.
The method provides, to a generative ML model, a model input based on the free text and the likelihood value to obtain data for an electronic document characterizing the event associated with the use of the application. The electronic document characterizes the event, and data for the electronic document is obtained from the generative ML model. An action is executed using the data for the electronic document.
The invention is also implemented as a system for events associated with use of applications. The system includes one or more processors and memory configured to identify free text, apply the free text to an ML architecture trained using sample texts indicative of events, determine a likelihood value, provide a model input based on the free text and the likelihood value to a generative ML model to obtain data for an electronic document, and execute an action using the data for the electronic document.
Claims Coverage
Two independent claims are present, one method and one system. The inventive coverage centers on a shared pipeline with free-text identification, ML-architecture-based likelihood value determination, generative ML document generation, and action execution, with dependent refinements mentioning event category outputs, likelihood threshold gating, constrained communication sources for free text, and additional structure for model input generation.
Likelihood-based action execution using generative ML electronic document
Identifying free text associated with an application to be evaluated for at least one of a plurality of events associated with a use of the application; applying the free text to a machine learning architecture trained using a plurality of sample texts indicative of at least one of the plurality of events; determining a value indicating a likelihood of occurrence of an event; providing to a generative ML model a model input based on the free text and the value to obtain data for an electronic document characterizing the event; executing an action using the data for the electronic document.
Event monitoring system with likelihood-determined generative document
Identify free text associated with an application; apply the free text to an ML architecture trained using a plurality of sample texts indicative of events; determine a value indicating a likelihood of occurrence of an event; provide to a generative ML model a model input based on the free text and the value to obtain data for an electronic document characterizing the event; execute an action using the data for the electronic document.
The independent claims are coextensive in the core workflow: free-text identification, ML-architecture-based likelihood value determination, generative ML model input using the free text and likelihood value to obtain data for an electronic document characterizing the event, and executing an action using that electronic document data.
Stated Advantages
Supports execution of actions using data for an electronic document characterizing the event associated with use of the application.
Documented Applications
No documented applications found
Interested in licensing this patent?