Logfile Recommender Service Uses ML for Support Tickets

ChangeBridge: Patent Apps - Business Methods (G06Q)

Detected March 26th, 2026

Summary

The USPTO has published a patent application (US20260087499A1) for a logfile recommender service developed by SAP SE. The service uses machine learning models trained on past support ticket data to predict and recommend relevant logfile types for support tickets, aiming to expedite resolution.

View original document View source feed page

What changed

This document is a published patent application (US20260087499A1) for a logfile recommender service developed by SAP SE. The service utilizes machine learning models, including attachment prediction and recommendation models, to analyze support ticket data (titles, problem descriptions, communication records) and suggest relevant logfile types. The goal is to streamline the support ticket resolution process by ensuring the correct logfiles are attached.

As this is a patent application, there are no immediate compliance obligations for regulated entities. However, companies involved in software development, IT support, or data analytics may find the described technological approach relevant to their own product development or intellectual property strategies. The application was filed on September 26, 2024.

Source document (simplified)

← USPTO Patent Applications

LOGFILE RECOMMENDER SERVICE

Application US20260087499A1 Kind: A1 Mar 26, 2026

Assignee

SAP SE

Inventors

Anviti Srivastava, Lukas Konstandin, Sudhir Verma, Nirjar Gandhi, Nibedita Dutta, Aditya Agashe

Abstract

A logfile recommender service incorporates trained machine learning models to predict recommended logfile types for support tickets. The machine learning models are trained using data from past support tickets such as titles, problem descriptions, and communication records. After receiving a request to generate a logfile recommendation for a given support ticket, the logfile recommender service first calls an attachment prediction machine learning model (e.g., a binary classification model) to predict whether logfiles are relevant to the support ticket. If so, the logfile recommender service calls an attachment recommendation machine learning model (e.g., a multi-label classification model) to generate a list of recommended logfile types for the support ticket, which is output by the logfile recommender service as the logfile recommendation. Logfiles of the recommended types can then be attached to the support ticket to facilitate and expedite resolution of the support ticket.