Microsoft patents scheduling system that fixes impossible work shifts
This patent describes a computer system that creates work schedules by grouping jobs based on their physical locations. It uses mathematical clustering to calculate how many shifts are needed for each group and adjusts assignments to ensure workers can realistically reach their jobs.
In the filing’s own words
Some embodiments detect infeasible scheduling requests, such as overlapping do-not-move bookings with a given resource required at different locations, bookings with insufficient travel time, or other enumerated examples. Some embodiments utilize retrieval augmented generation or language model function invocation or both to summarize infeasibility patterns, or to explain scheduling decisions, or to do both. Some embodiments utilize virtual bookings to produce a partial schedule instead of declining to produce any schedule which involves conflicts. Some embodiments partition a scheduling problem into smaller problems using an eligibility graph, or using clusters computed from location data and shift assignment exploration, or both.
What exactly they claim (claim 1)
1. A computing system configured for job scheduling using location-based partitioning, the computing system comprising: a digital memory containing job data structures, each job data structure identifying at least one resource which has a capability to perform at least a portion of a corresponding job, a job duration, and a job location which either specifies a physical location of the job or specifies that the job is location-agnostic; a processor in operable communication with the digital memory and configured by executable processor instructions; a clustering mechanism which upon execution provides job data structure clusters computed from at least the job locations; a shift calculation mechanism which upon execution calculates a cluster workload and a number of shifts corresponding to the cluster workload; a shift assignment mechanism which upon execution provides an assignment that assigns a particular shift to a particular job cluster; a cluster coverage score calculation mechanism which upon execution calculates a cluster coverage score; a cluster coverage score optimization mechanism which upon execution optimizes at least one cluster coverage score by utilizing at least one shift assignment change; and a job scheduling mechanism which upon execution by the computing system provides a schedule of at least a subset of the jobs, the schedule computed from at least one shift assignment or at least one shift assignment change or both.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- DETECTING AND PROCESSING INCONSISTENT SCHEDULING DATA
- Publication number
- US20260330346A1
- Application number
- 19216879
- Filed
- May 23, 2025
- Published
- Oct 22, 2026
- Inventors
- 9
- Claims
- 20
Classified under
G06Q 10/06311 Physics & computingG06Q 10/02 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.