Microsoft patents search ranking that prioritizes active job candidates
This patent describes a system for online job platforms that ranks search results based on how active a candidate is, rather than just their qualifications. It uses machine learning to score candidates based on how often they visit the site and interact with other users, allowing recruiters to switch between lists sorted by relevance or activity.
In the filing’s own words
The disclosed embodiments provide a system for processing data. During operation, the system determines activity features for candidates that match parameters of a search from a moderator of an opportunity, wherein the activity features include an amount of interaction between a candidate and additional moderators and a frequency of visits by the candidate to a platform used to conduct the interaction between the candidate and the additional moderators. Next, the system applies a machine learning model to the activity features to produce activeness scores representing levels of activity of the candidates with respect to the platform. The system then generates a ranking of the candidates according to the activeness scores. Finally, the system outputs at least a portion of the ranking as a set of search results of the search.
What exactly they claim (claim 1)
1. A method comprising: identifying, by a processing circuit, a set of candidate identifiers having profiles hosted by an online service with profile attributes that match search parameters of a search query; determining, by the processing circuit, activity features for each of the set of candidate identifiers, wherein the activity features include an interaction level corresponding to one of the set of candidate identifiers and the online service; tracking, by the processing circuit, profile events associated with the set of candidate identifiers and storing profile event data corresponding to the tracked profile events in a database, wherein the profile events include at least entity interaction data representing interactions with the online service; applying, by the processing circuit, a first machine learned model, trained on the profile event data, to profile attributes associated with the set of candidate identifiers to produce relevance scores corresponding to a measure of relevance for each of the set of candidate identifiers based on the profile attributes; generating, by the processing circuit, a first ranking of the set of candidate identifiers based on the corresponding relevance score of the set of candidate identifiers; applying, by the processing circuit, a second machine learned model to the activity features to produce activity scores corresponding to levels of activity of candidates corresponding to the set of candidate identifiers with respect to the online service; generating, by the processing circuit, a second ranking of the set of candidate identifiers based on the corresponding activity score of the set of candidate identifiers with respect to the online service; and presenting, by the processing circuit, a user interface element that when activated causes the user interface to switch between display of at least a portion of the first ranking of the set of candidate identifiers and at least a portion of the second ranking of the set of candidate identifiers.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Ranking candidate search results by activeness
- Patent number
- US12762195B2
- Application number
- 19008789
- Filed
- Jan 3, 2025
- Granted
- Oct 13, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06F 16/9536 Physics & computingG06F 16/90335 Physics & computingG06F 16/9538 Physics & computingG06N 20/00 Physics & computingG06Q 10/40 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.