Microsoft patents AI system that suggests professional connections based on shared interests
Microsoft describes a method using two machine learning models to analyze user requests and group related entities. The system then matches these groups with private user data to identify and recommend specific people for professional networking interactions.
In the filing’s own words
Artificial intelligence techniques for connections networking are described. In one embodiment, for example, a method comprises receiving a natural language query to group a set of entities by a first machine learning model trained on a public dataset, generating a set of entity groups by the first machine learning model based on the natural language query and the set of entities, generating a set of connections entity groups based on the set of entity groups by a second machine learning model trained on a private dataset, selecting a member identifier (ID) representing a member of a connections networking system associated with an entity from a connections entity group of the set of connections entity groups, and sending a recommendation for a networking service to an electronic device based on the member ID. Other embodiments are described and claimed.
What exactly they claim (claim 1)
1. A method, comprising: receiving a request associated with a first user identifier (ID) to interact with a networking application of a connections networking system, wherein the first user ID represents a first user of the connections networking system; generating, by a first machine learning model, a set of entity groups based on the request, wherein at least one of the entity groups comprises multiple related entities defined by a first set of rules; generating, by a second machine learning model, a set of connections entity groups based on the set of entity groups generated by the first machine learning model, wherein a connections entity group comprises two or more related entities from the multiple related entities defined by a second set of rules; retrieving connections data associated with the first user ID, the connections data comprising one or more parameters for the first user ID; determining a connections entity group from the set of connections entity groups generated by the second machine learning model based on the first user ID using the connections data; determining a second user ID of the connections entity group using a set of common parameters from the one or more parameters for the first user ID and one or more parameters for the second user ID, wherein the second user ID represents a second user of the connections networking system; and causing presentation of the second user ID on a graphical user interface (GUI) of a client system as a candidate to interact with the networking application of the connections networking system.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Artificial intelligence techniques for connections networking
- Patent number
- US12771612B2
- Application number
- 18758052
- Filed
- Jun 28, 2024
- Granted
- Oct 20, 2026
- Inventors
- 5
- Claims
- 20
Classified under
H04L 41/12 Electricity & electronicsH04L 41/16 Electricity & electronicsH04L 67/131 Electricity & electronicsMore 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.