Microsoft patents tool that spots when your posts copy others' ideas
Microsoft has filed a patent for a system that uses AI to check if a user's new message is based on their own past writing or influenced by others they have read. It compares the meaning of the new text against previous messages from the user and others to see which source is more likely. If the new content matches others' work more closely, the system highlights those specific parts as being influenced.
In the filing’s own words
The disclosure herein describes a system for measuring probability of influence in digital communications to determine if communication content originated in a person's own prior knowledge or new information more recently obtained from interaction with communications of others. An estimated probability a new communication by a first user comes from the same distribution as prior communications of the first user are generated using multidimensional statistics on embeddings representing the communications. A second estimated probability that the new communication comes from the same distribution as communication(s) of a second user that were accessible to the first user are generated. If the second probability is greater than the first probability, the new communication is more likely influenced by exposure of the first user to the second user's communications rather than the first user's own historical knowledge. An influence attribution recommendation is generated, including an influence attribution or other recommended action.
What exactly they claim (claim 1)
1. A system, comprising: a processor; and a memory storing computer-executable instructions that, when executed by the processor, cause the system to: generate, using a natural language processing model, semantic embeddings, each semantic embedding associated with a portion of content of a communication generated by a first user; compare the semantic embeddings against second semantic embeddings associated with prior communications of other users, to determine an indication of influence for each portion of content of the communication; identify portions of the communication that were most influential based on the indication of influence; and present, via a user interface, influential portions of the communication by augmenting the portions of the communication.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- MEASURING PROBABILITY OF INFLUENCE USING MULTI-DIMENSIONAL STATISTICS ON DEEP LEARNING EMBEDDINGS
- Publication number
- US20260330341A1
- Application number
- 19686604
- Filed
- May 22, 2026
- Published
- Oct 22, 2026
- Inventors
- 7
- Claims
- 20
Classified under
G06Q 10/04 Physics & computingG06F 40/30 Physics & computingG06N 3/08 Physics & computingG06Q 10/46 Physics & computingG06Q 10/48 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.