View source for 18049598. MEASURING PROBABILITY OF INFLUENCE USING MULTI-DIMENSIONAL STATISTICS ON DEEP LEARNING EMBEDDINGS simplified abstract (MICROSOFT TECHNOLOGY LICENSING, LLC)

=MEASURING PROBABILITY OF INFLUENCE USING MULTI-DIMENSIONAL STATISTICS ON DEEP LEARNING EMBEDDINGS=


==Organization Name==

[[:Category:MICROSOFT TECHNOLOGY LICENSING, LLC|MICROSOFT TECHNOLOGY LICENSING, LLC]]


[[Category:MICROSOFT TECHNOLOGY LICENSING, LLC]]

==Inventor(s)==

[[:Category:Amund Tveit of Trondheim (NO)|Amund Tveit of Trondheim (NO)]][[Category:Amund Tveit of Trondheim (NO)]]

[[:Category:Kateryna Solonko of Oslo (NO)|Kateryna Solonko of Oslo (NO)]][[Category:Kateryna Solonko of Oslo (NO)]]

[[:Category:Zoran Hranj of Oslo (NO)|Zoran Hranj of Oslo (NO)]][[Category:Zoran Hranj of Oslo (NO)]]

[[:Category:Aleksander Werpachowski of Oslo (NO)|Aleksander Werpachowski of Oslo (NO)]][[Category:Aleksander Werpachowski of Oslo (NO)]]

[[:Category:Roman Werpachowski of Ameberg (NO)|Roman Werpachowski of Ameberg (NO)]][[Category:Roman Werpachowski of Ameberg (NO)]]

[[:Category:Mohammadreza Bonyadi of Trondheim (NO)|Mohammadreza Bonyadi of Trondheim (NO)]][[Category:Mohammadreza Bonyadi of Trondheim (NO)]]

[[:Category:Arun Shankar Iyer of Bangalore (IN)|Arun Shankar Iyer of Bangalore (IN)]][[Category:Arun Shankar Iyer of Bangalore (IN)]]

==MEASURING PROBABILITY OF INFLUENCE USING MULTI-DIMENSIONAL STATISTICS ON DEEP LEARNING EMBEDDINGS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18049598 titled 'MEASURING PROBABILITY OF INFLUENCE USING MULTI-DIMENSIONAL STATISTICS ON DEEP LEARNING EMBEDDINGS

The disclosure outlines a system for measuring the probability of influence in digital communications to distinguish between content originating from a person's prior knowledge or new information obtained from interactions with others.

* Utilizes multidimensional statistics on embeddings representing communications to estimate the probability that a new communication by a user comes from the same distribution as their prior communications.
* Generates an estimated probability that a new communication comes from the same distribution as communications accessible to the user from another individual.
* Compares the two probabilities to determine if the new communication is more likely influenced by exposure to the other individual's communications rather than the user's own historical knowledge.
* Provides an influence attribution recommendation based on the comparison of probabilities.

Potential Applications:
- Social media platforms could use this technology to identify and attribute influences on user-generated content.
- Marketing companies could utilize this system to understand the impact of different communication sources on consumer behavior.

Problems Solved:
- Helps in determining the origin of digital communications, whether from personal knowledge or external influences.
- Provides insights into the influence of interactions on communication content.

Benefits:
- Enhances understanding of the factors influencing digital communication.
- Enables more accurate attribution of influences in online interactions.

Commercial Applications:
Title: Influence Attribution System for Digital Communications
This technology could be valuable for social media platforms, marketing agencies, and online content creators looking to understand and analyze the impact of various influences on communication content.

Questions about Influence Attribution System for Digital Communications:
1. How does this system differentiate between a user's own historical knowledge and external influences on new communications?
2. What are the potential implications of accurately attributing influences in digital communications for social media platforms and marketing companies?


==Original Abstract Submitted==

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.



[[Category:G06F40/30]]
[[Category:G06N3/04]]
[[Category:G06N3/08]]
[[Category:CPC_G06F40/30]]