I have written a few posts about patents at Google on personalized knowledge graphs (a topic worth thinking about seriously).
When Google introduced the Knowledge Graph in 2012 , they told us there was only one Knowledge Graph. However, it seems that the idea of a knowledge graph was not intended to be a singular idea - there is more than one Knowledge Graph.
Later, Google came out with a patent that told us how each query could return a set of results from which a new Knowledge Graph could be created to answer the original query. These mini-Knowledge Graphs could eventually be combined into one big Knowledge Graph. I wrote about this patent (filed in 2017) in this post:
Answering Questions Using Knowledge Graphs .
Another patent I wrote about was one on user-specific knowledge graphs: User-Specific Knowledge Graphs to Support Queries and Predictions . This patent was filed in November 2013 and was created then. These are personalized knowledge graphs based on information from your search history, from pages you've visited, and from documents like emails azerbaijan phone number data and social media posts you've written and received. This patent states that these personalized knowledge graphs can be stitched together to create a universal knowledge graph (combining non-user-specific knowledge graphs and user-specific knowledge graphs).
I also wrote about how Google could create personalized entity repositories that people could carry around on their mobile devices: A Personalized Entity Repository in the Knowledge Graph . The interesting thing about this is that it contains a knowledge base of information on the specific device, e.g. a mobile phone or a tablet, which means that the answer does not have to come from a server external to it, but can come from a knowledge graph built on top of this personalized knowledge base, namely an entity repository created from a machine learning approach based on the search history and the documents (emails, documents, social media posts) that have been accessed.
A Google white paper prepared for the International Conference on Theory of Information Retrieval (ICTIR) 2019, October 2-5, 2019 – Personal Knowledge Graphs: A Research Agenda by Krisztian Balog and Tom Kenter captures many of the ideas behind the personal knowledge graph patent (originally filed in 2013).
The summary tells us:
Knowledge graphs, organizing structured information about entities, and their attributes and relationships, are ubiquitous today. Entities, in this context, are usually taken to be anyone or anything considered to be globally important. This, however, rules out many entities people interact with on a daily basis.
In this position paper, we present the concept of personal knowledge graphs: resources of structured information about entities personally related to its user, including the ones that might not be globally important. We discuss key aspects that separate them for general knowledge graphs, identify the main challenges involved in constructing and using them, and define our search agenda.
The paper informs us about the purpose of knowledge graphs:
Obvious use cases include enabling rich knowledge panels and direct answers in search result pages, powering smart assistants, supporting data exploration and visualization (tables and graphs), and facilitating media monitoring and reputation management
These are important and essential aspects of how search engines like Google work today . What makes this paper interesting is the fact that it tells us about knowledge graphs that do these things and are tailored to work with individuals. As the authors tell us.