Predicting site quality
Topics: Document Classification, E-E-A-T, Navneet Panda, Passage based retrieval, Phrase based Indexing, Probably in use, Ranking
The patent describes methods for predicting site quality scores for new websites using phrase models. It involves generating a phrase model from previously scored sites, where the model maps phrase frequency measures to average site quality scores.
For new sites, relative frequencies of phrases are determined and used with the model to calculate an aggregate site quality score. This predicted score can then be used by search engines to help rank resources from that site in search results.
... You would like to read more about this exciting topic or use a tool? You can read the full article or use the tool as a member of the GEO Resesarch Suite. Complete access to full exclusive blog articles, analysis of the patents, research paper, other SEO and GEO related documents and use of AI assistants adn tools are only for GEO Research Suite Premium (yearly) and GEO Research Suite Premium (monthly) members.
Your advantages:
+ Get access to the full exclusive paid articles in the blog.
+ Full analysis of hundreds of well researched active Microsoft, OpenAI and Google patents and research paper.
+ Save a lot of time and get insights in just a few minutes, without having to spend hours analyzing the documents.
+ Get quick exclusive insights about how LLMs, search engines and Google could work with easy to understand summaries and analysis.
+ All patents classified by topic for targeted research.
+ New patent summaries and analysis every week. Weekly notification via E-Mail
+ Get GEO expert knowledge for optimizing your visibility in AI Search via the GEO assistant
+ Use all AI Research Tools to gain insights in seconds from all documents in the patent database, Google Leaks and DOJ trials via the Patent & Paper Analyzer and Google Leak Analyzer
+ Gain fundamental insights for your SEO and GEO work and become a real thought leader.
Get access to the GEO Research Suite and become a thought leader now!
Your advantages:
+ Get access to the full exclusive paid articles in the blog.
+ Full analysis of hundreds of well researched active Microsoft, OpenAI and Google patents and research paper.
+ Save a lot of time and get insights in just a few minutes, without having to spend hours analyzing the documents.
+ Get quick exclusive insights about how LLMs, search engines and Google could work with easy to understand summaries and analysis.
+ All patents classified by topic for targeted research.
+ New patent summaries and analysis every week. Weekly notification via E-Mail
+ Get GEO expert knowledge for optimizing your visibility in AI Search via the GEO assistant
+ Use all AI Research Tools to gain insights in seconds from all documents in the patent database, Google Leaks and DOJ trials via the Patent & Paper Analyzer and Google Leak Analyzer
+ Gain fundamental insights for your SEO and GEO work and become a real thought leader.
Get access to the GEO Research Suite and become a thought leader now!
Already a member? Log in here
Behzad Hussain
10.12.2024, 18:06 Uhr
Thanks for this nice explanation.
The Phrase Model generation and weighting is very complex in the Patent but you have explained these factors very nicely and comprehensively.
Olaf Kopp
10.12.2024, 18:37 Uhr
THX Behzad!
Behzad Hussain
19.01.2025, 12:58 Uhr
You mentioned this: “The process starts by identifying n-grams (phrases consisting of 2 to 5 words) within the text of the sites being analyzed. ”
In the Patent it’s also mentioned that the one gram is also considered. “In other implementations, n-grams of only one length are used.” (It’s mentioned under the exaplanation of Fig. 2, explanation of first step 200.
I think “only one length” refers here as unigram or 1-gram.