William slawski-google-patents- how-do-they-influence-search
•Download as PPTX, PDF•
2 likes•1,241 views
Bill Slawski presented a webinar on analyzing patents related to search engines and SEO. He discussed 12 Google patents covering topics like PageRank, Google's news ranking algorithm, analyzing images to detect brand penetration, and building user location history. The patents described Google's work in building knowledge graphs from web pages, ranking entities in search results, question answering, and determining quality visits to local businesses.
Report
Share
More Related Content
What's hot
What's hot (20)
Similar to William slawski-google-patents- how-do-they-influence-search
Similar to William slawski-google-patents- how-do-they-influence-search (20)
More from Bill Slawski
More from Bill Slawski (16)
Recently uploaded
Recently uploaded (20)
William slawski-google-patents- how-do-they-influence-search
- 1. #seozraz webinar: (with Bill Slawski, SEO by the Sea) Public · Event · by Basta digital October 13, 2021 https://www.seobythesea.com SEOzraz Webinar https://gofishdigital.com Twitter: @bill_slawski
- 2. Why look at Patents? A business analyst approach to marketing and SEO.
- 3. Parts of a Patent • Title • Inventors • Assignee • FILED (FILING DATE) • PRIORITY INFORMATION • REFERENCES CITED: PRIOR ART • ABSTRACT • DRAWINGS • SPECIFICATION • BACKGROUND • DETAILED DESCRIPTION • CLAIMS
- 4. First Claim For PageRank • Method for node ranking in a linked database • https://patents.google.com/patent/US628599 9B1/en • What is claimed is: • 1. A computer implemented method of scoring a plurality of linked documents, comprising: • obtaining a plurality of documents, at least some of the documents being linked documents, at least some of the documents being linking documents, and at least some of the documents being both linked documents and linking documents, each of the linked documents being pointed to by a link in one or more of the linking documents; • assigning a score to each of the linked documents based on scores of the one or more linking documents and • processing the linked documents according to their scores.
- 5. Google’s News Ranking Algorithm - Updated 3 times as continuation patents • Systems and methods for improving the ranking of news articles Inventors: Michael Curtiss, Krishna A. Bharat, and Michael Schmitt Assignee: Google LLC US Patent: 10,459,926 Granted: October 29, 2019 Filed: April 27, 2015 • Evolution of Google’s News Ranking Algorithm • https://www.seobythesea.com/20 19/10/news-ranking-algorithm/ • determining a quantity of named entities that (i) occur in the first object that is associated with the first source, and (ii) do not occur in objects that are identified as sharing a same cluster with the first object but that are associated with one or more sources other than
- 6. A look at 12 Google Patents
- 7. Systems and methods for searching quotes of entities using a database Inventors: Eyal Segalis, Gal Chechik, Yossi Matias, Yaniv Leviathan, and Yoav Tzur Assignee: GOOGLE US Patent: 9,727,617 Granted: August 8, 2017 Filed: March 10, 2014 This is a continuation patent, and the claims have been updated from finding answers on the knowledge graph to analyzing audio to answer queries. They recognize that quote searchers are intended to show a person giving a quote, rather than identifying who said what.
- 8. Generating ranked lists of entities Inventors: Toshiaki Fujiki, Slaven Bilac, Kavi J. Goel, Shuhei Takahashi, Tomohiko Kimura Assignee: Google LLC US Patent: 10,691,702 Granted: June 23, 2020 Filed: August 31, 2017 Ranked Entities in Search Results at Google https://www.searchenginejournal.com/ranke d-entities-google-search- results/372973/#close A query such as “Science Fiction Books 2021” will return pages with entities on them, and it will create a knowledge graph from those pages, and extract appropriate entities and rank those in a search carousel in an answering SERP.
- 9. Brand penetration determination system using image semantic content Inventors: Yan Mayster, Brian Edmond Brewington, and Rick Inoue Assignee: Google LLC (Mountain View, CA) US Patent: 11,107,099 Granted: August 31, 2021 ed: July 12, 2019 Detecting Brand Penetration Over Geographic Locations https://gofishdigital.com/detecting- brand-penetration-over-geographic- locations/ Google may start analyzing photos to identify brand penetration at different geographic locations across the country, including Streetviews Storefront windows and targeted advertisements, and identify business logos and tell what is selling where.
- 10. Systems and methods for generating a user location history Inventors: Daniel Mark Wyatt, Renaud Bourassa-Denis, Alexander Fabrikant, Tanmay Sanjay Khirwadkar, Prathab Murugesan, Galen Pickard, Jesse Rosenstock, Rob Schonberger, and Anna Teytelman Assignee: Google LLC US Patent: 9,877,162 Granted: January 23, 2018 Filed: October 11, 2016 Google’s Mobile Location History https://www.seobythesea.com/2018/01/goo gles-mobile-location-history/ Google describes how Location history works with mobile devices, and how people can track their location history over time. Google uses GPS, Cell Phone Triangulation, Wifi Access Points and other methods of tracking location, with user permission.
- 11. On-device query rewriting Inventors: David Petrou and Matthew Sharifi Assignee: GOOGLE LLC US Patent: 11,120,090 Granted: September 14, 2021 Filed: July 8, 2019 Rewritten Queries and User-Specific Knowledge Graphs https://www.seobythesea.com/2021/09/rew ritten-queries-and-user-specific-knowledge- graphs/ A mobile Device Collects Data About its user, and builds a User-Specific Knowledge Graph From that Data. It can then use that data to better respond to personalized queries about other entities communitated with in Chat, Email and on the Web.
- 12. On-device machine learning platform applications or other clients Inventors: Pannag Sanketi, Wolfgang Grieskamp, Daniel Ramage, Hrishikesh Aradhye, and Shiyu Hu Assignee: Google LLC US Patent: 11,138,517 Granted: October 5, 2021 Filed: August 11, 2017 On-Device Machine Learning and Prediction https://www.seobythesea.com/2021/10/on- device-machine-learning-and-prediction/ Google tracks a user’s selections on a mobile device and builds a model from user interactions. That information goes to the cloud daily where it is aggregated with other data, and gets returned to the mobile device to complete the machine learned model
- 13. Retrieval-augmented language model pre- training and fine-tuning Inventors: Kenton Chiu Tsun Lee, Kelvin Gu, Zora Tung, Panupong Pasupat, and Ming-Wei Chang Assignee: Google LLC US Patent: 11,003,865 Granted: May 11, 2021 Filed: May 20, 2020 BERT Question-Answering at Google https://www.seobythesea.com/2021/05/ber t-question-answering-at-google/ Google has started using a Pre-Training Language Model using BERT (Bidirectional Encoder Representations from Transformers) which can be used to guess missing content during query rewriting, help answer queries, Predict answer passages on web pages and other NLP Approaches
- 14. Computerized systems and methods for extracting and storing information regarding entities Inventors: Christopher Semturs, Lode Vandevenne, Danila Sinopalnikov, Alexander Lyashuk, Sebastian Steiger, Henrik Grimm, Nathanael Martin Scharli and David Lecomte Assignee: GOOGLE LLC US Patent: 10,198,491 Granted: February 5, 2019 Filed: July 6, 2015 Entity Extractions for Knowledge Graphs at Google https://gofishdigital.com/entity-extractions- knowledge-graphs/ Google is working on extracting Entities and knowledge (relationship information) from Web pages, moving on from Knowledge bases to build Tuples such as Noun->Verb->Objects Triples. Relationships between entities are weighed (confidence levels) based on things such as involving Temporal Weights, Reliability Weights, Popularity Weights and Proximity Weights
- 15. Automatic discovery of new entities using graph reconciliation • Example of “Reverse Tuples” • “Maryland is a state in the United States of America,” • “California is a state in the United States of America.” • “The United States of America has a state named Maryland,” • “The United States of America has a state named California.” Inventors: Oksana Yakhnenko and Norases Vesdapunt Assignee: GOOGLE LLC US Patent: 10,331,706 Granted: June 25, 2019 Filed: October 4, 2017 Google Knowledge Graph Reconciliation https://www.seobythesea.com/2019/08/goo gle-knowledge-graph-reconciliation/
- 16. Providing search results using augmented search queries • Google Looks for Entities in Queries. • Entities are People, Places, and Things (Concepts) • If There is an Entity, Google may Augment SERPs with Knowledge Results (Such as Knowledge panels, PAA Questions, Related Entities, Featured Snippets.) Inventors: Emily Moxley and Sean Liu Assignee: Google LLC US Patent: 10,055,462 Granted: August 21, 2018 Filed: March 15, 2013 Augmented Search Queries Using Knowledge Graph Information https://www.seobythesea.com/2019/08/aug mented-search-queries/
- 17. Generating related questions for search queries Inventors: Yossi Matias, Dvir Keysar, Gal Chechik, Ziv Bar-Yossef, and Tomer Shmiel Assignee: Google Inc. US Patent: 9,679,027 Granted: June 13, 2017 Filed: December 14, 2015 Google Related Questions now use a Question Graph https://www.seobythesea.com/2018/02/rela ted-questions-question-graph/
- 18. Quality visit measure for controlling computer response to query associated with physical location • A quality Visit at a dine-in restaurant can be long enough to eat a meal at a dining table • A Quality Visit at a Fast Food Restaurant can be long enough to place an order at a counter and purchase it, and leave with the order. Inventors: Krzysztof Duleba Assignee: Google LLC US Patent: 10,366,422 Granted: July 30, 2019 Filed: September 9, 2015 Quality Visit Scores to Businesses May Influence Rankings in Google Local Search https://gofishdigital.com/quality-visit-scores/