Welcome back to another week for the geeks.

The past few weeks have been a little uneventful, but I've come up with a few that are really worth reading.

As always, it takes some time to apply for patents. However, the more you read, the easier it gets.

So please take some time to click through and read them in full.

It can only make you a better SEO.

Also, my first post of 2021 will be a recap of all the patents related to Google search that I amassed in 2020. Be curious about it.

  • Filed: April 26, 2020
  • Excellent: November 10, 2020

abstract

“Example aspects of the present disclosure relate to systems and methods that use a machine-learned opinion classification model to classify portions (e.g., sentences, phrases, paragraphs, etc.) of documents (e.g., news articles, web pages, etc.). ) as opinions or not opinions. Further, in some implementations, parts classified as opinions may be considered for inclusion in an information display. For example, document parts can be classified according to importance and selected for inclusion in an information display based on their ranking. "

advertising

Read on below

Dave's notes

As with most patents, this can be customized and used in a number of ways. It seems that much of the original impetus has been on news (or potential blogs).

Understanding the tenor / opinion of a document can rank it accordingly.

As stated in the patent, "a portion of the document classified as an opinion and / or found to be of high importance". One could also imply that this further limits the user's exposure to new information by displaying high-level information that reinforces his own perceived opinions on a topic (query).

From the patent

“Understanding content (e.g. textual content) contained in a document by a computer system is a challenging problem. Even in the realm of professional news journalism, where articles are typically written in good quality language and syntax, computer systems are currently able to understand very little about the actual content of news articles. Additionally, determining how a given article compares to other related news articles by other journalists is an even more difficult task. "

“Example aspects of the present disclosure relate to systems and methods that use a machine-learned opinion classification model to classify portions (e.g., sentences, phrases, paragraphs, etc.) of documents (e.g., news articles, web pages, etc.). ) as opinions or not opinions. Further, in some implementations, parts classified as opinions may be considered for inclusion in an information display. For example, document parts can be classified according to importance and selected for inclusion in an information display based on their ranking. "

advertising

Read on below

  • Filed: March 27, 2019
  • Excellent: 1st December 2020

Dave & # 39; s Take

While I was digging out this patent (for personalization) the PageRank / Random Surfer approach was being discussed (in part). And the limitations in it.

For those who are not too familiar with it, this is the core element of links, which is an obviously important area.

You're trying to customize this through a more personal approach and a "profile rank" to better match the existing search results (created by PageRank) … Anyway, interesting things.

From the patent

“In reality, a user like the casual surfer never exists. Each user has their own settings when submitting a query to a search engine. The quality of the search results returned by the search engine must be assessed based on the satisfaction of the users. If a user's preferences can be well defined by the query itself, or if the user's preference is similar to the casual surfer's preference for a particular query, the user is more likely to be satisfied with the search results. However, if the user's preference is significantly skewed by some personal factors that are not clearly reflected in a search query itself, or if the user's preference is very different from the casual user's preference, the search results from the same search engine may be less useful to the User if not useless. "

  • Filed: 23 May 2019
  • Excellent: December 15, 2020

abstract

“A factual unit is determined from the content of a document, which relates to the content of the document. Content for a knowledge panel is requested. A knowledge panel is a user interface element that provides a collection of content related to the actual entity. The content of the knowledge panel is received for simultaneous display of the content of the document on the user device. "

Dave's notes

Interestingly, this one doesn't actually contain a ton of new elements that we are not familiar with when it comes to knowledge boards, but I haven't actually seen many descriptive patents on them. So it is worth being included here today.

For example, if you are unsure what an entity is, describe it as follows: “Entities may or may not include a person, place, country, landmark, animal, historical event, organization, or company limited to, sports team, sporting event, movie, song, album, game, work of art, or other suitable entity. "

advertising

Read on below

From the patent

“However, when developing search queries for submission to the search engine, the user often needs to provide contextual information about the document in the query. For example, a user can compose a document describing bears in the Smoky Mountains. The query that the user has to formulate must express this need for information. "

“In some implementations, a knowledge panel provides a summary of information for the company. For example, a knowledge panel for a singer may include the singer's name, a picture of the singer, a description of the singer, one or more facts about the singer, and content that identifies songs and albums recorded by the singer. "

“In some implementations, a knowledge panel can provide more detailed information. For example, if a section of the document deals with the singer's childhood, the knowledge panel may contain information about the school the singer attended, a snippet of the city the singer grew up in, and the singer's memories of growing up there. "

advertising

Read on below

That's it for this week folks. If there is a specific search area that you would like to find out more, please feel free to contact me.

I always help gladly.

Until next week!

More resources:

LEAVE A REPLY

Please enter your comment!
Please enter your name here