Welcome back to another week for the geeks.
The last few weeks were a bit uneventful, but I did come up with a few that really are worth a read.
As always, patents take some time to get into, but the more of them you read, the easier it gets.
So, please do take some time to click through and give them a full read.
It can only make you a better SEO.
Also, my first post of 2021 will be a round-up of all the Google search-related patents that I collected over the year that was 2020. Be sure to stay tuned for that.
Machine Learning to Identify Opinions in Documents
- Filed: April 26, 2020
- Awarded: Nov 10, 2020
Abstract
“Example aspects of the present disclosure are directed to systems and methods that employ 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 being opinions or not opinions. Further, in some implementations, portions classified as opinions can be considered for inclusion in an informational display. For example, document portions can be ranked according to importance and selected for inclusion in an informational display based on their ranking. “
Dave’s Notes
This one, as with most patents, can be adapted and used in a variety of ways, it does seem that a lot of the original impetus is towards news, (or potentially blogs).
By understanding the tenor/opinion of a document it can be ranked accordingly.
As stated in the patent, “a portion of the document that has been classified as opinion and/or ranked as having high importance.” One could also imply that it further limits the user’s exposure to new information by showing highly ranked information that reinforces their own perceived opinions on a topic (query).
From the Patent
“Understanding of content (e.g., textual content) contained in a document by a computing system is a challenging problem. Even in the professional news journalism space, where articles are typically written in high quality language and syntax, computing systems are currently able to understand only very little about the actual content of news articles. Furthermore, determining how a given article compares to other, related news articles written by other journalists is an even more challenging task.”
“Example aspects of the present disclosure are directed to systems and methods that employ 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 being opinions or not opinions. Further, in some implementations, portions classified as opinions can be considered for inclusion in an informational display. For example, document portions can be ranked according to importance and selected for inclusion in an informational display based on their ranking. “
Personalization of Web Search Results Using Term, Category, and Link-Based User Profiles
- Filed: March 27, 2019
- Awarded: Dec 1, 2020
Dave’s Take
As I was digging this patent (on personalization) it discusses (in part) the PageRank/Random Surfer approach. And the limitations therein.
For those not all that intimate with it, that’s the core element of links, which is an obviously important area.
They seek to adapt this by a more personalized approach and a “profile rank” to better tailor the existing (PageRank created) search results… Anyway, interesting stuff.
From the Patent
“In reality, a user like the random surfer never exists. Every user has his own preferences when he submits a query to a search engine. The quality of the search results returned by the engine has to be evaluated by its users’ satisfaction. When a user’s preferences can be well defined by the query itself, or when the user’s preference is similar to the random surfer’s preference with respect to a specific query, the user is more likely to be satisfied with the search results. However, if the user’s preference is significantly biased by some personal factors that are not clearly reflected in a search query itself, or if the user’s preference is quite different from the random user’s preference, the search results from the same search engine may be less useful to the user, if not useless.”
Contextually Relevant Knowledge Panels in an Application Environment
- Filed: May 23, 2019
- Awarded: Dec 15, 2020
Abstract
“From the content of a document, a factual entity that relates to the content of the document is determined. Content for a knowledge panel is requested. A knowledge panel is a user interface element that provides a collection of content related to the factual entity. The contents of the knowledge panel is received for contemporaneous display on the user device with the content of the document.”
Dave’s Notes
Interestingly this one doesn’t really have a ton of new elements we’d not be familiar with when it comes to knowledge panels, but I’ve actually not seen a ton of descriptive patents on them. So, it’s worth inclusion here today.
For example, if you’re not familiar with what an entity is fully, they do describe them as, “Entities can include, but are not limited to, a person, place, country, landmark, animal, historical event, organization, business, sports team, sporting event, movie, song, album, game, work of art, or any other appropriate entity.”
From the Patent
“However, when developing search queries to submit to the search engine, the user often needs to provide contextual information of the document in the query. For example, a user may be authoring a document to describe bears in the Smokey Mountains. The query the user will need to formulate will need to express this informational need.”
“In some implementations, a knowledge panel provides a summary of information for the entity. For example, a knowledge panel for a singer may include the name of the singer, an image 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 granular information. For example, if a document section is about the singer’s childhood, the knowledge panel can provide information regarding the school the singer attended, a snippet about the town the singer grew up in, and the singer’s recollections of growing up there.”
That’s about it for this week folks. If there’s a specific area of search that you’d be interested in reading up on, feel free to get in touch with me.
I am always happy to help.
See you next week!
More Resources:
