Back to results
US 12,596,765 B2Granted
Generation and use of content briefs for network content authoring
AssigneeGraphite Growth, Inc.
InventorsGregory Druck, Luis Alfredo Portillo Castillo
Life of this patent
Estimating the term…
Abstract
Summary generation functionality generates summaries (“content briefs”) with respect to topics from an existing topic graph that organizes a set of keywords into related groups over a set of electronic documents, such as web pages. Each content brief provides a summary of a corresponding topic from the topic graph. Content authors can consult the content brief for a given topic to gain insight into how to revise or draft a web page or other electronic document to improve its ranking in a search engine with respect to which the topic graph was generated.
Claims10
A computer-implemented method of generating a content brief for a topic, the computer-implemented method comprising:
- accessing a topic graph, the topic graph comprising a set of topics, each topic having an associated set of keywords, the associated set of keywords for each topic in the topic graph determined by:
- selecting, based on the set of topics in the topic graph, between a first calculation and a second calculation to calculate degree of similarity between each of a plurality of keywords and the topic;
- responsive to selecting the first calculation calculating the degree of similarity by identifying an intersection of top-ranking URLs for the keyword of the plurality of keywords, and
- responsive to selecting the second calculation calculating the degree of similarity by identifying embeddings of text from a search engine results page (SERP) for the keyword of the plurality of keywords;
- and
- selecting keywords from the plurality of keywords having a calculated degree of similarity above a threshold degree of similarity as the associated set of keywords;
- for a topic from the topic graph, and for each keyword of the associated set of keywords:
- obtaining a set of pages ranking highly for the keyword of the associated set of keywords in the search engine;
- determining attributes of the set of pages, the determining comprising:
- generating page outlines by extracting article headings from the set of pages;
- clustering the extracted article headings based on their similarities, and
- generating a representative heading based on the clustered article headings;
- and
- based on the determined attributes, generating the content brief for the topic comprising the representative headings.
11 more elements
A non-transitory computer-readable storage medium comprising computer program instructions for generating a content brief for a topic, the computer program instructions, when executed, causing one or more processors to:
- access a topic graph, the topic graph comprising a set of topics, each topic having an associated set of keywords, the associated set of keywords for each topic in the topic graph determined by:
- selecting, based on topics in the topic graph, between a first calculation and a second calculation to calculate for calculating a degree of similarity between each of a plurality of keywords and the topic:
- responsive to selecting the first calculation calculating the degree of similarity by identifying an intersection of top-ranking URLs for the keyword of the plurality of keywords, and
- responsive to selecting the second calculation calculating the degree of similarity by identifying embeddings of text from a search engine results page (SERP) for the keyword of the plurality of keywords;
- and
- selecting keywords from the plurality of keywords having a calculated degree of similarity above a threshold degree of similarity as the associated set of keywords;
- for a topic from the topic graph, and for each keyword of the associated set of keywords:
- obtain a set of pages ranking highly for the keyword of the associated set of keywords in the search engine;
- determine attributes of the set of pages, the determining comprising:
- generating page outlines by extracting article headings from the set of pages;
- clustering the extracted article headings based on their similarities, and
- generating a representative heading based on the clustered article headings;
- and
- based on the determined attributes, generate the content brief for the topic comprising the representative headings.
11 more elements
A system comprising:
- one or more processors;
- and
- a non-transitory computer-readable storage medium comprising computer program instructions for generating a content brief for a topic, the computer program instructions, when executed, causing the one or more processors to:
- access a topic graph, the topic graph comprising a set of connected topics, each topic having an associated set of keywords, the associated set of keywords for each topic in the topic graph determined by:
- selecting, based on topics in the topic graph, between a first calculation and a second calculation to calculate a degree of similarity between each of a plurality of keywords and the topic::
- responsive to selecting the first calculation-comprises calculating the degree of similarity by identifying an intersection of top-ranking URLs for the keyword of the plurality of keywords, and
- responsive to selecting the second calculation, calculating the degree of similarity by identifying embeddings of text from a search engine results page (SERP) for the keyword of the plurality of keywords;
- and
- selecting keywords from the plurality of keywords having a calculated degree of similarity above a threshold degree of similarity as the associated set of keywords;
- for a topic from the topic graph, and for each keyword of the associated set of keywords:
- obtain a set of pages ranking highly for the keyword of the associated set of keywords in the search engine;
- determine attributes of the set of pages, the determining comprising:
- generating page outlines by extracting article headings from the set of pages;
- clustering the extracted article headings based on their similarities, and
- generating a representative heading based on the clustered article headings;
- and
- based on the determined attributes, generate the content brief for the topic comprising the representative headings.
14 more elements
Dependencies are inferred from the claim text.