VideoContentSearchQnaAnchorSetFeatures

VideoLink Signal

GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchQnaAnchorSetFeatures

9
out of 10
Critical
SEO Impact
Debug info for Q&A anchors. Next ID: 15

SEO Analysis

AI Generated

Related to anchor text analysis and link signal processing. Anchor text—the clickable text in hyperlinks—has been a fundamental ranking signal since Google's inception. This model processes how link text is analyzed, stored, and weighted, affecting how Google understands what a page is about based on how other sites link to it.

Actionable Insights for SEOs

  • Monitor for changes in rankings that may correlate with updates to this system
  • Consider how your content strategy aligns with what this signal evaluates
  • Audit your backlink profile for anchor text diversity and relevance
  • Ensure internal linking uses descriptive, relevant anchor text
  • Monitor for unnatural link patterns that could trigger penalties

Attributes

10
Sort:|Filter:
backgroundEncodingPathstring
Default: nilFull type: String.t

Path to Descartes background encoding in the form of a serialized drishti.DenseFeatureData proto. This is generated by the flume_generate_background_encoding binary.

descartesModelVersionstring
Default: nilFull type: String.t

This field is used for debugging which model the decartes_model_score is generated from. You can learn more about the Descartes model at go/descartes-qa.

descartesScoreThresholdnumber(
Default: nil

Descartes score threshold for determining whether to output a QA pair as an anchor. This currently effects only the Descartes ranking score.

dolphinConfigVideoContentSearchDolphinScoringConfig →
Default: nilFull type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchDolphinScoringConfig.t

The configuration used for fetching Dolphin scores.

ensembleModelPathstring
Default: nilFull type: String.t

Path to Ranklab ensemble model used in post-trigger step.

ensembleModelScoreThresholdnumber(
Default: nil

Minimum score for video anchor to pass the post-trigger step. Calculated by training a logisitic regression model with 95% precision. Training colab can be found at go/video-qa-ensemble.

minEntityTopicalityScorenumber(
Default: nil

Threshold for determining whether to consider an entity from a CDoc for sourcing questions on that topic. Learn more about this score at: http://go/topicality-score

minQuestionDistancenumber(
Default: nil

Threshold for determining whether questions belong in the same cluster.

relatedQuestionsSstablePathstring
Default: nilFull type: String.t

Path to the Related Questions SSTable that maps entities to questions.

spanDurationSecsstring
Default: nilFull type: String.t

The duration threshold for merging captions.