VideoContentSearchVideoAnchorScoreInfo

AI Overview😉

The potential purpose of this module is to analyze and score video content anchors, which are specific points in a video that are relevant to a search query. The module appears to be collecting various features and metadata about these anchors, such as their captions, descriptions, and labels, as well as features related to their multimodal topics, opinions, and ratings.
This module could impact search results by influencing the ranking of video content based on the relevance and quality of their anchors. For example, videos with anchors that are more accurately labeled or have higher rating scores may be ranked higher in search results. The module may also help to filter out low-quality or irrelevant anchors, which could improve the overall user experience.
To be more favorable for this function, a website could focus on creating high-quality, accurately labeled anchors for their video content. This could include using clear and concise captions, descriptions, and labels, as well as incorporating multimodal features such as images, audio, and text. Additionally, websites could consider implementing rating systems or other forms of user feedback to help improve the quality and relevance of their anchors.

Interesting Module? Vote 👇

Voting helps other researchers find interesting modules.

Current Votes: 0

GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchVideoAnchorScoreInfo (google_api_content_warehouse v0.4.0)

Message to contain scoring / debugging information. If you want to add information which is not directly used in the final VideoAnchor data, it should be put here. Next ID: 27

Attributes

anchorCommonFeatureSet (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchAnchorCommonFeatureSet.t, default: nil) - Common features for any anchor types.
attachments (type: GoogleApi.ContentWarehouse.V1.Model.Proto2BridgeMessageSet.t, default: nil) - Additional attachments which extend MessageSet.
babelCheckpointPath (type: String.t, default: nil) - The path to the particular babel checkpoint
captionEntityAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchCaptionEntityAnchorFeatures.t, default: nil) - Training features and debug info for caption entity anchors.
captionSpanAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchCaptionSpanAnchorFeatures.t, default: nil) - Features for caption span anchors for use in training.
descriptionAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchDescriptionAnchorFeatures.t, default: nil) - Description anchor features for use in training.
filterReason (type: list(String.t), default: nil) - A description of why the anchor was removed. This is intended for debugging anchor sets which use multiple heuristics to filter anchors.
filtered (type: boolean(), default: nil) - Whether or not the anchor will be removed in the final proto.
generativeFeatures (type: list(GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchGenerativePredictionFeatures.t), default: nil) - Generated predictions from generative models
instructionAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchInstructionAnchorFeatures.t, default: nil) - Anchor level features for Instruction anchors.
instructionTrainingDataAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchInstructionTrainingDataAnchorFeatures.t, default: nil) - Training data features for Instruction anchors.
labelLanguage (type: String.t, default: nil) - Detected language of label
labelTransformation (type: list(GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchVideoAnchorScoreInfoLabelTransformation.t), default: nil) -
listAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchListAnchorFeatures.t, default: nil) - List anchor features.
listTrainingDataAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchListTrainingDataAnchorFeatures.t, default: nil) - Anchor level metadata about the description anchors used to build training data for list anchors.
multimodalTopicFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchMultimodalTopicFeatures.t, default: nil) - Multimodal features for a generated topic.
multimodalTopicTrainingFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchMultimodalTopicTrainingFeatures.t, default: nil) - Features for a generated topic used to build training data for multimodal topics.
normalizedBabelEmbedding (type: list(number()), default: nil) - Normalized babel embedding of anchor.label(). If the label has more than one sentences, the embedding will be the averaged normalized embedding of each sentence.
ocrAnchorFeature (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchOnScreenTextFeature.t, default: nil) - OCR anchor features.
ocrDescriptionTrainingDataAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchOcrDescriptionTrainingDataAnchorFeatures.t, default: nil) - Anchor level metadata about the join of description anchors and OCR data which is used to build training data.
opinionsAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchShoppingOpinionsAnchorFeatures.t, default: nil) - Shopping Opinions anchor features.
qnaAnchorFeatures (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchQnaAnchorFeatures.t, default: nil) - Q&A anchor features for use in training.
ratingScore (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchVideoAnchorRatingScore.t, default: nil) - Human rating score, used for training.
safeSearchClassifierOutput (type: GoogleApi.ContentWarehouse.V1.Model.ClassifierPornQueryMultiLabelClassifierOutput.t, default: nil) - The output of Safe Search's MultiLabelClassifier.
textSimilarityFeatures (type: list(GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchTextSimilarityFeatures.t), default: nil) - ASR matching feature for any anchor types.
thumbnailInfo (type: GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchAnchorThumbnailInfo.t, default: nil) - Information about the thumbnail anchor.

Summary

Types

t()

Functions

decode(value, options)

Unwrap a decoded JSON object into its complex fields.

Types

Link to this type

t()

@type t() ::
  %GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchVideoAnchorScoreInfo{
    anchorCommonFeatureSet:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchAnchorCommonFeatureSet.t()
      | nil,
    attachments:
      GoogleApi.ContentWarehouse.V1.Model.Proto2BridgeMessageSet.t() | nil,
    babelCheckpointPath: String.t() | nil,
    captionEntityAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchCaptionEntityAnchorFeatures.t()
      | nil,
    captionSpanAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchCaptionSpanAnchorFeatures.t()
      | nil,
    descriptionAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchDescriptionAnchorFeatures.t()
      | nil,
    filterReason: [String.t()] | nil,
    filtered: boolean() | nil,
    generativeFeatures:
      [
        GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchGenerativePredictionFeatures.t()
      ]
      | nil,
    instructionAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchInstructionAnchorFeatures.t()
      | nil,
    instructionTrainingDataAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchInstructionTrainingDataAnchorFeatures.t()
      | nil,
    labelLanguage: String.t() | nil,
    labelTransformation:
      [
        GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchVideoAnchorScoreInfoLabelTransformation.t()
      ]
      | nil,
    listAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchListAnchorFeatures.t()
      | nil,
    listTrainingDataAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchListTrainingDataAnchorFeatures.t()
      | nil,
    multimodalTopicFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchMultimodalTopicFeatures.t()
      | nil,
    multimodalTopicTrainingFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchMultimodalTopicTrainingFeatures.t()
      | nil,
    normalizedBabelEmbedding: [number()] | nil,
    ocrAnchorFeature:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchOnScreenTextFeature.t()
      | nil,
    ocrDescriptionTrainingDataAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchOcrDescriptionTrainingDataAnchorFeatures.t()
      | nil,
    opinionsAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchShoppingOpinionsAnchorFeatures.t()
      | nil,
    qnaAnchorFeatures:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchQnaAnchorFeatures.t()
      | nil,
    ratingScore:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchVideoAnchorRatingScore.t()
      | nil,
    safeSearchClassifierOutput:
      GoogleApi.ContentWarehouse.V1.Model.ClassifierPornQueryMultiLabelClassifierOutput.t()
      | nil,
    textSimilarityFeatures:
      [
        GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchTextSimilarityFeatures.t()
      ]
      | nil,
    thumbnailInfo:
      GoogleApi.ContentWarehouse.V1.Model.VideoContentSearchAnchorThumbnailInfo.t()
      | nil
  }

Functions

Link to this function

decode(value, options)

@spec decode(struct(), keyword()) :: struct()

Unwrap a decoded JSON object into its complex fields.