ImageRepositoryShoppingProductInformationProductInformation

AI Overview😉

  • The potential purpose of this module is to analyze and understand product information within images, extracting features such as product categories, detection scores, and embeddings. This helps Google to better understand the content of images and provide more accurate search results, especially for product-related searches.
  • This module could impact search results by influencing the ranking of product-related searches. For instance, if a product image is accurately detected and categorized, it may be more likely to appear in search results for related queries. Conversely, if the detection is inaccurate or incomplete, the product may not appear in relevant search results. This module could also affect the quality of product information displayed in search results, such as product descriptions, prices, and availability.
  • To be more favorable for this function, a website could optimize its product images by ensuring they are high-quality, well-lit, and clearly display the product. Additionally, providing accurate and descriptive product information, such as categories, descriptions, and specifications, could help Google's algorithm better understand the product and improve its detection and categorization. Furthermore, using structured data and schema markup on product pages could provide Google with additional context and improve the accuracy of its product information extraction.

Interesting Module? Vote 👇

Voting helps other researchers find interesting modules.

Current Votes: 0

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

Information about a single product. For ProductNet models, each product has one label with a detection score. The label is mapped to one or multiple category ids. For PRIMI generic feature models, each product can have multiple entities, and each entity has a score. The category_id and detection_score fields are not populated for PRIMI generic feature models.

Attributes

  • categoryId (type: list(integer()), default: nil) - The possible Merlot ids for the item. There may be more than one if the product detector result corresponds to a collection of merlot ids, which can't be easily grouped up to a common ancestor, for which the detector would still make sense for all the children. E.g. a detected "chair" can be either an indoor chair or an outdoor one, however in Merlot the common ancestor of the two is furniture.
  • clusterIds (type: list(integer()), default: nil) - The k-d tree clusters for retrieval. Will be deprecated, use the token_groups instead. To add tokens/cluster_ids from new tokenization model in the future, add it to the token_groups.
  • detectionScore (type: number(), default: nil) - The localization detection score.
  • embedding (type: String.t, default: nil) - The serialized embedding values.
  • entities (type: list(GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryShoppingProductInformationEntity.t), default: nil) - The recognized entities and scores.
  • featureType (type: String.t, default: nil) - Feature type (different detectors and embedders) requested.
  • productLocation (type: GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryShoppingProductInformationBoundingBox.t, default: nil) - The bounding box.
  • tokenGroups (type: list(GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryShoppingProductInformationProductInformationTokenGroup.t), default: nil) -

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.ImageRepositoryShoppingProductInformationProductInformation{
    categoryId: [integer()] | nil,
    clusterIds: [integer()] | nil,
    detectionScore: number() | nil,
    embedding: String.t() | nil,
    entities:
      [
        GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryShoppingProductInformationEntity.t()
      ]
      | nil,
    featureType: String.t() | nil,
    productLocation:
      GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryShoppingProductInformationBoundingBox.t()
      | nil,
    tokenGroups:
      [
        GoogleApi.ContentWarehouse.V1.Model.ImageRepositoryShoppingProductInformationProductInformationTokenGroup.t()
      ]
      | nil
  }

Functions

Link to this function

decode(value, options)

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

Unwrap a decoded JSON object into its complex fields.