KnowledgeAnswersSensitivityArgumentEvalPolicy

AI Overview😉

  • The potential purpose of this module is to control the sensitivity of argument values in search queries, particularly for complex argument value types such as HomeAutomationDevice. It aims to scrub and redact sensitive information from search queries to maintain user privacy and security.
  • This module could impact search results by removing or replacing sensitive information from search queries, which may affect the accuracy or relevance of search results. For example, if a user searches for "control my home thermostat", the module may redact the "home thermostat" part to maintain the user's privacy. This could lead to less accurate search results or a loss of context.
  • To be more favorable for this function, a website may need to:
    • Use standardized and simple argument value types to reduce the need for scrubbing and redaction.
    • Implement clear and concise intent definitions to help the Intent Scrubber accurately identify and handle sensitive information.
    • Provide customized replacement phrases for redacted information to maintain context and accuracy in search results.

Interesting Module? Vote 👇

Voting helps other researchers find interesting modules.

Current Votes: 0

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

Policy controlling argument level eval.

Attributes

  • policyName (type: String.t, default: nil) - Optional cannery policy name. If it presents then Intent Scrubber will use the corresponding Cannery rule for argument scrubbing and redaction instead. It should only be used for existing complex argment value types such as HomeAutomationDevice.
  • redactQuerySpan (type: boolean(), default: nil) - Redact corresponding span of the string query.
  • replacement (type: String.t, default: nil) - Customized replacement phrase, if missing ${ArgumentName}_REDACTED is used as default.
  • scrubArgumentValue (type: boolean(), default: nil) - Scrub argument value and signals before saving to eval storage. If not set, 1) inherit the policy from the outer argument if there is one (for nested intents); 2) finally default to type based scrubbing: see go/argument-type-scrubbing.

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.KnowledgeAnswersSensitivityArgumentEvalPolicy{
    policyName: String.t() | nil,
    redactQuerySpan: boolean() | nil,
    replacement: String.t() | nil,
    scrubArgumentValue: boolean() | nil
  }

Functions

Link to this function

decode(value, options)

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

Unwrap a decoded JSON object into its complex fields.