Account-Attribute Search Ranking for Cold-Start Query Relevance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle with determining relevant resources for user queries when historical data is scarce or unbalanced, leading to inaccurate responses due to the 'cold-start' situation, where systems lack sufficient context about the user.

Innovation Solution

The system utilizes user account attributes such as location, job title, and department to determine resource relevance by comparing user attributes with resource attributes, even in the absence of sufficient historical data, using modules like language, knowledge, and attribute modules to personalize responses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the system relies on historical data to determine resource relevance, then response accuracy improves with sufficient data, but performance deteriorates in cold-start situations with scarce or unbalanced historical data

Engineering Contradiction:

Improveresponse accuracyVSAvoidcontext information about user

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The system performs preliminary actions by collecting and storing user account attributes (location, job title, department) in advance. When a query is received, these pre-collected attributes are immediately used to determine resource relevance without waiting for historical interaction data, thus resolving the cold-start problem

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces user account attributes as an intermediary between the query and historical data. These attributes serve as a mediator that provides contextual information about the user when historical data is unavailable or unbalanced, enabling the system to make informed decisions without relying solely on historical interactions

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If the system uses unbalanced historical data for resource selection, then processing speed improves, but response relevance deteriorates due to inaccurate representations of user needs

Engineering Contradiction:

Improveprocessing speedVSAvoidresource relevance determination

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system applies local quality by using different data sources for different aspects of resource selection. User account attributes provide localized, user-specific contextual information that complements or corrects the broader but potentially unbalanced historical data, ensuring both speed and precision in resource relevance determination

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12561376B2Personalized search based on account attributes

Publication Date: 2026.02.24 OKTA INC

AI summary

A system stores resources such as text articles, videos, and so forth for an organization. During operation, the system receives a query and provides a response. During initial use of the system, there is little or no historical data available to help determine which resource is most relevant to a particular query. In this “cold-start” situation, the system determines attributes associated with a user account of the user making the query. The query is used to search a data store and retrieve a set of resources based on a term match with the query and to find the resources which correspond to the attributes of the user account. This allows the system to provide simplified output that is more likely to be relevant to that particular user in the “cold-start” situation.