Automated Keyword Assignment for Retail Search Databases

Solution Overview

Problem

Existing methods for generating keywords for online retail databases rely on human intervention, which is inefficient and costly, especially when dealing with large datasets, and fail to ensure accurate and relevant keyword generation for new products.

Innovation Solution

A computerized system that retrieves search metric data and interaction data to generate ranked lists of search strings, assigning keywords to product identifiers based on interaction frequency and predetermined rules, allowing for automated and efficient keyword assignment without human intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If human individuals manually provide keywords for database entries, then keyword accuracy and relevancy can be maintained, but the process becomes inefficient and costly when dealing with large numbers of database entries

Engineering Contradiction:

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system enables automatic keyword generation by having the database system itself perform the keyword assignment task. The server system automatically retrieves product data, generates candidate keywords, ranks them, and assigns top keywords to database entries without requiring human intervention, thus achieving both efficiency and maintained accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of human keyword assignment with an automated computational system. The server system uses algorithms to retrieve product data, generate candidate keywords from various product attributes, rank these keywords based on predetermined criteria, and automatically assign the top-ranked keywords to database entries

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If human intervention is used to update keywords for each entry, then keyword relevancy can be maintained, but the cost and time required become prohibitively high

Engineering Contradiction:

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables continuous automatic keyword generation and updating for database entries. As new products are added to the database, the server system continuously retrieves their data, generates candidate keywords, and assigns appropriate keywords automatically, ensuring keyword relevancy is maintained without interruption or manual intervention

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system performs preliminary keyword generation and ranking actions automatically when products are added to the database. By pre-generating and pre-ranking candidate keywords based on product attributes before they are needed for search, the system ensures keywords are ready immediately, eliminating delays associated with manual keyword assignment

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11475015B2Systems and method for generating search terms

Publication Date: 2022.10.18

AI summary

A method for generating keywords for searches, comprising the steps of retrieving search metric data comprising a plurality of search strings and interaction data; retrieving a plurality of first product identifiers each having one or more first attributes; generating, a table comprising the plurality of search strings ranked by interaction data; generating relevant lists comprising the plurality of search strings having interaction data above threshold values; retrieving data relating to a second product identifier; extracting one or more second attributes of the second product identifier; performing searches in the relevant lists using the second attribute data; assigning keywords to the data relating to the second identifier.