Keyword Annotation for Targeted Paid Search Campaigns

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current online advertising methods lack the ability to deliver highly personalized ads to individual users effectively, leading to reduced ad relevance and increased costs for advertisers.

Innovation Solution

The system generates targeted paid search campaigns by creating ad groups and ad copies based on annotated keywords, using a network of clients, web servers, ad servers, and application servers to match user search queries with relevant ad content, employing methods such as exact matching, similarity-based approaches, and classification-based approaches to annotate and group keywords for personalized ad delivery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional online advertising methods are used, then advertising coverage is broad, but ad relevance to individual users is low and advertising costs increase

Engineering Contradiction:
Improvead relevanceVSAvoidadvertising costs
Core Design Contradiction:
Measurement precisionVSLoss of energy

Solution Approach 1:

The patent segments the advertising system into multiple components: ad groups containing themed keywords, annotated keywords with metadata tags, and personalized ad copies. This segmentation allows precise matching of user search queries with relevant ad content while reducing wasted impressions on uninterested users, thereby improving ad relevance and lowering advertising costs

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-annotating keywords with metadata tags and pre-grouping them into ad groups before actual ad serving. This advance preparation enables rapid, accurate matching of user queries with relevant ads without real-time complex processing, improving both relevance and cost-efficiency

Inventive Principle:
Principle #10Preliminary action

2Productivity

If personalized advertising is implemented, then ad effectiveness increases, but system complexity increases

Engineering Contradiction:
Improvead effectivenessVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent applies parameter changes by introducing metadata tags as additional parameters for keywords. These tags capture semantic information and relationships, enabling sophisticated ad matching without requiring complex algorithms. The system transforms simple keyword matching into parameter-rich pattern matching, improving ad effectiveness while maintaining manageable system complexity

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces annotated keywords with metadata tags as an intermediary layer between raw search queries and ad copies. This intermediary structure simplifies the matching process by providing structured information that bridges the gap between user intent and relevant advertisements, reducing overall system complexity while enhancing personalization

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS8311997B1Generating targeted paid search campaigns
Publication Date: 2012.11.13 WALMART APOLLO LLC
  • US8311997B1 patent drawing
  • US8311997B1 patent drawing
  • US8311997B1 patent drawing

AI summary

In particular embodiments, annotating each keyword of a plurality of keywords with one or more labels of a plurality of labels, comprising: for each label, computing a score for the keyword document corresponding to the keyword and the label using an annotation model; and annotating the keyword with a specific label where the keyword document corresponding to the keyword and the specific label have the highest or the lowest score. Constructing a classifier based on a plurality of training keywords. For each keyword of the plurality of keywords, for each label annotating the keyword, calculating a second index-wise product between a word count vector of the keyword document corresponding to the keyword and a word count vector of the label document corresponding to the label; and predicting whether the label annotating the keyword is correct using the classifier with the second index-wise product as an input to the classifier.