Social Network Keyword Vectorization for Context-Aware Content Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing keyword matching systems in advertising and content provision struggle to understand the context and meaning of conversations in social networks due to variations in language usage over time, slang, colloquial words, and the difficulty in registering proper nouns, leading to inefficient matching and context understanding.

Innovation Solution

A method and system that translates input keywords into everyday language using a word set collected from social network content, constructing a keyword database through natural language processing to convert words into vectors and generate synonym sets, allowing for automated expansion and use in content provision.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If keyword matching is performed using a predesignated dictionary or advertising category, then the matching process is straightforward and automated, but the system fails to understand the context or meaning of conversations due to language variations, slang, and colloquial words

Engineering Contradiction:

Improveautomation of keyword matchingVSAvoidcontext understanding accuracy

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary translation system that converts colloquial expressions, slang, and proper nouns from social network content into standardized keywords from a predesignated dictionary. This intermediary layer enables automated keyword matching to work effectively by bridging the gap between informal user language and formal advertising categories, thereby maintaining both automation and context understanding accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically changes the parameter of language representation by transforming variable colloquial expressions into fixed standardized keywords. This parameter transformation allows the matching system to handle language variations, slang, and proper nouns by converting them into a consistent format that can be effectively matched against advertising categories

Inventive Principle:

Principle #35Parameter changes

2Reliability

If proper nouns from social network content are registered one by one to a dictionary, then the system can recognize specific terms, but the process is difficult and time-consuming

Engineering Contradiction:

Improverecognition accuracy of proper nounsVSAvoidtime for dictionary registration

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent implements a self-service mechanism where the translation system automatically extracts proper nouns from social network content, translates them into standardized keywords, and registers them in the dictionary without manual intervention. This self-service approach maintains high recognition accuracy for proper nouns while eliminating the time-consuming manual registration process

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary translation and registration of proper nouns from social network content into the standardized dictionary before they are needed for matching. This preliminary action ensures that proper nouns are already recognized and standardized in advance, improving recognition accuracy while avoiding time-consuming manual registration when needed

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If slang and colloquial words are used in conversations, then the language reflects actual daily usage, but keyword matching becomes difficult due to variations in meaning over time

Engineering Contradiction:

Improvelanguage usage diversityVSAvoidkeyword matching accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent implements a dynamic translation system that adapts to changing slang and colloquial expressions by continuously learning from social network content. The system dynamically updates its translation mappings to reflect current language usage trends, thereby maintaining both language usage diversity and keyword matching accuracy despite variations in meaning over time

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11734508B2Method and system for expansion to everyday language by using word vectorization technique based on social network content

Publication Date: 2023.08.22 LY CORP

AI summary

Provided is a method and system for expanding to an everyday language using a word vectorization technique based on social network content. A content providing method includes collecting social network content on the Internet; expanding corresponding content information to a word set of words included in the social network content with respect to target content that is to be serviced to a client; and providing the target content to the client with respect to user information associated with the client using the word set.