Chatbot Commercial Intent Detection and Keyword Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing interactive platforms struggle to provide personalized and relevant advertisements to users during conversations with chatbots, often resulting in generic or untargeted ads that detract from the user experience.

Innovation Solution

A chatbot system that detects commercial intent during conversations using machine learning models, extracts relevant keyword candidates, assigns scores based on relevance and commercial intent, and transmits these keywords to advertising content servers to retrieve targeted advertisements, which are then integrated into the conversation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If generic advertisements are provided to users during chatbot conversations, then the advertising system is simple to implement, but the user experience deteriorates due to lack of personalization and relevance

Engineering Contradiction:

Improveease of implementationVSAvoidpersonalization capability

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary actions by detecting commercial intent and extracting keywords from user conversations before selecting and providing advertisements. This advance processing enables personalized ad selection based on actual user needs rather than using generic advertisements, resolving the contradiction between implementation simplicity and personalization capability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the simple mechanical system of displaying generic ads with an intelligent system using machine learning models to detect commercial intent, extract keywords, and select relevant advertisements. This substitution of mechanical processes with intelligent algorithms achieves personalization while maintaining system manageability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If targeted advertisements are provided based on commercial intent detection, then user experience is improved through personalization, but device complexity increases due to multiple machine learning models and processing steps

Engineering Contradiction:

Improvepersonalization capabilityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the advertising process into distinct functional modules: commercial intent detection, keyword extraction, advertisement selection, and ad serving. Each module performs a specific function and can be independently optimized or replaced, reducing overall system complexity while maintaining personalization capability

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The machine learning models in the system serve multiple functions - detecting commercial intent, extracting relevant keywords, and ranking advertisements. This multi-functionality reduces the need for separate specialized components, thereby managing system complexity while achieving personalized advertising

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Measurement precision

If commercial intent detection and keyword extraction are implemented, then advertisement relevance is improved, but processing time increases due to multiple scoring and selection steps

Engineering Contradiction:

Improveadvertisement relevanceVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial action by focusing computational resources on the most critical processing steps - commercial intent detection and keyword extraction - while using more efficient algorithms for subsequent advertisement selection and ranking. This selective processing maintains high advertisement relevance while reducing overall processing time

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system changes parameters by adjusting the complexity and thresholds of machine learning models based on processing requirements. For example, it can modify keyword extraction sensitivity, advertisement ranking criteria, or intent detection confidence thresholds to balance processing speed with advertisement relevance, resolving the contradiction between precision and time

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250173758A1Commercial intent detection and keyword extraction

Publication Date: 2025.05.29 SNAP INC

AI summary

A chatbot system detects commercial intent during conversations with users and provides targeted advertisements. The chatbot system extracts keyword candidates from a conversation and assigns relevance scores based on the meaning of the conversation and commercial scores based on a machine learning model trained to detect commercially-related keywords. The chatbot system selects keywords based on a combination of the scores and transmits the selected keywords to advertising content servers that provide advertising content including advertisements selected using the keywords. The chatbot system displays the advertisements to the user during the conversation. The chatbot system may integrate the advertisements into the chatbot's responses, select advertisements based on a predicted click-through rate for the user, train the machine learning model using translations of labeled examples, access a long-term memory of the user's conversations and user profile data to provide context for the advertisements, and analyze messages from multiple users in group chats.