Helper Behavior Signals for Context-Aware Supplemental Content
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advertising methods rely solely on past user behavior and fail to leverage new knowledge to provide relevant and effective advertisements, as they do not consider the user's current needs or the expertise of helpers in their interactions.
Innovation Solution
A system that tracks the behavior and interactions of a helper during a conversation with a user, using natural language processing and machine learning to identify relevant products or services, and delivers supplemental content based on the helper's knowledge and insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If search engine recommendation approaches are used to select ads based on user's past browsing history, then ads can be selected automatically without user intervention, but the ads are not specifically based on the user's current needs and do not leverage new knowledge
Solution Approach 1:
The system performs preliminary actions by having the helper browse and interact with content before the ad selection process. The helper's pre-browsing behavior captures current interests and needs, which are then used to inform ad selection, moving beyond just past user history to include fresh, relevant information gathered through the helper's actions.
Solution Approach 2:
The helper acts as an intermediary between the user and the ad selection system. The helper browses content and generates interactions that capture current user needs and interests, translating these into signals that the system uses to select relevant ads. This intermediary role bridges the gap between automated selection and current user context.
2Loss of information
If the system asks the user what product is best for them to determine relevant ads, then the ads can be tailored to user needs, but it interferes with the user experience and users may not know what is available in the marketplace
Solution Approach 1:
The helper performs the information-gathering function on behalf of the user without requiring direct user input. The helper browses content, interacts with products, and captures relevant information about current needs and interests. This self-service approach by the helper eliminates the need to interrupt the user with questions while still gathering necessary information for personalized ad selection.
Solution Approach 2:
The system performs preliminary information gathering through the helper's browsing and interactions before ad selection is needed. This advance capture of user needs and interests through the helper's actions provides the system with current, relevant information without requiring real-time user input or disrupting the user experience.
3Productivity
If ads are selected based on competitor product keywords, then ads can be displayed for matching products, but the ads are not specifically based on the user's current needs
Solution Approach 1:
The system changes the parameters used for ad selection from static keyword matching to dynamic behavior-based signals. Instead of relying solely on competitor product keywords and past browsing history, the system incorporates real-time parameters such as the helper's current browsing behavior, interactions, and captured interests, which reflect the user's current needs and context.
Solution Approach 2:
The system performs preliminary browsing and interaction capture through the helper before ad selection occurs. This advance gathering of current user context and interests provides up-to-date information that complements keyword-based approaches, ensuring ads are based on both efficiency signals and current user needs.
Data Source
AI summary
Systems and methods for selecting supplemental content based on a conversation between a user and a helper are disclosed. The methods analyze a conversation, or other interactions, to identify one or more words or phrases associated with the conversation. The methods further evaluates a degree of emotion associated with the identified one or more words or phrases to determine a level of interest of the first user in a subject matter. Based on the determined a level of interest, the methods trigger a subsequent action.