Chatbot Intent Eligibility Filtering for User-Specific Access

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current chatbots lack the ability to autonomously filter user intents based on user-specific characteristics during a session, leading to inefficiencies and increased complexity in managing dialog paths.

Innovation Solution

Implement a natural language understanding model with user intent eligibility filters that analyze session data to restrict or allow user intents based on user location, job role, and other parameters, creating a filtered user intent mapping table to provide customized intent filtering.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If chatbot uses natural language understanding to analyze user requests, then the chatbot can respond appropriately to user intents, but the chatbot cannot filter user intents based on user-specific characteristics

Engineering Contradiction:
Improveability to filter user intents based on user characteristicsVSAvoidcomplexity of managing dialog paths
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the intent recognition process by introducing a separate filtering component that operates independently from the main NLU pipeline. User intents are first generated by the NLU model, then filtered through a eligibility filter that checks user characteristics. This segmentation allows the system to gain adaptability without proportionally increasing overall complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary filtering layer between the NLU model and the response generation system. This intermediary component (eligibility filter) acts as a mediator that uses user characteristics from session data to determine which intents should be processed further. This intermediary approach enables customized filtering while maintaining a clean separation of concerns.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If chatbot processes all user intents without filtering, then all user requests can be handled, but unauthorized access to sensitive information may occur

Engineering Contradiction:
Improvesecurity of information accessVSAvoidefficiency of intent processing
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent applies preliminary action by filtering user intents before they are processed for response generation. The eligibility filter checks user characteristics and intent eligibility in advance, blocking unauthorized intents before they reach the response system. This preliminary filtering ensures security while improving efficiency by avoiding unnecessary processing of blocked intents.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If chatbot implements customized intent filtering based on user characteristics, then unauthorized access is prevented, but the system complexity increases

Engineering Contradiction:
Improvecontrol over user accessVSAvoidcomplexity of filtering mechanism
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies local quality by making the filtering behavior specific to each user and intent combination. Rather than a global filter, the system evaluates user characteristics and intent eligibility locally for each user intent pair. This allows customized filtering control while keeping the underlying mechanism relatively simple and modular.

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS20250252260A1Filtering user intent eligibility
Publication Date: 2025.08.07 ADP INC
  • US20250252260A1 patent drawing
  • US20250252260A1 patent drawing
  • US20250252260A1 patent drawing

AI summary

A system can include one or more processors, coupled with memory, to determine one or more characteristics corresponding to a session between a client device and a chatbot and generate a first mapping table including a plurality of intents configured for the session, the first mapping table configured by selecting and applying a filter based on the one or more characteristics. The one or more processors can receive an input via the chatbot during the session and, responsive at least in part to receiving the input, generate a second mapping table by using a natural language model, the second mapping table including a set of allowed intents of the plurality of intents that correspond with the input. The one or more processors can provide content corresponding with at least one intent of the set of allowed intents to the client device as a response to the input during the session.