Chatbot Personalization via Real-Time Context Integration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing natural language chatbots, such as ChatGPT, fail to provide responses adapted to a user's real-time status, relying on standard answers generated through training data without consideration for the user's current circumstances.

Innovation Solution

A method and system that processes natural language messages by integrating user preferences and real-time environmental information, using natural language processing and generative AI technologies to generate dialogue contents consistent with the user's personal requirements and current situation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If standard answers are generated through training data, then the chatbot can provide consistent responses, but the responses are not adapted to the user's real-time status

Engineering Contradiction:
Improveadaptability to user real-time statusVSAvoidloss of real-time environmental information
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system pre-trains the language model with extensive dialogue data to establish baseline conversational capabilities, then subsequently integrates real-time environmental information and user data to adapt responses to current user status, allowing the chatbot to leverage both pre-learned knowledge and real-time context

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system incorporates user data including historical dialogue records, user preferences, and real-time environmental information to continuously refine and adapt the chatbot's responses, creating a feedback loop where user interactions and environmental context inform future responses

Inventive Principle:
Principle #23Feedback

2Adaptability or versatility

If real-time environmental information and user data are integrated, then the dialogue contents become personalized, but the processing complexity increases

Engineering Contradiction:
Improvepersonalization of dialogue contentsVSAvoidprocessing system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system divides the complex processing task into distinct modules: an environmental information acquisition module that collects real-time data, a user data management module that stores and retrieves user preferences and historical data, and a natural language generation module that synthesizes personalized responses, allowing each component to be optimized independently

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces a natural language model as an intermediary that processes and integrates multiple data sources including environmental information, user preferences, and historical dialogue records, transforming these diverse inputs into coherent personalized responses without requiring direct complex interactions between all data elements

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4557157A1Method for processing natural language messages and natural-language-message processing system
Publication Date: 2025.05.21 PLAYSEE INC
  • EP4557157A1 patent drawingFigure 1
  • EP4557157A1 patent drawingFigure 2
  • EP4557157A1 patent drawingFigure 3

AI summary

A method for processing natural language messages and a natural-language-message processing system are provided. The system includes a cloud server (100). In the method, an online dialogue procedure is initiated for receiving user-input contents via a dialogue interface (115). An intelligent method is used to extract semantic features of the user-input content. A user preference and real-time environmental information can also be obtained. Then, contents that match the semantic features, the user preference, and the real-time environmental information can be determined. Dialogue contents can be generated by processing the contents with a natural language model. The dialogue content that matches the semantic features, the user preference, and the real-time environmental information is imported to the online dialogue procedure, and is outputted via the dialogue interface (115).