Chatbot Context Retrieval via Entity Relationship Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current chatbot systems lack the ability to effectively capture and utilize entities and their relationships to provide personalized and contextually relevant responses, relying on keyword matching and natural language processing without active curation or dynamic relevancy scoring.
Innovation Solution
A method and system that initializes chatbot conversations by identifying entities and relationships, determining initial relevancy scores based on domain topics, and updating these scores in real-time through user interactions to generate tailored responses and clarify missing information, using a prerequisite knowledge store expanded from structured and unstructured data sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If chatbot systems use keyword matching and basic natural language processing, then the system complexity is low, but the personalization and contextual relevance of responses are insufficient
Solution Approach 1:
The system performs preliminary action by proactively identifying entities and relationships in user input before generating responses. The chatbot extracts entities, determines their relationships, and calculates relevancy scores in advance, creating a structured knowledge representation that enhances personalization without requiring complex real-time processing during conversation
Solution Approach 2:
The patent introduces an intermediary layer between basic NLP and response generation. This intermediary component calculates relevancy scores for identified entities and relationships, acting as a mediator that transforms raw extracted information into prioritized contextual data that guides response personalization while maintaining manageable system complexity
2Measurement precision
If chatbot systems actively curate entities and relationships with dynamic relevancy scoring, then response accuracy and personalization improve, but the processing time and computational resources increase
Solution Approach 1:
The system applies parameter changes by dynamically adjusting relevancy scores based on conversation context, user preferences, and domain importance. This allows the chatbot to prioritize processing of high-relevancy entities while potentially simplifying or skipping low-relevancy ones, thereby improving response accuracy without uniformly increasing processing time for all entities
3Loss of information
If chatbot systems rely on static keyword matching, then the implementation is simple, but the ability to capture entities and relationships for context supplementation is limited
Solution Approach 1:
The patent applies segmentation by breaking down user input into discrete entities and their relationships. Instead of treating input as a whole, the system segments it into identifiable entities (people, places, things) and the relationships between them, allowing selective extraction and processing of contextually important information while managing processing complexity through structured decomposition
Data Source
AI summary
A method for supplementing context in dialog flows for chatbot systems includes responsive to receiving identification information associated with a user and a topic for a chatbot conversation, initializing a chatbot conversation between a chatbot and the user. The method identifies a set of entities and a set of one or more relationships, wherein each relationship from the set one or more relationships is between two entities from the set of entities. The method determines an initial set of relevancy scores for each entity in the set of entities and the set of one or more relationships, wherein the initial set of relevancy scores are based at least on a domain for the topic of the chatbot conversation. The method generates a first response to the user based on the initial set of relevancy scores, wherein the first response includes at least one entity and at least one relationship.