Graph Database Chat Bot Query Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current chat bots face issues with providing relevant and timely responses due to inefficient keyword matching and lack of contextual understanding, leading to user frustration and slow processing times.
Innovation Solution
Implementing a graph database model that uses natural language processing to parse inputs, assign part-of-speech tags, and dynamically build relationships between nodes, allowing for efficient traversal to a root node that provides accurate and contextually relevant solutions, while continuously learning from user feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If keyword matching is used to resolve client queries, then the chat bot can provide responses, but the accuracy and relevance of the information returned deteriorates
Solution Approach 1:
A graph database model is introduced as an intermediary between the chat bot and the query database. The graph database stores structured relationships between queries, keywords, and solutions, enabling the system to traverse contextual paths rather than relying on simple keyword matching. This intermediary structure improves both accuracy and efficiency by leveraging pre-computed relationships.
Solution Approach 2:
The system transforms the query resolution approach from flat keyword matching to hierarchical graph traversal. By changing the data structure parameter from traditional databases to graph databases, the system can evaluate multiple contextual paths simultaneously, improving both the precision of query resolution and the speed of response generation.
2Reliability
If traditional database processing is used, then the chat bot can operate, but the processing and communication bandwidth requirements increase, causing slower response times
Solution Approach 1:
The graph database is pre-populated with structured relationships between queries, keywords, and solutions before runtime. During query processing, the system traverses pre-established paths in the graph rather than performing exhaustive database searches, significantly reducing response time while maintaining high information relevance.
Solution Approach 2:
The query processing is segmented into distinct phases: parsing input text, extracting keywords, traversing the graph database along relevant paths, and returning results. This segmentation allows the system to efficiently process queries by following predetermined graph paths rather than scanning entire databases.
Data Source
AI summary
A computer-implemented method of improving a speed and an accuracy of a server computer executing a chat bot using a processor. An input is received at the chat bot at the server computer from a client computer over a network. The input is parsed using a natural language engine into one or more keywords. The one or more keywords are assigned to one or more part of speech tags. All of the input is stored as a profile into a non-transitory computer recordable storage medium. The graph database model is traversed, with traversing including comparing the profile to nodes in the graph database model and using relationships among the nodes as part of the comparing, and wherein traversing ends at a root node in the graph database model. A solution stored in the root node is returned to the client computer, by the processor and over the network.