Chatbot Scenario Link Generation via Hierarchical Keyword Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In scenario-type chatbots, manually setting links between answers can be inefficient and difficult as the amount of information increases, leading to users following unnecessary links and struggling to obtain necessary information effectively.
Innovation Solution
A scenario generation apparatus and method that automatically sets links by extracting hierarchical structures from documents, selecting keywords, generating scenario candidates with and without links, calculating evaluation values based on setting rules, and adopting the most appropriate scenario candidate for generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If links are manually set in scenario-type chatbot, then the scenario can be created with proper link structure, but the work becomes difficult and time-consuming as the amount of information increases
Solution Approach 1:
The system enables automatic link setting by allowing the chatbot scenario to self-configure links between answers based on content analysis. The evaluation value calculation unit automatically determines appropriate links without human intervention, making the system self-sufficient in link configuration tasks.
Solution Approach 2:
The manual mechanical process of link setting is replaced with an automated computational system. The evaluation value calculation unit uses algorithms to compute link appropriateness, substituting the manual mechanical operation with an automated information processing system that analyzes answer content and automatically establishes links.
2Ease of manufacture
If links are not set properly in scenario-type chatbot, then the setup process is simple, but users follow unnecessary links and cannot efficiently obtain necessary information
Solution Approach 1:
The system incorporates feedback mechanisms where the evaluation value calculation unit continuously assesses link appropriateness based on user interactions and answer content. This feedback loop ensures that links are optimized for both ease of scenario creation and user information access efficiency, adjusting link configurations to prevent unnecessary link following.
Solution Approach 2:
The system changes the parameter of link configuration from manual binary decisions to automated probabilistic evaluations. By calculating evaluation values that reflect link appropriateness, the system dynamically adjusts link settings to balance scenario creation simplicity with user information access efficiency, preventing poor link configurations.
3Measurement precision
If manual link setting is used in scenario-type chatbot, then links can be set with human judgment, but it becomes difficult to set links appropriately as the amount of information increases
Solution Approach 1:
The evaluation value calculation unit serves as an intermediary between the scenario content and the link configuration. It mediates the complex relationship between increasing information volume and link setting precision by automatically analyzing answer content and determining appropriate links, bridging the gap between content complexity and link accuracy.
Solution Approach 2:
The system uses template-based link configuration that can be copied and adapted across different scenario contexts. Once link patterns are established through evaluation, they can be replicated across similar answer pairs, maintaining precision without requiring manual analysis of each individual link in complex scenarios.
Data Source
AI summary
A scenario generation apparatus includes: a keyword selection unit that extracts a hierarchical structure from documents that is a basis of a scenarios for use in chatbot and has the hierarchical structure, and selects keywords from the headings in each layer of the extracted hierarchical structure, a link candidate generation unit that generates a first scenario candidate in which a link is set between the keywords and a second scenario candidate in which a link is not set between the keywords, by using documents, an evaluation value calculation unit that calculates an evaluation value for the link for each of the generated first scenario candidate and the second scenario candidate according to a setting rule, and a scenario generation unit that adopts one of the scenario candidates based on the calculated evaluation value and generates the scenario using the adopted scenario candidate.