Information Processing System for Explaining Recommendation Credibility
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional recommendation systems fail to enhance user trust in recommended results by not providing explanations for the recommended objects, leading to decreased user experience and efficiency, especially in technical support scenarios where the credibility of suggested knowledge bases is questioned.
Innovation Solution
A method that determines a target object associated with input text by assigning weights to words, identifying key words, and determining target words related to the text topic, which are then output to explain the relevance of the target object, thereby improving user trust and credibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional recommendation systems only output target objects without explanations, then the system complexity is low, but user trust and credibility in the recommended results decrease
Solution Approach 1:
The recommendation system is segmented into multiple functional modules: a target object determination module that identifies the recommended object, a keyword extraction module that identifies important words, a target word determination module that selects words related to the text topic, and an output module that presents both the target object and its explanation. This segmentation allows the system to add explanation functionality while maintaining clear modular architecture.
Solution Approach 2:
Target words serve as an intermediary element that bridges the gap between the target object and the user's understanding. The target words extract key concepts from the input text that are relevant to the recommended object, providing a natural language explanation that enhances user trust without requiring the system to directly justify its recommendation algorithm.
2Reliability
If the system provides detailed explanations with target words, then user trust increases, but the information processing time and computational resources increase
Solution Approach 1:
The system applies local quality by focusing computational resources only on specific words in the input text that are most relevant to the target object. Rather than analyzing the entire text equally, the system identifies and processes only the target words that contribute to explaining the recommendation, reducing overall processing time while maintaining explanation quality.
Solution Approach 2:
The system performs partial action by extracting only the necessary target words needed to explain the recommendation, rather than providing a comprehensive analysis of all text elements. This selective approach provides sufficient explanation to build user trust without the computational overhead of complete text analysis.
3Ease of operation
If the system extracts and outputs target words to explain recommendations, then user experience improves, but the device complexity and processing steps increase
Solution Approach 1:
The system merges the explanation generation process with the target object determination process. The keyword extraction, target word determination, and target object identification are integrated into a unified workflow where results from each step feed into the next, reducing the need for separate independent processing stages and simplifying the overall system architecture.
Solution Approach 2:
The target word determination module serves multiple functions: it identifies key concepts in the text, provides explanation for the recommended object, and can potentially be used for other text analysis tasks. This multi-functionality reduces the need for separate dedicated components for each function, thereby reducing overall system complexity.
Data Source
AI summary
Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for information processing. In an information processing method, based on multiple weights corresponding to multiple words in text, a computing device determines a target object associated with the text among predetermined multiple objects, and also determines, among the multiple words, a set of key words with respect to the determination of the target object. Next, the computing device determines, among the set of key words, a set of target words related to a text topic of the text. Then, the computing device outputs the set of target words and an identifier of the target object in an associated manner. In this way, the credibility of the target object associated with the text that is determined by the information processing method is improved, thereby improving the user experience of the information processing method.