Satisfaction-Guided Knowledge Base Compression for Memory-Constrained Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large knowledge bases consume significant memory resources, leading to ineffective feedback message determination due to insufficient memory in electronic devices using task processing models.
Innovation Solution
A knowledge base updating method that determines target documents in the knowledge base based on user satisfaction with feedback messages, compressing documents with high comprehensive satisfaction degrees to reduce memory consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the knowledge base is expanded to include more knowledge information, then the accuracy of feedback message determination is improved, but the memory resource consumption increases
Solution Approach 1:
The knowledge base is segmented into multiple documents, and each document is independently evaluated for compression based on its contribution to task processing accuracy. This allows selective retention of important knowledge while removing redundant information, thereby reducing memory consumption while maintaining accuracy.
Solution Approach 2:
The patent changes the state of knowledge documents from uncompressed to compressed format based on their importance. By adjusting the compression parameter (compressed vs. uncompressed), the system optimizes the balance between memory resource consumption and feedback message determination accuracy.
2Reliability
If the knowledge base size is increased to improve task processing accuracy, then the feedback message determination becomes more accurate, but the electronic device may become unable to effectively determine feedback messages due to insufficient memory resources
Solution Approach 1:
The system dynamically adjusts the compression state of knowledge documents based on their importance scores. High-importance documents are kept uncompressed to ensure reliability, while low-importance documents are compressed to free up memory resources, preventing memory exhaustion while maintaining determination effectiveness.
Solution Approach 2:
The patent employs a feedback mechanism where the task processing model evaluates the impact of each knowledge document on task processing accuracy. Based on this feedback, the system determines which documents to compress and which to retain, ensuring that reliability is maintained while optimizing memory resource availability.
3Loss of information
If all knowledge documents are retained in uncompressed format, then complete knowledge information is available for processing, but memory resources are excessively consumed
Solution Approach 1:
The knowledge base is divided into individual documents that can be independently compressed or retained. This segmentation allows the system to selectively compress documents based on their importance, ensuring that critical knowledge information is preserved while reducing overall memory consumption.
Solution Approach 2:
The system changes the compression parameter of individual knowledge documents based on their importance to task processing. By adjusting this parameter dynamically, the system maintains knowledge information completeness for important documents while compressing less critical ones to reduce memory consumption.
Data Source
AI summary
A knowledge base updating method includes: obtaining a plurality of question messages processed by a task processing model without relying on a knowledge base and a plurality of satisfaction results corresponding to the plurality of question messages; determining at least one target document in the knowledge base matching a question message of the plurality of question messages; based on a satisfaction result of the plurality of satisfaction results corresponding to each question message of at least one question message of the plurality of question messages associated with a target document of the at least one target document, determining a comprehensive satisfaction degree of the user with at least one feedback message corresponding to the at least one question message associated with the target document; and when the comprehensive satisfaction degree corresponding to the target document exceeds a set threshold, compressing the target document.