Intelligent Knowledge Base Construction via Abstract Semantic Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional question-answer knowledge bases require manual input of numerous questions, are inefficient in storage, and often lack sufficient paired questions-answers due to storage limitations, leading to suboptimal user query responses.

Innovation Solution

The system employs an intelligent knowledge base construction method involving abstract semantic expressions and semantic similarity calculations to dynamically generate answers, using an abstract semantic recommending module to fill semantic gaps in user queries and store relevant information efficiently.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual input of numerous questions is used to improve question-answer knowledge base accuracy, then answer accuracy is improved, but time consumption and labor efficiency deteriorate

Engineering Contradiction:

Improveanswer accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables automatic question generation by allowing the knowledge base to self-populate with questions derived from semantic analysis of user queries and existing knowledge, eliminating the need for manual question input while maintaining answer accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of question input is replaced by an automated semantic processing system that uses natural language understanding and generation algorithms to automatically create and organize question-answer pairs

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If paired questions-answers are stored to improve knowledge base functionality, then knowledge coverage is improved, but storage space requirements increase

Engineering Contradiction:

Improveknowledge coverageVSAvoidstorage space

Core Design Contradiction:

Adaptability or versatilityVSVolume of stationary object

Solution Approach 1:

The knowledge base is segmented into modular knowledge points, each containing a question, answer, and associated metadata. This segmentation allows for efficient storage and retrieval while maintaining comprehensive knowledge coverage through organized, reusable units

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Each knowledge point is designed to be multi-functional, serving as both a standalone question-answer pair and as a component that can be combined with other knowledge points to address more complex queries, maximizing knowledge coverage without proportionally increasing storage requirements

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Reliability

If extensive paired questions-answers are stored to improve user query response capability, then response capability is improved, but storage limitations are exceeded

Engineering Contradiction:

Improveresponse capabilityVSAvoidstorage capacity

Core Design Contradiction:

ReliabilityVSVolume of stationary object

Solution Approach 1:

An abstract semantic representation layer is introduced as an intermediary between user queries and the knowledge base. This layer performs semantic matching and query transformation, enabling effective retrieval with a compact knowledge base that does not require exhaustive question-answer pairing

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system changes the parameter of knowledge representation from concrete question-answer text pairs to abstract semantic structures. This transformation reduces storage requirements while maintaining or improving response capability through more efficient semantic matching algorithms

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11301637B2Methods, devices, and systems for constructing intelligent knowledge base

Publication Date: 2022.04.12 SHANGHAI XIAOI ROBOT TECH CO LTD

AI summary

An abstract semantic recommending device, comprising an abstract semantic expression obtaining unit to obtain a plurality of abstract semantic expressions; a receiving unit to receive an initial request message; a word segmentation unit to perform a word segmentation process on the initial request message to obtain one or more single words; a part-of-speech tagging unit to perform a part-of-speech tagging process on at least one of the one or more single words to obtain its part-of-speech information; a wordclass determination unit to perform a wordclass determination process on at least one of the one or more single words to obtain its wordclass information; a searching unit to acquire an abstract semantic candidate set relevant to the initial request message; and a matching unit to derive one or more abstract semantic expressions by performing a matching process on the several abstract semantic expressions in the abstract semantic candidate set.