Power Dispatching QA Using Knowledge Graph Rules

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing method of power dispatching in substations relies heavily on manual checks and dispatcher experience, leading to inefficiencies and inaccuracies, with knowledge transfer between dispatchers prone to errors.

Innovation Solution

An intelligent question answering system using natural language processing and knowledge graphs to analyze power dispatching questions, determining semantic information, and applying a preset rule base to provide accurate dispatching answers, reducing the need for manual checks and experience-based decision-making.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual checking and experience-based decision-making are used for power dispatching, then dispatcher knowledge and experience can be applied, but the efficiency and accuracy of power dispatching deteriorate due to manual operations and potential knowledge transfer errors

Engineering Contradiction:
Improveaccuracy of power dispatchingVSAvoidefficiency of power dispatching
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent replaces the manual mechanical process of checking operation parameters and making dispatching decisions with an automated intelligent system. The system automatically acquires operation parameters, determines question semantic information, and generates answer information based on a preset rule base, eliminating manual operations and associated errors while improving both accuracy and efficiency.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The intelligent system performs self-service by autonomously acquiring power dispatching question information, automatically determining semantic information including target substations and parameters, and independently generating answer information using the preset rule base without requiring manual dispatcher intervention for each dispatching decision.

Inventive Principle:
Principle #25Self-service

2Loss of information

If manual power dispatching is used, then dispatcher experience can be utilized, but knowledge transfer between dispatchers deteriorates due to errors in manual transmission

Engineering Contradiction:
Improveknowledge transfer accuracyVSAvoidcomplexity of dispatching system
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent creates a digital copy of dispatcher knowledge by establishing a preset rule base that stores standardized dispatching rules and knowledge. This rule base serves as an accurate, error-free replica of expert knowledge that can be consistently applied and transferred without the degradation inherent in manual knowledge transmission between dispatchers.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system performs preliminary action by pre-establishing the rule base containing all necessary dispatching knowledge and rules before actual dispatching operations. This advance preparation ensures that knowledge is codified and stored in a structured format, eliminating the need for repeated manual knowledge transfer and reducing errors.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12475319B2Method of dispatching power, electronic device, and storage medium
Publication Date: 2025.11.18 BEIJING BAIDU NETCOM SCI & TECH CO LTD
  • US12475319B2 patent drawing
  • US12475319B2 patent drawing
  • US12475319B2 patent drawing

AI summary

A method of dispatching power, an electronic device, and a storage medium, which relate to a field of artificial intelligence technology, and in particular to technical fields such as natural language processing and knowledge graph. The method includes: acquiring a power dispatching question information; determining a question semantic information corresponding to the power dispatching question information, wherein the question semantic information includes an identification of a target substation, a question intention, and a target parameter; and determining an answer information according to the question semantic information and a preset rule base, and outputting the answer information, wherein the answer information is used for a power dispatching of the target substation.