摘要
电力调度文本中含有大量的价值信息,针对现行调度员多依靠手工方式查阅信息导致工作量大、效率低的问题,提出一种基于自然语言理解的电力调度文本检索方法。基于正则表达式建立电力调度文本解析模型,抽取电力文本关键信息及与关键信息对应的解释内容,将电力文本解析内容以“实体-关系-实体”方式融合,建立电力调度文本知识图谱。提出电力调度文本信息相似度计算方法,通过计算待检索电力文本信息与电力调度文本知识图谱中实体间的相似距离,判定电力文本信息检索结果。通过对某地区电力调度文本的验证,得出所提基于自然语言理解的电力调度文本检索方法具有较高的检索准确率和检索效率,具有广泛的工程应用前景。
The text of power dispatching contains a lot of valuable information.Aiming at the problem that the current dispatchers rely on manual way to consult information,and it leads to heavy workload and low efficiency.A text retrieval method for power dispatching based on natural language understanding is proposed.Power dispatching text analysis model based on regular expression is established,which is used to extract key information of power text and corresponding interpretation content of key information.The power dispatching text analysis content is integrated by entity-relation-entity method,and the power dispatching text information knowledge map is established.A method to calculate the similarity of text information in power dispatching is proposed,and the result of power text information retrieval is determined by calculating the similar distance between entities in the knowledge graph of power dispatching text information and power text information to be retrieved.Through the verification of aregional power dispatch text,the text retrieval method of power dispatching based on natural language understanding has high retrieval accuracy and efficiency,and has a wide range of engineering application prospects.
作者
张小韬
季小龙
ZHANG Xiaotao;JI Xiaolong(NARI Group Corporation Co.,Ltd.(State Grid Electric Power Research Institute Co.,Ltd.),Nanjing 211106,China;Beijing Kedong Electric Power Control System Co.,Ltd.,Beijing 100192,China)
出处
《黑龙江电力》
CAS
2023年第5期466-470,共5页
Heilongjiang Electric Power
关键词
电力调度文本
自然语言理解
正则表达式
知识图谱
文本相似度
查准率
power dispatching text
natural language understanding
regular expression
knowledge graph
text similarity
precision ratio
