CN111046189A - Modeling method of power distribution network knowledge graph model - Google Patents
Modeling method of power distribution network knowledge graph model Download PDFInfo
- Publication number
- CN111046189A CN111046189A CN201911184390.1A CN201911184390A CN111046189A CN 111046189 A CN111046189 A CN 111046189A CN 201911184390 A CN201911184390 A CN 201911184390A CN 111046189 A CN111046189 A CN 111046189A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- knowledge graph
- model
- entity
- power distribution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The embodiment of the invention discloses a modeling method of a knowledge graph model of a power distribution network, which comprises the following steps: step 100, converting a data body of a distribution network model of a research area into an inputtable format; step 200, carrying out natural language analysis on the data body capable of inputting formats, and extracting entity elements in the power distribution network equipment or the line knowledge graph; step 300, building a distribution network knowledge graph model according to entity elements extracted from distribution network equipment or lines; the invention converts the distribution network files in the distribution network CIM/XML format into the knowledge map files expressed by vectors, the knowledge map files are expressed by a ternary relationship group, and the high-level characteristics are extracted based on the deep neural network RNN model to express the relationship between the head entity and the tail entity, thereby unifying various different data bodies, simplifying the complex relationship between different data bodies, and directly and quickly establishing the distribution network model by taking the characteristic values as the basis.
Description
Technical Field
The embodiment of the invention relates to the technical field of power grid dispatching management, in particular to a modeling method of a knowledge graph model of a power distribution network.
Background
The integration and coordination management of the main network and the distribution network information are the core of a main network and distribution network integrated management model, and the key is that the main network model and the distribution network model need to have uniform equipment information and entity relationship. In the process of splicing the main network model and the distribution network model, because the distribution network model has numerous devices, complex structure and low automation level, the distribution network model is mostly described in a CIM/XML format at present, and the modeling work is greatly challenged by various structural type data and complex relations of CIM/XML files, and the knowledge and experience of a plurality of working personnel are involved.
Disclosure of Invention
Therefore, the embodiment of the invention provides a modeling method of a knowledge graph model of a power distribution network, which aims to solve the problems that in the prior art, the data types are multiple, the relations are complex, and rapid modeling cannot be realized.
In order to achieve the above object, an embodiment of the present invention provides the following:
a modeling method of a power distribution network knowledge graph model comprises the following steps:
step 100, converting a data body of a distribution network model of a research area into an inputtable format;
step 200, carrying out natural language analysis on the data body capable of inputting formats, and extracting entity elements in the power distribution network equipment or the line knowledge graph;
and 300, building a distribution network knowledge graph model according to the entity elements extracted from the distribution network equipment or lines.
As a preferred scheme of the invention, the data volume conversion format of the distribution network model is CIM/XML.
As a preferred scheme of the invention, the data volume of the distribution network model is converted into a knowledge graph element represented by a vector after being converted into a CIM/XML format.
As a preferred scheme of the present invention, the knowledge graph elements are represented by a ternary relationship group < h, r, t >, where h represents a head entity, t represents a tail entity, and r represents a relationship between power supply.
As a preferred scheme of the present invention, in step 200, when performing natural language analysis on the CIM/XML file of the network configuration model data, a bidirectional LSTM model is used to extract keywords from the CIM/XML file, so as to obtain entity elements in the knowledge graph.
As a preferred embodiment of the present invention, the specific steps of obtaining the entity elements in step 200 are:
step 201, selecting CIM/XML sentences in corresponding word segments;
step 202, carrying out word segmentation on the sentences in the CIM/XML by adopting the ending word segmentation to obtain a plurality of word segmentation sentences;
step 203, taking the participle sentences as the input of the bidirectional LSTM model, extracting key words in a plurality of the participle sentences, and combining the extracted key words into associated words;
and 204, obtaining entity elements of the triples in the knowledge graph according to the combined associated words.
As a preferred scheme of the present invention, in step 300, the specific steps of building a distribution network knowledge graph model are as follows:
step 301, extracting high-level characteristics by adopting a deep neural network (RNN) model to acquire entity relationships;
step 302, connecting a head entity h and a tail entity t by using an entity relationship to form a triple of a knowledge graph;
and step 303, combining all the triples into a distribution network knowledge topology model.
As a preferred scheme of the present invention, in step 301, a deep neural network RNN is used to extract high-level features for prediction, so as to obtain a relationship between a head entity h and a tail entity t.
The embodiment of the invention has the following advantages:
the invention converts the distribution network files in the distribution network CIM/XML format into the knowledge map files expressed by vectors, the knowledge map files are expressed by a ternary relationship group, and the high-level characteristics are extracted based on the deep neural network RNN model to express the relationship between the head entity and the tail entity, thereby unifying various different data bodies, simplifying the complex relationship between different data bodies, and directly and quickly establishing the distribution network model by taking the characteristic values as the basis.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
FIG. 1 is a flow diagram of a construction of a knowledge graph model of a power distribution network;
fig. 2 is a diagram of an embodiment of a knowledge graph representation of a power distribution network.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the invention provides a modeling method of a knowledge graph model of a power distribution network, which comprises the following steps:
and step 100, converting the data body of the distribution network model of the research area into an input CIM/XML format.
And converting the data body of the distribution network model into a knowledge graph element represented by a vector after converting the data body into a CIM/XML format. The knowledge graph elements are represented by a ternary relationship group < h, r, t >, wherein h represents a head entity, t represents a tail entity, and r represents the relationship between power supply and the head entity.
And 200, carrying out natural language analysis on the data body with the input format, and extracting entity elements in the power distribution network equipment or the line knowledge graph.
When the natural language analysis is carried out on the CIM/XML file of the distribution network model data, a bidirectional LSTM model is adopted to extract key words from the CIM/XML file, so that entity elements in the knowledge graph are obtained. The method comprises the following specific steps:
step 201, selecting CIM/XML sentences in corresponding word segments;
step 202, carrying out word segmentation on the sentences in the CIM/XML by adopting the ending word segmentation to obtain a plurality of word segmentation sentences;
step 203, taking the participle sentences as the input of the bidirectional LSTM model, extracting key words in a plurality of the participle sentences, and combining the extracted key words into associated words;
and 204, obtaining entity elements of the triples in the knowledge graph according to the combined associated words.
For example: take the following statements of an XML file as an example:
name of XX mansion #1 ring main unit (three remote) XX I loop 901 switch! -switch name >
The method comprises the following implementation steps:
A. firstly, carrying out word segmentation on XML sentences by adopting crust segmentation, wherein the word segmentation results are 'XX', 'mansion', '# 1 looped network cabinet', 'three remote', 'star I loop' and '901 switch';
B. then, the word segmentation result is used as the input of a bidirectional LSTM model, and keywords 'XX mansion', '# 1 ring main unit', 'x I loop' and '901 switch' are extracted;
C. obtaining an entity of the knowledge graph triple according to the keywords, wherein the entity obtained through the keywords is as follows: "XX mansion", "# 1 ring main unit", ". aster I loop", "901 switch".
And 300, building a distribution network knowledge graph model according to the entity elements extracted from the distribution network equipment or lines.
The specific steps of building a distribution network knowledge map model are as follows:
301, extracting high-level features by adopting a deep neural network RNN model to obtain an entity relationship, wherein the high-level features are extracted by adopting the deep neural network RNN to predict, and further the relationship between a head entity h and a tail entity t is obtained;
step 302, connecting a head entity h and a tail entity t by using an entity relationship to form a triple of a knowledge graph;
and step 303, combining all the triples into a distribution network knowledge topology model.
Further referring to the above embodiment, in step 302, the triplets of the knowledge graph are formed, for example, on (901 switch, # I loop), installed on (# I loop, #1 ring main unit), and powered (#1 ring main unit, XX building). Then, a knowledge graph consisting of 901 switches, loop I, loop 1 and building XX can be obtained according to the three triplets, as shown in fig. 2.
Based on the above, the present invention is characterized by the following four aspects:
1. the modeling method of the power distribution network knowledge graph model is provided for the first time, and the method is also suitable for building the power transmission network knowledge graph model;
2. performing word segmentation processing on the CIM/XML file by using a crust word segmentation method;
3. extracting keywords of the XML file by using a bidirectional LSTM model;
4. and extracting high-level features by using a deep neural network RNN model to obtain the entity relationship.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (8)
1. A modeling method of a power distribution network knowledge graph model is characterized by comprising the following steps:
step 100, converting a data body of a distribution network model of a research area into an inputtable format;
step 200, carrying out natural language analysis on the data body capable of inputting formats, and extracting entity elements in the power distribution network equipment or the line knowledge graph;
and 300, building a distribution network knowledge graph model according to the entity elements extracted from the distribution network equipment or lines.
2. The modeling method of the power distribution network knowledge graph model according to claim 1, wherein a data volume conversion format of the distribution network model is CIM/XML.
3. The modeling method of the power distribution network knowledge graph model according to claim 2, wherein the data volume of the distribution network model is converted into the knowledge graph elements represented by vectors after being converted into a CIM/XML format.
4. The modeling method of the power distribution network knowledge graph model according to claim 3, wherein the knowledge graph elements are represented by a ternary relationship group < h, r, t >, wherein h represents a head entity, t represents a tail entity, and r represents a relationship between power supply and the like.
5. The modeling method of the knowledge graph model of the power distribution network as claimed in claim 1, wherein in step 200, when performing natural language analysis on the CIM/XML file of the data of the power distribution network model, the bidirectional LSTM model is used to extract keywords from the CIM/XML file, so as to obtain entity elements in the knowledge graph.
6. The modeling method of the power distribution network knowledge graph model according to claim 5, wherein the specific step of obtaining the entity elements in step 200 is:
step 201, selecting CIM/XML sentences in corresponding word segments;
step 202, carrying out word segmentation on the CIM/XML sentences by adopting the crust word segmentation to obtain a plurality of word segmentation sentences;
step 203, taking the participle sentences as the input of the bidirectional LSTM model, extracting key words in a plurality of the participle sentences, and combining the extracted key words into associated words;
and 204, obtaining entity elements of the triples in the knowledge graph according to the combined associated words.
7. The modeling method of the power distribution network knowledge graph model according to claim 4, wherein in step 300, the concrete steps of building the power distribution network knowledge graph model are as follows:
step 301, extracting high-level characteristics by adopting a deep neural network (RNN) model to acquire entity relationships;
step 302, connecting a head entity h and a tail entity t by using an entity relationship to form a triple of a knowledge graph;
and step 303, combining all the triples into a distribution network knowledge topology model.
8. The modeling method of the knowledge graph model of the power distribution network as claimed in claim 7, wherein a deep neural network (RNN) is used to extract high-level features for prediction in step 301, so as to obtain the relationship between the head entity h and the tail entity t.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911184390.1A CN111046189A (en) | 2019-11-27 | 2019-11-27 | Modeling method of power distribution network knowledge graph model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911184390.1A CN111046189A (en) | 2019-11-27 | 2019-11-27 | Modeling method of power distribution network knowledge graph model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111046189A true CN111046189A (en) | 2020-04-21 |
Family
ID=70233922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911184390.1A Pending CN111046189A (en) | 2019-11-27 | 2019-11-27 | Modeling method of power distribution network knowledge graph model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111046189A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112072652A (en) * | 2020-09-03 | 2020-12-11 | 武汉大学 | Power supply range division method for calculating DGs after faults |
| CN112181952A (en) * | 2020-11-30 | 2021-01-05 | 中国电力科学研究院有限公司 | Method, system, device and storage medium for constructing data model |
| CN112507129B (en) * | 2020-12-07 | 2023-09-08 | 云南电网有限责任公司普洱供电局 | Content change processing method of power distribution network operation file and related equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776562A (en) * | 2016-12-20 | 2017-05-31 | 上海智臻智能网络科技股份有限公司 | A kind of keyword extracting method and extraction system |
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| CN108460136A (en) * | 2018-03-08 | 2018-08-28 | 国网福建省电力有限公司 | Electric power O＆M information knowledge map construction method |
| CN109800310A (en) * | 2018-12-03 | 2019-05-24 | 国网浙江省电力有限公司杭州供电公司 | A kind of electric power O&M text analyzing method based on structuring expression |
| CN110277086A (en) * | 2019-06-25 | 2019-09-24 | 中国科学院自动化研究所 | Phoneme synthesizing method, system and electronic equipment based on dispatching of power netwoks knowledge mapping |
-
2019
- 2019-11-27 CN CN201911184390.1A patent/CN111046189A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| CN106776562A (en) * | 2016-12-20 | 2017-05-31 | 上海智臻智能网络科技股份有限公司 | A kind of keyword extracting method and extraction system |
| CN108460136A (en) * | 2018-03-08 | 2018-08-28 | 国网福建省电力有限公司 | Electric power O＆M information knowledge map construction method |
| CN109800310A (en) * | 2018-12-03 | 2019-05-24 | 国网浙江省电力有限公司杭州供电公司 | A kind of electric power O&M text analyzing method based on structuring expression |
| CN110277086A (en) * | 2019-06-25 | 2019-09-24 | 中国科学院自动化研究所 | Phoneme synthesizing method, system and electronic equipment based on dispatching of power netwoks knowledge mapping |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112072652A (en) * | 2020-09-03 | 2020-12-11 | 武汉大学 | Power supply range division method for calculating DGs after faults |
| CN112072652B (en) * | 2020-09-03 | 2022-03-01 | 武汉大学 | Power supply range division method for calculating DGs after faults |
| CN112181952A (en) * | 2020-11-30 | 2021-01-05 | 中国电力科学研究院有限公司 | Method, system, device and storage medium for constructing data model |
| CN112507129B (en) * | 2020-12-07 | 2023-09-08 | 云南电网有限责任公司普洱供电局 | Content change processing method of power distribution network operation file and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046189A (en) | Modeling method of power distribution network knowledge graph model | |
| CN101232180B (en) | Power distribution system load obscurity model building device and method | |
| CN104978411B (en) | A kind of automobile development method and apparatus of bullet train | |
| CN105701271B (en) | Method for creating and deleting equipment in graph-model hybrid simulation modeling of power system | |
| CN104732322A (en) | Mobile operation and maintenance method for power communication network machine rooms | |
| CN110929951B (en) | Correlation analysis and prediction method for power grid alarm signal | |
| CN112632288A (en) | Power dispatching system and method based on knowledge graph | |
| CN110390020A (en) | The modeling method of semantic gateway and semantic gateway | |
| CN113314106A (en) | Electric power information query and regulation function calling method based on voice and intention recognition | |
| CN110991188A (en) | Ticket forming method applied to distribution network scheduling intelligent ticket forming system | |
| CN106845935A (en) | A kind of method and system of engineering project flow template | |
| CN108829884A (en) | data mapping method and device | |
| CN109447466B (en) | Overall process visual management and control system based on power distribution network communication network construction | |
| CN109542452A (en) | A kind of operation management method and system based on AI semantic analysis | |
| CN106844819B (en) | Intelligent station secondary graph model library design tool database acquisition system | |
| CN112613790A (en) | Cooperative data processing method, device and medium applied to multi-station fusion environment | |
| CN117172413A (en) | Power grid equipment operation state monitoring method based on multi-mode data joint characterization and dynamic weight learning | |
| CN114201844A (en) | Hydropower station panoramic modeling method based on IEC61850 standard | |
| CN110086166B (en) | Method and system for representing stable operation quota of power grid | |
| Jiang et al. | Construction of substation engineering design knowledge graph based on “ontology seven-step method” | |
| CN111191845A (en) | Power communication network work monotony scheduling method based on DBSCAN algorithm and KMP mode matching method | |
| CN111046633A (en) | LSTM-based power grid primary frequency modulation data prediction method and device | |
| CN114328959B (en) | Knowledge graph construction and use method, device, equipment and medium | |
| CN115470798A (en) | Training method of intention recognition model, intention recognition method, device and equipment | |
| CN116128199A (en) | Information data analysis control platform and method based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |