CN111552813A - Power knowledge graph construction method based on power grid full-service data - Google Patents
Power knowledge graph construction method based on power grid full-service data Download PDFInfo
- Publication number
- CN111552813A CN111552813A CN202010191662.7A CN202010191662A CN111552813A CN 111552813 A CN111552813 A CN 111552813A CN 202010191662 A CN202010191662 A CN 202010191662A CN 111552813 A CN111552813 A CN 111552813A
- Authority
- CN
- China
- Prior art keywords
- data
- power grid
- power
- knowledge graph
- service data
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 4
- 238000005065 mining Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000000547 structure data Methods 0.000 description 2
- 241000282813 Aepyceros melampus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005338 heat storage Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
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
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Public Health (AREA)
- Tourism & Hospitality (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a power knowledge graph construction method based on power grid full-service data, which comprises the steps of converting the power grid full-service data into an RDF model; performing type division on data in the RDF model, and selecting phrases with similar meanings based on the divided phrases; constructing a knowledge triple of the selected phrases according to different entity attributes; and constructing the power knowledge graph according to the triples. By means of the knowledge graph technology, cross-business communication of business data is achieved, a gridding high-speed retrieval and deep mining function is provided, and the standardization, standardization and lean levels of enterprise management are improved.
Description
Technical Field
The invention belongs to the field of database management, and particularly relates to a power knowledge graph construction method based on power grid full-service data.
Background
The full-service unified data center is a collection center of full-service, full-type and full-time dimension data, provides complete data resources, high-efficiency analysis and calculation capacity and a unified operating environment for various analysis and decision applications of a company, changes the situation of repeated extraction and redundant storage of analysis type application data in the past, realizes the conversion from data moving to data moving, and supports the comprehensive development of enterprise-level data analysis and application.
At present, data through and data management are carried out in a full-service unified data center through modes of main data management, unified coding management and the like, but the effect on the carding and through of historical data is very weak, effective guarantee measures are lacked, and the continuity and effectiveness of the data through are difficult to ensure.
Disclosure of Invention
In order to solve the defects and shortcomings in the prior art, the invention provides a power knowledge graph construction method based on power grid full-service data, which realizes cross-service communication of service data by means of a knowledge graph technology, provides gridding high-speed retrieval and deep mining functions, and improves the standardization, standardization and lean levels of enterprise management.
Specifically, the electric power knowledge graph construction method includes:
converting the power grid full-service data into an RDF model,
performing type division on data in the RDF model, and selecting phrases with similar meanings based on the divided phrases;
constructing a knowledge triple of the selected phrases according to different entity attributes;
and constructing the power knowledge graph according to the triples.
Optionally, the converting the power grid full-service data into the RDF model includes:
and mapping the structured data representing the power grid full-service data into an RDF model.
The structured data is stored in a relational database, tables of the relational database are described as a class, columns are described as attributes, rows are described as entities, and values of cells are described as attribute values.
Optionally, the type division is performed on the data in the RDF model, and based on the divided phrases with similar meanings, the method includes:
dividing words of each sentence of text by adopting a hidden Markov model, and calculating the similarity of word vectors after word division;
and screening the entity words in accordance with the threshold value range based on the similarity degree value of the word vector, and performing object matching based on the screening result.
Optionally, the segmenting each sentence of the text by using the hidden markov model includes:
matching each participle with the class, attribute and entity word in the participle, and calculating two word vectors Vi,VjCosine similarity Sim (V) ofi,Vj) Similarity with part of speech Set (V)i,Vj)，
Wherein depth isViRepresents ViGrade of (D), Dist (V)i,Vj) Represents ViAnd VjSetting a threshold x for distances in the hierarchical tree1、x2And judging the similarity of the two words on the storage structure.
Optionally, the screening, based on the word vector similarity value, entity words that meet the threshold range, and performing object matching based on a screening result includes:
if Set (V)i,Vj)＜x1Or Sim (V)i,Vj)＜x2And then, the two words are considered to have similar word senses or parts of speech, all the entity words meeting the threshold range are sorted according to the similarity, and the participles are matched with similar classes, attributes and entity words.
Optionally, the constructing a knowledge triple from the selected phrases according to different entity attributes includes:
counting all possible situations of two different entity combinations and one entity and one attribute combination, wherein two entities or one entity and one attribute serve as two known elements e and r;
calculating the probability h (e, r) that each other entity matches a known element e, r into a triplet,
wherein WcBeing a vector matrix of elements under test, bpThe projection deviation is represented by the difference between the projection deviation,
Deand DrIs a diagonal matrix of dimension k × k, representing entities and relationship weights, respectively, bcIndicating the associated deviation;
setting a threshold value y, and if the condition of h (e, r) > y exists, selecting the triple formed by the e and the r of the maximum element.
The technical scheme provided by the invention has the beneficial effects that:
the built knowledge graph can provide knowledge service for novel application in the unified analysis service module, based on the knowledge graph technology, historical equipment data of operation inspection and marketing are combined, an account and an operation data graph which are unified for operation inspection and marketing are built, automatic matching of the account and the operation data is achieved, the change situation among data can be dynamically sensed, and the running-through efficiency and quality of operation and distribution data are improved. In addition, the method is applied to the construction of a cross-transport inspection and material datamation decision-making model and a monitoring system, the cross-business communication of enterprise data is realized, the inquiry of defective equipment purchasing information is completed, and a reliable basis is provided for supplier evaluation and purchasing plan making.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a power knowledge graph construction method based on power grid full-service data according to an embodiment of the present application.
Detailed Description
To make the structure and advantages of the present invention clearer, the structure of the present invention will be further described with reference to the accompanying drawings.
Example one
The embodiment of the application provides a power knowledge graph construction method based on power grid full-service data, and as shown in fig. 1, the power knowledge graph construction method comprises the following steps:
converting power grid full-service data into an RDF model;
secondly, performing type division on data in the RDF model, and selecting phrases with similar meanings based on the divided phrases;
step three, constructing a knowledge triple by the selected phrases according to different entity attributes;
and step four, constructing a power knowledge graph according to the triples.
In implementation, the full-service unified data center is a platform for modeling, collecting, uniformly storing, managing and analyzing and applying structured data, measurement and collection data and unstructured data of a power grid, and the main technical structure of the full-service unified data center is shown in fig. 1. The data layer is data of each service system of the power grid and is generally divided into three types, namely a structure type, a semi-structure type and a non-structure type, different types of data are collected through the data collection layer and stored in the data collection layer, structured data are collected and extracted at regular time through the data timing extraction module and are synchronously stored in an MPP (maximum power point tracking) data warehouse, and semi-structure data and non-structure data are collected through the real-time data and file data collection module and are stored in the Hadoop storage component. The storage component stores heat storage point data and real-time acquisition data by using a Redis database and an Hbase database respectively, and the distributed file system HDFS component [10] provides high-reliability bottom-layer storage support for the Hbase. The platform data summarization layer provides computing components including stream computing, memory computing, batch computing, query computing and the like, data cleaning and computing services are provided, the stream computing components adopt an STORM computing framework to achieve data cleaning and real-time computing analysis, the memory computing components adopt a Spark computing engine to achieve rapid computing of large-scale data, the batch computing components adopt a MapReduce distributed computing model to complete offline distributed computing of the large-scale data, and the query computing components adopt an Impala real-time analysis query engine to achieve rapid query of the data. The data summarization layer cleans and converts the data according to the service requirements, extracts and integrates the correlation information among all stored data into a field standardized table for storage, organizes the data into a special data set of a data mart according to different service rules, and provides data support for upper analysis service and service application.
The method comprises the steps of constructing a knowledge graph of the electric power data, organizing and retrieving the electric power data in an intelligent and efficient mode, providing support for cross-professional business process optimization, deep mining and data asset utilization, establishing enterprise information holographic figures, achieving cross-business communication of the business data, providing gridding high-speed retrieval and deep mining functions, and improving the standardization, standardization and lean levels of power grid enterprise management.
According to the first step, the structured data is mapped into an RDF model. When the map is constructed, according to the first step, mapping the structured data into an RDF model by taking each field as an index of the data of the line; according to the second step, extracting various indexes of the semi-structured data according to time periods, and taking the combination of the time and the indexes as a basis for word segmentation; and according to the second step, performing word segmentation on the unstructured data according to the key description information, and performing similarity calculation on the unstructured data and words in a word bank to realize entity matching. And according to the third step, calculating the probability of forming the triples by different entities and attributes, and constructing the triples of the power grid data. And according to the fourth step, a knowledge graph is constructed between the unified storage service and the unified analysis service of the unified data center of the power saving network company.
Specifically, the step of converting the model provided in the step one includes:
and mapping the structured data representing the power grid full-service data into an RDF model.
The structured data is stored in a relational database, tables of the relational database are described as a class, columns are described as attributes, rows are described as entities, and values of cells are described as attribute values.
The matching step proposed in the second step comprises the following steps:
dividing words of each sentence of text by adopting a hidden Markov model, and calculating the similarity of word vectors after word division;
and screening the entity words in accordance with the threshold value range based on the similarity degree value of the word vector, and performing object matching based on the screening result.
In implementation, the segmenting words for each sentence of text by using the hidden markov model includes:
matching each participle with the class, attribute and entity word in the participle, and calculating two word vectors Vi,VjCosine similarity Sim (V) ofi,Vj) Similarity with part of speech Set (V)i,Vj)，
Wherein
Represents ViGrade of (D), Dist (V)i,Vj) Represents ViAnd VjSetting a threshold x for distances in the hierarchical tree1、x2And judging the similarity of the two words on the storage structure.
The method for screening the entity words meeting the threshold value range based on the word vector similarity degree value comprises the following steps of:
if Set (V)i,Vj)＜x1Or Sim (V)i,Vj)＜x2And then, the two words are considered to have similar word senses or parts of speech, all the entity words meeting the threshold range are sorted according to the similarity, and the participles are matched with similar classes, attributes and entity words.
The triple composition step proposed by the third step comprises the following steps:
counting all possible situations of two different entity combinations and one entity and one attribute combination, wherein two entities or one entity and one attribute serve as two known elements e and r;
calculating the probability h (e, r) that each other entity matches a known element e, r into a triplet,
wherein WcBeing a vector matrix of elements under test, bpThe projection deviation is represented by the difference between the projection deviation,
Deand DrIs a diagonal matrix of dimension k × k, representing entities and relationship weights, respectively, bcIndicating the associated deviation;
setting a threshold value y, and if the condition of h (e, r) > y exists, selecting the triple formed by the e and the r of the maximum element.
And the knowledge graph integrally constructs a model, and is positioned between the unified storage service and the unified analysis service. Structured, semi-structured and unstructured data resources of the full-service unified data center provide original data for construction of the knowledge graph, and then triples are calculated through entity extraction and knowledge fusion of the knowledge graph and stored in a knowledge graph library. The unified analysis service may directly invoke the data content of the knowledge-graph.
The sequence numbers in the above embodiments are merely for description, and do not represent the sequence of the assembly or the use of the components.
The above description is only exemplary of the present invention and should not be taken as limiting the invention, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A power knowledge graph construction method based on power grid full-service data is characterized by comprising the following steps:
converting the power grid full-service data into an RDF model;
performing type division on data in the RDF model, and selecting phrases with similar meanings based on the divided phrases;
constructing a knowledge triple of the selected phrases according to different entity attributes;
and constructing the power knowledge graph according to the triples.
2. The method for constructing the power knowledge graph based on the power grid full-service data according to claim 1, wherein the converting the power grid full-service data into the RDF model comprises:
mapping structured data representing power grid full-service data into an RDF model;
the structured data is stored in a relational database, tables of the relational database are described as a class, columns are described as attributes, rows are described as entities, and values of cells are described as attribute values.
3. The method for constructing the power knowledge graph based on the power grid full-service data according to claim 1, wherein the type division is performed on the data in the RDF model, and the method comprises the following steps of based on divided phrases with similar meanings:
dividing words of each sentence of text by adopting a hidden Markov model, and calculating the similarity of word vectors after word division;
and screening the entity words in accordance with the threshold value range based on the similarity degree value of the word vector, and performing object matching based on the screening result.
4. The method for constructing the power knowledge graph based on the power grid full-service data according to claim 1, wherein the segmenting of each sentence of text by using the hidden Markov model comprises the following steps:
matching each participle with the class, attribute and entity word in the participle, and calculating two word vectors Vi,VjCosine similarity Sim (V) ofi,Vj) Similarity with part of speech Set (V)i,Vj)，
Wherein
Represents ViGrade of (D), Dist (V)i,Vj) Represents ViAnd VjSetting a threshold x for distances in the hierarchical tree1、x2And judging the similarity of the two words on the storage structure.
5. The power knowledge graph construction method based on power grid full-service data according to claim 4, wherein the step of screening entity words meeting a threshold range based on word vector similarity numerical values and performing object matching based on screening results comprises the steps of:
if Set (V)i,Vj)＜x1Or Sim (V)i,Vj)＜x2And then, the two words are considered to have similar word senses or parts of speech, all the entity words meeting the threshold range are sorted according to the similarity, and the participles are matched with similar classes, attributes and entity words.
6. The power grid full-service data-based power knowledge graph construction method according to claim 1, wherein the constructing of the selected phrases into the knowledge triples according to different entity attributes comprises:
counting all possible situations of two different entity combinations and one entity and one attribute combination, wherein two entities or one entity and one attribute serve as two known elements e and r;
calculating the probability h (e, r) that each other entity matches a known element e, r into a triplet,
wherein WcBeing a vector matrix of elements under test, bpThe projection deviation is represented by the difference between the projection deviation,
Deand DrIs a diagonal matrix of dimension k × k, representing entities and relationship weights, respectively, bcIndicating the associated deviation;
setting a threshold value y, and if the condition of h (e, r) > y exists, selecting the triple formed by the e and the r of the maximum element.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010191662.7A CN111552813A (en) | 2020-03-18 | 2020-03-18 | Power knowledge graph construction method based on power grid full-service data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010191662.7A CN111552813A (en) | 2020-03-18 | 2020-03-18 | Power knowledge graph construction method based on power grid full-service data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111552813A true CN111552813A (en) | 2020-08-18 |
Family
ID=72001848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010191662.7A Pending CN111552813A (en) | 2020-03-18 | 2020-03-18 | Power knowledge graph construction method based on power grid full-service data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111552813A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148893A (en) * | 2020-09-25 | 2020-12-29 | 南方电网数字电网研究院有限公司 | Energy analysis knowledge graph construction method and energy analysis visualization method |
| CN112308464A (en) * | 2020-11-24 | 2021-02-02 | 中国人民公安大学 | Business process data processing method and device |
| CN112463990A (en) * | 2020-12-17 | 2021-03-09 | 北京国电通网络技术有限公司 | Power grid infrastructure knowledge graph construction method and device, electronic equipment and storage medium |
| CN112486992A (en) * | 2020-11-30 | 2021-03-12 | 深圳供电局有限公司 | Data storage method and system |
| CN112612902A (en) * | 2020-12-23 | 2021-04-06 | 国网浙江省电力有限公司电力科学研究院 | Knowledge graph construction method and device for power grid main device |
| CN112685570A (en) * | 2020-12-15 | 2021-04-20 | 南京南瑞继保电气有限公司 | Multi-label graph-based power grid network frame knowledge graph construction method |
| CN112860914A (en) * | 2021-03-02 | 2021-05-28 | 中国电子信息产业集团有限公司第六研究所 | Network data analysis system and method of multi-element identification |
| CN113095646A (en) * | 2021-03-31 | 2021-07-09 | 天津大学 | Shale gas exploitation step water cyclic utilization intelligent system |
| CN113159326A (en) * | 2021-03-03 | 2021-07-23 | 国网山西省电力公司信息通信分公司 | Intelligent business decision method based on artificial intelligence |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016117920A1 (en) * | 2015-01-20 | 2016-07-28 | 한국과학기술원 | Knowledge represention expansion method and apparatus |
| CN110674311A (en) * | 2019-09-05 | 2020-01-10 | 国家电网有限公司 | Knowledge graph-based power asset heterogeneous data fusion method |
-
2020
- 2020-03-18 CN CN202010191662.7A patent/CN111552813A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016117920A1 (en) * | 2015-01-20 | 2016-07-28 | 한국과학기술원 | Knowledge represention expansion method and apparatus |
| CN110674311A (en) * | 2019-09-05 | 2020-01-10 | 国家电网有限公司 | Knowledge graph-based power asset heterogeneous data fusion method |
Non-Patent Citations (1)
| Title |
|---|
| 王渊等: "知识图谱在电网全业务统一数据中心的应用" * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148893A (en) * | 2020-09-25 | 2020-12-29 | 南方电网数字电网研究院有限公司 | Energy analysis knowledge graph construction method and energy analysis visualization method |
| CN112308464A (en) * | 2020-11-24 | 2021-02-02 | 中国人民公安大学 | Business process data processing method and device |
| CN112308464B (en) * | 2020-11-24 | 2023-11-24 | 中国人民公安大学 | Business process data processing method and device |
| CN112486992A (en) * | 2020-11-30 | 2021-03-12 | 深圳供电局有限公司 | Data storage method and system |
| CN112486992B (en) * | 2020-11-30 | 2023-11-21 | 深圳供电局有限公司 | Data storage method and system |
| CN112685570B (en) * | 2020-12-15 | 2022-07-22 | 南京南瑞继保电气有限公司 | Multi-label graph-based power grid network frame knowledge graph construction method |
| CN112685570A (en) * | 2020-12-15 | 2021-04-20 | 南京南瑞继保电气有限公司 | Multi-label graph-based power grid network frame knowledge graph construction method |
| CN112463990A (en) * | 2020-12-17 | 2021-03-09 | 北京国电通网络技术有限公司 | Power grid infrastructure knowledge graph construction method and device, electronic equipment and storage medium |
| CN112612902B (en) * | 2020-12-23 | 2023-07-14 | 国网浙江省电力有限公司电力科学研究院 | Knowledge graph construction method and device for power grid main equipment |
| CN112612902A (en) * | 2020-12-23 | 2021-04-06 | 国网浙江省电力有限公司电力科学研究院 | Knowledge graph construction method and device for power grid main device |
| CN112860914A (en) * | 2021-03-02 | 2021-05-28 | 中国电子信息产业集团有限公司第六研究所 | Network data analysis system and method of multi-element identification |
| CN113159326A (en) * | 2021-03-03 | 2021-07-23 | 国网山西省电力公司信息通信分公司 | Intelligent business decision method based on artificial intelligence |
| CN113159326B (en) * | 2021-03-03 | 2024-02-23 | 国网山西省电力公司信息通信分公司 | Intelligent business decision method based on artificial intelligence |
| CN113095646A (en) * | 2021-03-31 | 2021-07-09 | 天津大学 | Shale gas exploitation step water cyclic utilization intelligent system |
| CN113095646B (en) * | 2021-03-31 | 2022-08-19 | 天津大学 | Shale gas exploitation step water cyclic utilization intelligent system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111552813A (en) | Power knowledge graph construction method based on power grid full-service data | |
| CN109918511B (en) | BFS and LPA based knowledge graph anti-fraud feature extraction method | |
| CN111967761A (en) | Monitoring and early warning method and device based on knowledge graph and electronic equipment | |
| CN114077674A (en) | Power grid dispatching knowledge graph data optimization method and system | |
| CN112256882A (en) | Multi-similarity-based cross-system network entity fusion method | |
| CN107862459B (en) | Metering equipment state evaluation method and system based on big data | |
| CN115438199A (en) | Knowledge platform system based on smart city scene data middling platform technology | |
| CN115858829A (en) | Multi-source heterogeneous environment data asset construction method based on computational power network | |
| CN115934856A (en) | Method and system for constructing comprehensive energy data assets | |
| CN109886618B (en) | Method and device for optimizing logistics operation | |
| CN116662860A (en) | User portrait and classification method based on energy big data | |
| CN116401338A (en) | Design feature extraction and attention mechanism based on data asset intelligent retrieval input and output requirements and method thereof | |
| CN115688729A (en) | Power transmission and transformation project cost data integrated management system and method thereof | |
| CN115587190A (en) | Construction method and device of knowledge graph in power field and electronic equipment | |
| Chen | Characteristic scales, scaling, and geospatial analysis | |
| CN115687788A (en) | Intelligent business opportunity recommendation method and system | |
| Qin et al. | Construction of knowledge graph of multi-source heterogeneous distribution network systems | |
| CN114238045A (en) | System and method for judging and automatically repairing integrity of multi-source measurement data of power grid | |
| Meng et al. | Design and Implementation of Knowledge Graph Platform of Power Marketing | |
| CN113987164A (en) | Project studying and judging method and device based on domain event knowledge graph | |
| Zhang et al. | Research on the application of auto spare parts sales forecast in the age of big data | |
| Yang et al. | Power user portrait model based on random forest | |
| CN118246749B (en) | Financial data risk analysis method and system based on large model proxy | |
| CN117934209B (en) | Regional power system carbon emission big data analysis method based on knowledge graph | |
| CN109299442A (en) | Chinese chapter primary-slave relation recognition methods and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200818 |