CN113342987B - Composite network construction method of distribution DTU acceptance special corpus - Google Patents
Composite network construction method of distribution DTU acceptance special corpus Download PDFInfo
- Publication number
- CN113342987B CN113342987B CN202110427261.1A CN202110427261A CN113342987B CN 113342987 B CN113342987 B CN 113342987B CN 202110427261 A CN202110427261 A CN 202110427261A CN 113342987 B CN113342987 B CN 113342987B
- Authority
- CN
- China
- Prior art keywords
- acceptance
- corpus
- equipment
- adopting
- information
- 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.)
- Active
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 41
- 239000002131 composite material Substances 0.000 title claims abstract description 11
- 238000010276 construction Methods 0.000 title abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 238000003860 storage Methods 0.000 claims abstract description 11
- 230000000295 complement effect Effects 0.000 claims abstract description 4
- 230000003993 interaction Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 4
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000029087 digestion Effects 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims 1
- 238000012795 verification Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000013523 data management Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- 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
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- 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 Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Animal Behavior & Ethology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Telephonic Communication Services (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a composite network construction method of a distribution DTU acceptance special corpus, and relates to double-engine semantic search of a sentence call corpus with changeable business content and sentence patterns. Comprises the following steps of S1: extracting semantics, namely extracting non-formatted texts such as equipment entities, equipment attributes, relations and the like in data sources such as a distribution network procedure by adopting CNN, RNN and BiLSTM respectively; step S2: knowledge fusion, namely, adopting an ESIM coreference resolution model to finish fusion of repeated information with the same index in the extraction result; step S3: the distributed storage corpus is stored by adopting a distributed database model with a graph database and a relational database which are mutually complementary for the consistency result of knowledge fusion; step S4: the semantic retrieval, the sentence pattern fixed sentence pattern adopts template matching, and tests show that the corpus and the retrieval mode constructed by the scheme have the characteristics of accurate semantic recognition and high keyword retrieval speed.
Description
Technical Field
The invention belongs to the field of distribution network terminal debugging, and particularly relates to a composite network construction method of a distribution DTU acceptance special corpus.
Background
And the distribution data terminal (DATA TRANSFER unit, DTU) is used as key equipment of the distribution network, and the automatic test efficiency is directly related to whether the distribution network upgrading and transformation can be delivered on time. At present, automatic acceptance of a power distribution terminal still needs to be matched with operation and maintenance personnel of a main station through field staff to trigger communication, and in a traditional mode, automatic acceptance personnel at a main station side of a distribution network are required to carry out information check acceptance through telephones and field staff, the acceptance time is long, and the module acceptance efficiency is low.
In recent years, with mass equipment and terminal access in energy internet construction, requirements on power supply reliability are more strict. The construction of a power reliability management system is continuously strengthened by the relevant departments of the country in combination with power grid enterprises, the advanced integration of power supply reliability index management and distribution business management is promoted, and the comprehensive upgrading and transformation of a power distribution network are unprecedented. The automatic test receiving mode of the traditional power distribution terminal is difficult, and the automatic test receiving mode becomes a problem to be solved in the reliable operation of the energy Internet.
The knowledge graph is used as a core foundation for integrating the heterogeneous data resources of the power grid, and can provide effective support for heterogeneous data management of the power grid enterprises under the energy Internet. At present, research of knowledge graph-based knowledge questions and answers (knowledge based question answering, KBQA) in the power industry is mainly focused on a field named entity identification method and customer service system construction, and a field knowledge graph construction method for automatic acceptance of a power distribution terminal and an automatic acceptance implementation method taking intelligent man-machine conversation as a basis are not formed.
Disclosure of Invention
The invention aims to solve the problems of long waiting time, large repeated workload and low acceptance efficiency of a power distribution main station worker in the traditional acceptance mode of a power distribution data terminal, and provides a composite network construction method of a power distribution DTU acceptance special corpus.
The invention aims at realizing the following technical method:
the method for constructing the composite network of the distribution DTU acceptance special corpus comprises the following steps:
Step S1: semantic extraction, namely extracting non-formatted texts in a data source including a distribution network procedure by adopting CNN, RNN and BiLSTM respectively;
Step S2: knowledge fusion, namely, adopting an ESIM coreference resolution model to finish fusion of repeated information with the same index in the extraction result;
Step S3: the distributed storage corpus is stored by adopting a distributed database model with a graph database and a relational database which are mutually complementary for the consistency result of knowledge fusion;
Step S4: semantic retrieval, wherein sentences with fixed sentence patterns are matched by adopting templates, and the semantic retrieval relates to double-engine semantic search of a corpus invoked by sentences with changeable business content and sentence patterns;
wherein the non-formatted text includes device entities, device attributes, and relationships.
Optionally, the method comprises the following steps:
in the knowledge fusion process, the extracted information is subjected to co-index disambiguation and co-index digestion based on an ESIM model, and the method specifically comprises the following steps:
αt=ωα·FFNNα(x*) (1);
Where x *=[ht,1,ht,-1 is the output of the BiLSTM network, 1 and-1 represent the direction in which LSTM recognizes the context, where The attention factor is the accumulation of co-indexed word weights in a sequence span i.
Optionally, the method includes:
And classifying and storing the equipment, personnel and index entities stored in the power distribution automation domain knowledge graph according to the entity association degree, wherein the entity with the entity association degree less than or equal to 10 is stored in MySQL, and the entity with the entity association degree greater than 10 is stored in Neo4 j.
Optionally, the acceptance personnel in step S1 calls an intelligent virtual debugging seat module running in the Open5200 system after dialing a specified private line by holding the encrypted mobile terminal uniformly distributed by the power grid company.
Optionally, in step S1, an MVC architecture is adopted in a man-machine interaction process between the field debugging personnel and the virtual seat.
Optionally, the information fused in the step S2 includes equipment ID information and personnel identity information;
the equipment ID information comprises geographic position information of equipment and the serial numbers of the equipment in the system;
the person identity information includes the name and number of the acceptance person.
Optionally, the method specifically comprises the following steps:
Step S91: the site acceptance personnel dials a special line, and the virtual seat is accessed to the master station;
step S92: verifying the equipment ID and the identity information of the acceptance person;
step S93: testing the terminals to be regulated on the target line one by one according to a preset debugging plan and acceptance rules, comparing the field test result of each data terminal with the telemetry data of the master station, and automatically generating an acceptance report according to the comparison result and feeding back to the master station;
Step S94: if the acceptance report is abnormal, automatically entering the next terminal acceptance process, if the data are not matched, switching on the master station manual service, and making a further decision after the debugger and the on-site acceptance person are in dialogue.
Therefore, the invention has the following advantages:
1. The intelligent virtual debugging seat system has intelligent voice interaction and semantic search functions, can realize automation of acceptance rule execution and intellectualization of joint debugging data interaction, and integrates high-efficiency data processing, reliable storage and intelligent interaction.
2. The distributed storage technology of the combined graph database and the relational database simplifies the relation construction flow, improves the retrieval efficiency and gives consideration to the integrity and the reliability of data storage.
3. The knowledge extraction technology based on deep learning solves the problems that data are difficult to align when a graph mapping method is adopted to obtain the relationship between power equipment from a topological structure (semi-structured data) of a circuit diagram, and accuracy and coverage rate of results are difficult to reach engineering application requirements when information extraction is carried out from unstructured data by using a traditional machine learning method such as a conditional random field, a support vector machine, a decision tree and the like.
Drawings
Fig. 1 is a schematic diagram of a business process according to the present invention.
Detailed Description
In order to make the features and advantages of the present patent comprehensible, embodiments accompanied with figures are described in detail below:
the method for constructing the composite network of the distribution DTU acceptance special corpus comprises the following steps as shown in figure 1:
Step S1: semantic extraction, namely extracting non-formatted texts in a data source including a distribution network procedure by adopting CNN, RNN and BiLSTM respectively;
Step S2: knowledge fusion, namely, adopting an ESIM coreference resolution model to finish fusion of repeated information with the same index in the extraction result;
Step S3: the distributed storage corpus is stored by adopting a distributed database model with a graph database and a relational database which are mutually complementary for the consistency result of knowledge fusion;
Step S4: semantic retrieval, wherein sentences with fixed sentence patterns are matched by adopting templates, and the semantic retrieval relates to double-engine semantic search of a corpus invoked by sentences with changeable business content and sentence patterns;
wherein the non-formatted text includes device entities, device attributes, and relationships.
Optionally, the method comprises the following steps:
in the knowledge fusion process, the extracted information is subjected to co-index disambiguation and co-index digestion based on an ESIM model, and the method specifically comprises the following steps:
αt=ωα·FFNNα(x*) (1);
Where x *=[ht,1,ht,-1 is the output of the BiLSTM network, 1 and-1 represent the direction in which LSTM recognizes the context, where The attention factor is the accumulation of co-indexed word weights in a sequence span i.
Optionally, the method includes:
And classifying and storing the equipment, personnel and index entities stored in the power distribution automation domain knowledge graph according to the entity association degree, wherein the entity with the entity association degree less than or equal to 10 is stored in MySQL, and the entity with the entity association degree greater than 10 is stored in Neo4 j.
Optionally, the acceptance personnel in step S1 calls an intelligent virtual debugging seat module running in the Open5200 system after dialing a specified private line by holding the encrypted mobile terminal uniformly distributed by the power grid company.
Optionally, in step S1, an MVC architecture is adopted in a man-machine interaction process between the field debugging personnel and the virtual seat.
Optionally, the information fused in the step S2 includes equipment ID information and personnel identity information;
the equipment ID information comprises geographic position information of equipment and the serial numbers of the equipment in the system;
the person identity information includes the name and number of the acceptance person.
Optionally, the method specifically comprises the following steps:
Step S91: the site acceptance personnel dials a special line, and the virtual seat is accessed to the master station;
step S92: verifying the equipment ID and the identity information of the acceptance person;
step S93: testing the terminals to be regulated on the target line one by one according to a preset debugging plan and acceptance rules, comparing the field test result of each data terminal with the telemetry data of the master station, and automatically generating an acceptance report according to the comparison result and feeding back to the master station;
Step S94: if the acceptance report is abnormal, automatically entering the next terminal acceptance process, if the data are not matched, switching on the master station manual service, and making a further decision after the debugger and the on-site acceptance person are in dialogue.
Specifically, practical examples of the above scheme are:
Step 1: unstructured data in the text is subjected to structuring processing by using a deep neural network, and the step is divided into three subtasks of named entity recognition, attribute extraction and relation extraction. Respectively realized by CNN, RNN and BiLSTM;
step 2: the data obtained through knowledge extraction in the step 1 contains a plurality of repeated information, such as 3U0 and ABC phase zero sequence voltages, and three-phase zero sequence voltages refer to the same object; the power distribution DTU and the power distribution DTU device have the same meaning. Coreference resolution is required by relational extension computation. The screened data are not stored in the map, and are used as the connection between the relational database and the knowledge map;
In particular, ESIM coreference resolution models are employed, i.e
αt=ωα·FFNNα(x*) (1)
Where x *=[ht,1,ht,-1 is the output of the BiLSTM network and 1 and-1 represent the direction in which the LSTM recognizes the context. Wherein the method comprises the steps ofThe attention factor is the accumulation of co-indexed word weights in a sequence span i.
A sequence representation of the integration into the attention mechanism can be obtained after weighted summation of the BiLSTM network's output x * The sequence is subjected to comprehensive evaluation on the accuracy, recall rate and harmonic F value through a three-layer scoring structure, and the sequence with the highest score is considered as the target sequence needing to be stored in the map.
Step 3: in order to effectively solve the problems of difficult construction of entity relationship and long retrieval time caused by deep coupling and high data association degree among power equipment of the distribution network, the data search efficiency is improved, and all results of knowledge extraction are reserved as far as possible. Storing the target sequence obtained in the step 2 by adopting a distributed storage technology of a joint graph database and a relational database;
And 4, the invention provides a semantic search technology based on sentence pattern matching and KGDTAAD double engines. The step 4 specifically includes:
Step 4.1, determining the relation between the node to be identified and the object to be searched through text analysis;
Step 4.2, carrying out pattern matching on the instruction response of which the sentence patterns are relatively fixed, such as 'hello, i is XXX', 'dialing XXX', 'correct, please start', by adopting an ESIM model and sentence patterns in a predefined corpus, and executing preset operation in a template library when the results are consistent;
and 4.3, directly calling KGDTAAD to form an answer for a long sentence scene containing a plurality of equipment operation parameters.
And 5, constructing a software architecture of the intelligent virtual seat, providing general technical support for development, operation and management of various applications of the system, providing uniform exchange service, model management, data management and graphic management, meeting the requirements of the distribution network for scheduling various real-time, quasi-real-time and production management services, and supporting various operation monitoring applications of the distribution network.
Step 6: by improving the hardware architecture of the Open5200 system and enhancing the data throughput and interaction capability, a distributed hardware processing platform based on an aggregated semantic search engine is developed.
And step 1, carrying out knowledge extraction and distributed storage on a distribution DTU acceptance rule text, a history alarm, an operation log and the like through an NLP technology, and importing the knowledge graph into a distribution terminal for automatically testing the acceptance field knowledge graph.
Step 1.1 knowledge extraction technique based on deep learning
And 1.1.1, respectively using CNN, RNN and BiLSTM to implement named entity identification, attribute extraction and relationship extraction so as to extract knowledge elements of entity, relationship and attribute from unstructured data.
Step 1.1.2, the data obtained through knowledge extraction contains a plurality of repeated information, such as 3U0, ABC phase zero sequence voltage and three phase zero sequence voltage, which refer to the same object; the power distribution DTU and the power distribution DTU device have the same meaning. The method is characterized in that the coreference resolution is realized through relation extension calculation, screened data are not stored in the map, and the data can be linked with entities in the knowledge map by using a relation type database.
Step 1.2 distributed storage techniques in conjunction with graph databases and relational databases
If the topological relation among the power equipment participating in the joint debugging is represented by a circuit diagram, a diagram database is used for storage. For entity classes with rich entity attribute information, and some frequently updated data (such as events, logs, fault logs, etc.), relational database storage is used.
Step 1.3, establishing a structured index label on an attribute column of a graph database entity node, and enabling the structured index label to point to a corresponding table in a relational database to realize the link with data in a knowledge graph.
And 2, after receiving a trigger instruction (such as channel connection of a master station, identity information confirmation and the like) of a field person, the aggregation AI scheduling engine invokes a semantic retrieval function, connects a preset corpus and a graph database, and selects a retrieval mode according to the entity attribute richness.
And 3, the aggregate AI dispatching engine and the field personnel confirm the ID and the geographical position information of the equipment to be dispatched, and test the DTU to be dispatched on the target line one by one according to a preset debugging plan and an acceptance rule after verifying that the equipment ID and the geographical position information are correct.
And 4, comparing the field test result of each DTU with the remote measurement data of the master station, automatically generating an acceptance report according to the result, and feeding back to the master station, and making a further decision by the master station staff according to the acceptance report.
And 5, structuring the processed acceptance report, constructing an expert system through a deep learning technology, automatically generating structured domain knowledge such as fault records, acceptance rules, processing plans and the like, further constructing or updating an automatic testing acceptance map of the distribution DTU, and forming a case knowledge map for case recording, consulting and reasoning.
The foregoing is illustrative of the present application and is not to be construed as limiting thereof, but rather, the present application is to be construed as limited to the appended claims.
Claims (5)
1. The method for constructing the composite network of the distribution DTU acceptance special corpus is characterized by comprising the following steps of:
Step S1: semantic extraction, namely extracting non-formatted texts in a data source including a distribution network procedure by adopting CNN, RNN and BiLSTM respectively;
Step S2: knowledge fusion, namely, adopting an ESIM coreference resolution model to finish fusion of repeated information with the same index in the extraction result;
Step S3: the distributed storage corpus is stored by adopting a distributed database model with a graph database and a relational database which are mutually complementary for the consistency result of knowledge fusion;
Step S4: semantic retrieval, wherein sentences with fixed sentence patterns are matched by adopting templates, and the semantic retrieval relates to double-engine semantic search of a corpus invoked by sentences with changeable business content and sentence patterns;
Wherein the non-formatted text comprises equipment entities, equipment attributes and relationships;
Named entity recognition, attribute extraction and relationship extraction are respectively realized by CNN, RNN and BiLSTM to extract knowledge elements such as entities, relationships, attributes and the like from unstructured data;
in the knowledge fusion process, the extracted information is subjected to co-index disambiguation and co-index digestion based on an ESIM model, and the method specifically comprises the following steps:
αt=ωα·FFNNα(x*) (1);
where x *=[ht,1,ht,-1 is the output of the BiLSTM network, 1 and-1 represent the direction in which LSTM recognizes the context, where The attention coefficient is the accumulation of the weights of the co-pointed words in a sequence span i;
The method comprises the following steps:
And classifying and storing the equipment, personnel and index entities stored in the power distribution automation domain knowledge graph according to the entity association degree, wherein the entity with the entity association degree less than or equal to 10 is stored in MySQL, and the entity with the entity association degree greater than 10 is stored in Neo4 j.
2. The method for constructing a composite network of a corpus dedicated to power distribution DTU acceptance according to claim 1, wherein the acceptance personnel in step S1 call an intelligent virtual debugging seat module running in the Open5200 system after dialing a specified private line by holding an encrypted mobile terminal uniformly distributed by a power grid company.
3. The method for constructing a composite network of a corpus dedicated to power distribution DTU acceptance according to claim 1, wherein in step S1, an MVC architecture is adopted in a man-machine interaction process between field debugging personnel and a virtual agent.
4. The method for constructing a composite network of a corpus dedicated to power distribution DTU acceptance according to claim 1, wherein the information fused in step S2 includes equipment ID information and personnel identity information;
the equipment ID information comprises geographic position information of equipment and the serial numbers of the equipment in the system;
the person identity information includes the name and number of the acceptance person.
5. The method for constructing the compound network of the distribution DTU acceptance special corpus according to claim 1, further comprising a corpus verification operation, and is characterized by specifically comprising:
Step S91: the site acceptance personnel dials a special line, and the virtual seat is accessed to the master station;
step S92: verifying the equipment ID and the identity information of the acceptance person;
step S93: testing the terminals to be regulated on the target line one by one according to a preset debugging plan and acceptance rules, comparing the field test result of each data terminal with the telemetry data of the master station, and automatically generating an acceptance report according to the comparison result and feeding back to the master station;
Step S94: if the acceptance report is abnormal, automatically entering the next terminal acceptance process, if the data are not matched, switching on the master station manual service, and making a further decision after the debugger and the on-site acceptance person are in dialogue.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110427261.1A CN113342987B (en) | 2021-04-21 | 2021-04-21 | Composite network construction method of distribution DTU acceptance special corpus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110427261.1A CN113342987B (en) | 2021-04-21 | 2021-04-21 | Composite network construction method of distribution DTU acceptance special corpus |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113342987A CN113342987A (en) | 2021-09-03 |
CN113342987B true CN113342987B (en) | 2024-05-14 |
Family
ID=77468244
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110427261.1A Active CN113342987B (en) | 2021-04-21 | 2021-04-21 | Composite network construction method of distribution DTU acceptance special corpus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113342987B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114069836A (en) * | 2021-09-28 | 2022-02-18 | 国网浙江省电力有限公司杭州供电公司 | Artificial intelligence-based docking method for operation and maintenance operation of distribution automation system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018036239A1 (en) * | 2016-08-24 | 2018-03-01 | 慧科讯业有限公司 | Method, apparatus and system for monitoring internet media events based on industry knowledge mapping database |
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 |
CN111598702A (en) * | 2020-04-14 | 2020-08-28 | 徐佳慧 | Knowledge graph-based method for searching investment risk semantics |
-
2021
- 2021-04-21 CN CN202110427261.1A patent/CN113342987B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018036239A1 (en) * | 2016-08-24 | 2018-03-01 | 慧科讯业有限公司 | Method, apparatus and system for monitoring internet media events based on industry knowledge mapping database |
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 |
CN111598702A (en) * | 2020-04-14 | 2020-08-28 | 徐佳慧 | Knowledge graph-based method for searching investment risk semantics |
Also Published As
Publication number | Publication date |
---|---|
CN113342987A (en) | 2021-09-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108491378B (en) | Intelligent response system for operation and maintenance of electric power information | |
CN109740928A (en) | Electric power consultation service treating method and apparatus | |
CN107180029A (en) | A kind of information processing method and device based on consultation service | |
CN109446305A (en) | The construction method and system of intelligent tour customer service system | |
CN112200465B (en) | Electric power AI method and system based on multimedia information intelligent analysis | |
CN111859969B (en) | Data analysis method and device, electronic equipment and storage medium | |
CN111598417B (en) | Natural language processing-based electric power non-emergency repair order distribution method | |
CN112241402A (en) | Empty pipe data supply chain system and data management method | |
CN113434634A (en) | Knowledge graph construction method and device | |
CN112632239A (en) | Brain-like question-answering system based on artificial intelligence technology | |
Yuan | [Retracted] The Construction and Exploration of University English Translation Teaching Mode Based on the Integration of Multimedia Network Technology | |
CN113342987B (en) | Composite network construction method of distribution DTU acceptance special corpus | |
Dong | Exploration on web usage mining and its application | |
Zhang et al. | Research on Intelligent Robot Engine of Electric Power Online Customer Services Based on Knowledge Graph | |
CN116561288B (en) | Event query method, device, computer equipment, storage medium and program product | |
CN111784192A (en) | Industrial park emergency plan executable system based on dynamic evolution | |
Shi et al. | Human resources balanced allocation method based on deep learning algorithm | |
CN115587174A (en) | Power grid intelligent question-answering system based on question information missing completion | |
CN115048528A (en) | Method and device for constructing knowledge graph of new energy electric field operation data | |
Li et al. | Research on Grid Basic Data Synchronization Method for Electricity IoT Cloud Platform | |
Liu et al. | Big data analysis model of customer appeal based on power enterprise service platform | |
Paludetto et al. | MESP-An Interoperable Platform for Multi-Energy Systems | |
CN114069836A (en) | Artificial intelligence-based docking method for operation and maintenance operation of distribution automation system | |
Meng et al. | Design and Implementation of Knowledge Graph Platform of Power Marketing | |
Ning et al. | UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |