CN116702902A - Hydrologic data map reasoning and knowledge base construction method - Google Patents
Hydrologic data map reasoning and knowledge base construction method Download PDFInfo
- Publication number
- CN116702902A CN116702902A CN202310398421.3A CN202310398421A CN116702902A CN 116702902 A CN116702902 A CN 116702902A CN 202310398421 A CN202310398421 A CN 202310398421A CN 116702902 A CN116702902 A CN 116702902A
- Authority
- CN
- China
- Prior art keywords
- data
- reasoning
- hydrologic
- knowledge base
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000009411 base construction Methods 0.000 title claims abstract description 17
- 238000007726 management method Methods 0.000 claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims abstract description 36
- 238000004519 manufacturing process Methods 0.000 claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000010276 construction Methods 0.000 claims abstract description 11
- 238000013523 data management Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 20
- 238000012544 monitoring process Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000001228 spectrum Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 abstract description 2
- 238000012546 transfer Methods 0.000 abstract description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 18
- 238000000605 extraction Methods 0.000 description 8
- 230000008521 reorganization Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 230000008020 evaporation Effects 0.000 description 2
- 239000003673 groundwater Substances 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012558 master data management Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- 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
-
- 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
- G06N5/027—Frames
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention provides a hydrological data map reasoning and knowledge base construction method, which comprises the steps of constructing a hydrological data map reasoning machine and constructing a hydrological data map knowledge base; the construction of the hydrological data map inference engine comprises the following steps: constructing a hydrologic analysis calculation inference engine, a hydrologic data production chain inference engine and a system stop operation influence inference engine; the construction of the hydrological data map knowledge base comprises the following steps: constructing a system and data, a model, station measurement data, personnel data and transaction management data; the hydrologic analysis calculation inference engine is constructed on the basis of the hydrologic data map, the model description language is used as transfer, the model is introduced into the knowledge base, the barriers of the system to which the model belongs can be disregarded, and the purpose is to guide and drive the multi-system related model to calculate.
Description
Technical Field
The invention relates to the hydrologic field, in particular to a hydrologic data map reasoning and knowledge base construction method.
Background
The hydrologic data are important data supporting various projects of water conservancy and reflect the change of rivers and lakes. At present, due to the early-stage short and quick hydrologic informatization construction mode, hydrologic services are severely cut, independent systems are respectively established by different services, interaction is difficult to achieve, resultant force is formed, great resistance is caused to hydrologic comprehensive analysis, management and application, and the requirements of multi-service joint management and scheduling are difficult to meet. For hydrologic data with complex production process, due to the fact that more data are involved, operators are more, when problems are found, tracing is difficult, links with problems are difficult to find, the data problems can be solved only by adopting a way of misplacing or discarding the erroneous data, however, the way often causes deviation of analysis results due to insufficient data quantity or insufficient data precision.
Disclosure of Invention
Aiming at overcoming the defects of the prior art, the invention provides a hydrological data map reasoning and knowledge base construction method, which constructs a hydrological data map knowledge base and performs integrated hydrological data processing and management.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the invention provides a hydrologic data spectrum reasoning and knowledge base construction method, which comprises the steps of constructing a hydrologic data spectrum reasoning machine and constructing a hydrologic data spectrum knowledge base;
the construction of the hydrological data map inference engine comprises the following steps: constructing a hydrologic analysis calculation inference engine, a hydrologic data production chain inference engine and a system stop operation influence inference engine;
the construction of the hydrological data map knowledge base comprises the following steps: and constructing a system and data, a model, station measurement data, personnel data and transaction management data.
Further, the hydrologic analysis calculation inference engine is:
DC＝{d i ,modle,D i+1 ,S i ,a i }{i∈[0,n]}
wherein d i The current reasoning node data is formed into { st, tm, d, sl }, and st is a measuring station; tm is time; d is a numerical value; sl is the storage location; mode i A calculation model for obtaining current reasoning node data; d (D) i+1 For mode i Input parameter set of (2)When there is data +.>When the numerical value cannot be obtained, the data is used as the next reasoning node data; s is(s) i To produce d i Is a system of (2); ai is s i Is a business manager;
when i=0, calculation target data is represented;
when i=n, it means that the hydrologic analysis calculation inference engine stops the inference.
Further, the condition that the hydrologic analysis and calculation inference engine stops the inference includes:
D i+1 all parameters in the model (a) obtain values and directly calculate;
modle i if not, the data can not be obtained through inference calculation, and the system s is required to be contacted i Is a business manager of (a) i The situation is verified and the data is acquired.
Further, the hydrologic data production chain inference engine is:
DP＝{d j ,modle,D j+1 ,S j+1 ,H j+1 }(j∈[0,n])
wherein S is j+1 Is equal to D j+1 Set of production coefficients for one-to-one correspondence of data
H j+1 To extract from the system operation log, and D j+1 Data one-to-one production system set
When D is j+1 Data in (a)In case of abnormality, contact H j+1 Middle->The producer contact check condition;
when j=0, data indicating that an abnormality is initially found;
when j=n, it means that the hydrologic data production chain inference engine stops the inference.
Further, the conditions for stopping the reasoning by the hydrologic data production chain reasoning machine include:
modle j is empty and represents d j Rather than being obtained by calculation, there is no further data backtracking for monitoring, at which point D j+1 、s j+1 And H j+1 And are also empty.
Further, the system stopping operation influence inference engine is as follows:
SO＝{S k ,D k ,S k+1 ,A k+1 }(k∈[0,n])
wherein S is k For a system to stop running, representing a system function or representing a database; d (D) k For data sets which cannot be produced or storedA k+1 Is s is equal to k+1 One-to-one corresponding service manager setNotifying service manager of corresponding condition in time; s is(s) k+1 Each parameter within the set will be divided intoThe initial condition of the next reasoning is not used;
when k=0, the system initially stops running;
when k=n, the stopping operation of the current system does not affect other systems, and reasoning is stopped.
Furthermore, the system and the data are organized by using a metadata management tool in data management and taking a production system as a main line, the relation among the systems and the data is organized, the metadata management information is finally extracted into a knowledge base through the combination relation of metadata and the dependency relation of the metadata, and the relation among the systems and the data entities is formed through the combination and the dependency relation.
Further, the model is packaged into an interface service, and then the interface of the module is described by using an interface description language to form model description data; and extracting the model description data into a knowledge base to form a model entity.
Further, the station measurement data refers to that the main data management tool in the data management is utilized to perform consistency processing on the data of the same station measurement in different services, the consistency processing object comprises definition and attribute value of basic information attribute of the station measurement, and the consistency processing mode is to discard the data with low priority based on the data with high priority; and finally, extracting the maximum intersection of the basic attributes of the measuring stations of different services to form measuring station data, designating unified codes, and extracting the unified codes into a knowledge base to form a measuring station entity.
Further, the personnel data refers to extracting unified user information of the mechanism into a knowledge graph to form personnel entities;
the transaction management data refers to forming a transaction data set by using a data set management tool in data management.
The beneficial effects of the invention are as follows: the hydrologic analysis calculation inference engine is constructed on the basis of the hydrologic data map, the model description language is used as transfer, the model is introduced into the knowledge base, the barriers of the system to which the model belongs can be disregarded, and the purpose is to guide and drive the multi-system related model to calculate.
The hydrologic data production chain inference machine is constructed on the basis of the hydrologic data processing management knowledge graph, and under the complex production chain of the multi-service system, aiming at data abnormality, the retrospective production flow is assisted, the positioning of a problem link is assisted, and the situation that the hydrologic data is misplaced or important data is abandoned is reduced.
And (3) constructing a system stop operation influence inference engine on the basis of the hydrologic data processing management knowledge graph, and when serious data problems are caused by the system and database stop operation, actively early warning is carried out to assist related personnel in preparing in advance, and the problem is passively solved after the problem is generated.
On the basis of hydrologic data, an entering person and a system are introduced into a knowledge base, and a knowledge graph performs hydrologic data processing and management integrated reasoning, so that each hydrologic data processing and management work is guaranteed, related responsible persons can be traced back in time, and management efficiency is improved.
Detailed Description
The present invention will be described in further detail below in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
A hydrologic data spectrum reasoning and knowledge base construction method is characterized by comprising the steps of constructing a hydrologic data spectrum reasoning machine and constructing a hydrologic data spectrum knowledge base;
the construction of the hydrological data map inference engine comprises the following steps: constructing a hydrologic analysis calculation inference engine, a hydrologic data production chain inference engine and a system stop operation influence inference engine;
the method constructs a hydrologic analysis calculation inference engine, realizes the combined calculation of a model and data of a drive cross system, constructs a data production chain inference engine, backtracks a production chain, positions abnormality, solves the problem, constructs an influence inference engine of a system stopping operation for events (such as large-range data loss) of serious data problems caused by the system stopping operation of a database, analyzes the data influence in time and assists related personnel to perform active early warning and alarming for the data abnormality problem generated in calculation.
The construction of the hydrological data map knowledge base comprises the following steps: and constructing a system and data, a model, station measurement data, personnel data and transaction management data.
When a certain item of data needs to be calculated, all the data participating in the calculation are automatically inferred and calculated, and if the calculation cannot be performed due to the lack of necessary data, a responsible person is immediately searched to complete the production and preparation of the related data.
The hydrologic analysis calculation inference engine is:
DC＝{d i ,modle,D i+1 ,S i ,a i }{i∈[0,n]}
wherein d i The current reasoning node data is formed into { st, tm, d, sl }, and st is a measuring station; tm is time; d is a numerical value; sl is the storage location; mode i A calculation model for obtaining current reasoning node data; d (D) i+1 For mode i Input parameter set of (2)When there is data +.>When the numerical value cannot be obtained, the data is used as the next reasoning node data; s is(s) i To produce d i Is a system of (2); a, a i Is s i Is a business manager;
when i=0, calculation target data is represented;
when i=n, it means that the hydrologic analysis calculation inference engine stops the inference.
The condition that the hydrologic analysis and calculation inference engine stops the inference comprises:
D i+1 all parameters in the model (a) obtain values and directly calculate;
modle i if not, the data can not be obtained through inference calculation, and the system s is required to be contacted i Is a business manager of (a) i The situation is verified and the data is acquired.
When the data is abnormal, the link which may be wrong in the production process is traced back through reasoning the data production chain.
The hydrologic data production chain inference engine is:
DP＝{d j ,modle,D j+1 ,S j+1 ,H j+1 }(j∈[0,n])
wherein S is j+1 Is equal to D j+1 Set of production coefficients for one-to-one correspondence of data
H j+1 To extract from the system operation log, and D j+1 Data one-to-one production system set
When D is j+1 Data in (a)In case of abnormality, contact H j+1 Middle->The producer contact check condition;
when j=0, data indicating that an abnormality is initially found;
when j=n, it means that the hydrologic data production chain inference engine stops the inference.
The conditions for stopping reasoning by the hydrologic data production chain reasoning machine include:
modle j is empty and represents d j Rather than being obtained by calculation, there is no further data backtracking for monitoring, at which point D j+1 、s j+1 And H j+1 And are also empty.
When the system is required to stop running due to maintenance or faults, maintenance staff is assisted to maintain and recover by reasoning the service influenced by the system.
The system stop operation influence inference engine is as follows:
SO＝{S k ,D k ,S k+1 ,A k+1 }(k∈[0,n])
wherein S is k To stop the system, the system is representedSystem functions or representation databases; d (D) k For data sets which cannot be produced or storedA k+1 Is s is equal to k+1 One-to-one corresponding service manager setNotifying service manager of corresponding condition in time; s is(s) k+1 Each parameter in the set is used as an initial condition for the next reasoning;
when k=0, the system initially stops running;
when k=n, the stopping operation of the current system does not affect other systems, and reasoning is stopped.
System shutdown affects the inference engine implementation, see table below:
the system and the data are organized by using a metadata management tool in data management and taking a production system as a main line, the relation among the systems and the data is organized, and finally the metadata management information is extracted into a knowledge base to form a system and a data entity, and the relation among the entities is formed by combining and depending on the combination relation of the metadata and the depending relation of the metadata.
The combination relation of metadata represents the relation between the system and adjacent layers such as a database, a database and a data table, a data table and a data attribute and the like.
The dependency relationship of metadata represents the relationship among systems, databases, data tables and data attributes.
The model is an important content in hydrologic calculation, and the knowledge graph has the advantages of relationship management and reasoning, so that the calculation model is difficult to directly introduce into a knowledge base. The method introduces the model into the knowledge base in a model description mode.
The model is packaged into an interface service, and then the interface of the module is described by using an interface description language, wherein the interface comprises a model name, a function description, input and output parameters, a model source, a calling mode and the like.
Forming model description data; and extracting the model description data into a knowledge base to form a model entity. The model is not directly used as the entity node of the knowledge graph, but the model description data is used as the entity node, and the model interface is further called through the model description data. The knowledge graph establishes a relation between the model and the business data through the description of the input data parameters in the model description data.
The station measurement data is that the main data management tool in the data management is utilized to carry out consistency processing on the data of the same station measurement in different services, the consistency processing object comprises definition and attribute value of basic information attribute of the station measurement, the consistency processing mode is that the data with high priority is used as the reference, and the data with low priority is discarded; that is, when information can be extracted from service data with high priority, the information in service data with low priority can be directly extracted, and the information in service data with low priority is not considered. According to the attention degree and the data reliability of the hydrologic industry, the priority is as follows from high to low: hydrological water level information, precipitation evaporation information, real-time water rain condition information, water quality information and groundwater information.
And finally, extracting the maximum intersection of the basic attributes of the measuring stations of different services to form measuring station data, designating unified codes, and extracting the unified codes into a knowledge base to form a measuring station entity.
And establishing a relation between the unified code and each business code, taking the unified code as a tie, and establishing an entity relation between different business data.
The personnel data refers to extracting unified user information of a mechanism into a knowledge graph to form personnel entities;
the transaction management data refers to forming a transaction data set by using a data set management tool in data management. Transaction data sets include workflow, user logs, attendance, personnel, finance, contract management, and the like. The transaction data is introduced into a knowledge base, so that the entity relationship between the person and business works such as hydrologic analysis and calculation, hydrologic data production, system operation and maintenance management and the like is established.
Example 1
The hydrological data atlas system construction generally comprises three aspects of determining the domain and category of the ontology, atlas extraction and inference engine construction.
The domain and category of the ontology are determined through data management.
At present, the field and the category of the body are mainly determined in a top-down mode by expert experience, omission is unavoidable in the mode, and in practical application of the water conservancy industry, a main key of the defect is reserved. Therefore, a bottom-up method is adopted to determine the domain and category of the ontology. The bottom-up method generally has large analysis, arrangement and extraction difficulties due to large data volume, and adopts a data management mode to manage complex, heterogeneous and dispersed data into an orderly, standard and manageable whole, so that the bottom-up analysis and arrangement process is more scientific, and the difficulty is reduced.
Determining data fields using metadata
The production system is taken as a main line, data produced by each system and data produced by other systems are organized, the data produced and maintained by the systems are represented by a combination relation, and the data required to be input and used by the system production is represented by a dependency relation. The data mainly contained in the hydrological metadata comprises service data, file metadata and model metadata, wherein the service data is a data item which is directly produced by each service system and can be directly used for calculation and analysis, and the service data comprises hydrological monitoring data, hydrological forecast data, hydrological analysis data, equipment working condition data and the like. The file metadata is information for managing the data of each business file, the file comprises a data analysis report, a data distribution diagram, a file, a working image and the like, and the management information comprises a file name, key content, a storage position, file time and the like. The model metadata is information for describing a model in the model management system, the model comprises a hydrological mechanism model, a mathematical model, a machine learning model and the like, and the description information comprises a model name, a function description, input and output parameters, a model source, a calling mode and the like. By metadata management of file metadata and model metadata, files and models can be managed together from the data perspective.
An example of metadata organization of the present invention is the following table:
determining a survey station area and a personnel area using master data
Station measuring field
And taking the station as a main line, establishing a station code relation of the station codes of the unified station in different services, and determining the identification of one station in different services. And then, taking the unique station code as a tie, and carrying out consistency processing on definition and attribute values of basic information attributes of measuring stations in different businesses, wherein the sequence of the definition and the attribute values is hydrologic water level information, precipitation evaporation information, real-time water rain information, water quality information and groundwater information. And then extracting the maximum intersection of basic attributes of different service stations, wherein unique station identification is used as main data, the attributes in the intersection comprise names, drainage basin water systems, administrative regions, management units and geographic positions, and the rest data are not included in the main data management. Finally, the data series catalogue of the measuring station is extracted one by one according to the database table by taking the measuring station as a unit, and the catalog content comprises the data name, the source, the annual and monthly range of the data, and the accumulated annual and monthly number of the data. The data series list of a certain measuring station is as follows:
personnel domain
And establishing corresponding relation of user information in different service systems by taking the unified user of the organization as a main line. And the same user code is used as a tie, and the user information in different services is subjected to consistency processing.
Determining topic domains using topic data
Taking the data service theme as a main line, regardless of the production source, storage position and storage format of the data, the data of the same theme are assembled to form different theme domains convenient to analyze and mine.
The method comprises the steps of taking a business theme as a main line, and dividing data into five main core theme domains of basic data, reorganized data, monitoring data, business processing data, transaction data and the like according to a data processing process. Then gradually refining each theme set, wherein basic data comprise basic information theme sets of supporting services related to station basic information, station code corresponding relation, water conservancy object information, mechanism information, characteristic values and index information and other different services; the reorganization data comprise core hydrologic data theme sets subjected to arrangement such as basic hydrologic reorganization data, water quality analysis and evaluation data and underground water reorganization data; the monitoring data comprises original data theme sets automatically or manually monitored such as hydrologic monitoring data, water quality monitoring data and underground water monitoring data; the service processing data comprise theme sets such as forecast data, water resource analysis and evaluation data, monitoring process data, equipment working condition data, cross-service fusion data and the like; the transaction data includes data sets of workflow, user logs, attendance, personnel, finance, contract management, and the like.
Knowledge graph extraction method based on data management resource library
The data management is carried out, the generated management catalogue, management items and management description information jointly form a data management resource library, and the knowledge graph is extracted based on the data management resource library.
Ontology and ontology relationship extraction
Selected, the ontology derived from metadata management includes: production system, database, data resource, file, model, key attributes. The ontology derived from the master data management includes: station, river basin, water system, river, province, city, management unit, monitoring unit, station data, personnel. The ontology derived from topic data management includes: basic data, reorganization data, monitoring data, business processing data, transaction data.
The hydrologic ontology relationship includes: the "produced" relation between the database and the business system, the "containing" relation between the database and the data resource, the file and the model, the "association" relation between the measuring station and other water conservancy objects, the "membership" relation between the measuring station, personnel and organization mechanisms, the "membership" relation between different hierarchy mechanisms, the "association" relation between different water conservancy objects and the "membership" relation between the measuring station and measuring station data. The data types of different levels are in 'belonging' relation, and the data resources are in 'input' relation and 'output' relation with the model.
Entity and entity relationship extraction
And a Java development knowledge extractor is utilized to provide the entity extraction function. The ontology extraction supports the user to select an ontology and an ontology relationship from a data management resource library, and creates the ontology as a label and the ontology relationship as a relationship in Neo4 j. The entity extraction function supports the user to extract records from the table of the selected ontology, and correspondingly store the records into the label and the relation created in Neo4 j. Meanwhile, the method supports the manual establishment of the ontology by the user, and the importing of the entity and the entity relationship. The final data map is stored and queried through Neo4 j.
The foregoing examples merely illustrate embodiments of the invention and are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A hydrologic data spectrum reasoning and knowledge base construction method is characterized by comprising the steps of constructing a hydrologic data spectrum reasoning machine and constructing a hydrologic data spectrum knowledge base;
the construction of the hydrological data map inference engine comprises the following steps: constructing a hydrologic analysis calculation inference engine, a hydrologic data production chain inference engine and a system stop operation influence inference engine;
the construction of the hydrological data map knowledge base comprises the following steps: and constructing a system and data, a model, station measurement data, personnel data and transaction management data.
2. The method for hydrologic data map reasoning and knowledge base construction according to claim 1, wherein the hydrologic analysis and calculation reasoning machine is as follows:
DC＝{di,modle,Di+1,Si,ai}{i∈[0,n]}
where di is current reasoning node data, and is formed as { st, tm, d, sl }, and st is a station; tm is time; d is a numerical value; sl is the storage location; mode i A calculation model for obtaining current reasoning node data; d (D) i+1 For mode i Input parameter set of (2)When there is data +.>When the numerical value cannot be obtained, the data is used as the next reasoning node data; s is(s) i To produce d i Is a system of (2); ai is s i Is a business manager;
when i=0, calculation target data is represented;
when i=n, it means that the hydrologic analysis calculation inference engine stops the inference.
3. The method for hydrologic data map reasoning and knowledge base construction according to claim 2, wherein the condition that the hydrologic analysis and calculation reasoning machine stops reasoning comprises:
D i+1 all parameters in the model (a) obtain values and directly calculate;
modle i if not, the data can not be obtained through inference calculation, and the system s is required to be contacted i The service manager ai of (1) verifies the situation and acquires the data.
4. The method for hydrological data map reasoning and knowledge base construction according to claim 2, wherein the method comprises the following steps: the hydrologic data production chain inference engine is:
DP＝{dj,modle,Dj+1,Sj+1,Hj+1}(j∈[0,n]) Wherein S is j+1 Is equal to D j+1 Raw data one-to-one correspondenceSet of yield coefficientsH j+1 To extract from the system operation log, and D j+1 Data one-to-one set of production systems>
When D is j+1 Data in (a)In case of abnormality, contact H j+1 Middle->The producer contact check condition;
when j=0, data indicating that an abnormality is initially found;
when j=n, it means that the hydrologic data production chain inference engine stops the inference.
5. The method for hydrologic data map reasoning and knowledge base construction according to claim 4, wherein the condition for stopping reasoning by the hydrologic data production chain reasoning machine comprises:
modle j is empty and represents d j Rather than being obtained by calculation, there is no further data backtracking for monitoring, at which point D j+1 、s j+1 And H j+1 And are also empty.
6. The method for hydrological data map reasoning and knowledge base construction according to claim 5, wherein the system stopping operation affects the reasoning machine: so= { S k ,D k ,S k+1 ,A k+1 }(k∈[0,n])
Wherein S is k For a system to stop running, representing a system function or representing a database; d (D) k For data sets which cannot be produced or storedA k+1 Is s is equal to k+1 One-to-one corresponding service manager setNotifying service manager of corresponding condition in time; s is(s) k+1 Each parameter in the set is used as an initial condition for the next reasoning;
when k=0, the system initially stops running;
when k=n, the stopping operation of the current system does not affect other systems, and reasoning is stopped.
7. The method for hydrological data map reasoning and knowledge base construction as claimed in claim 6, wherein: the system and the data are organized by using a metadata management tool in data management and taking a production system as a main line, the relation among the systems and the data is organized, and finally the metadata management information is extracted into a knowledge base to form a system and a data entity, and the relation among the entities is formed by combining and depending on the combination relation of the metadata and the depending relation of the metadata.
8. The method for hydrological data map reasoning and knowledge base construction as claimed in claim 7, wherein: the model is packaged into an interface service, and then the interface of the module is described by using an interface description language to form model description data; and extracting the model description data into a knowledge base to form a model entity.
9. The method for hydrological data map reasoning and knowledge base construction as claimed in claim 8, wherein: the station measurement data is that the main data management tool in the data management is utilized to carry out consistency processing on the data of the same station measurement in different services, the consistency processing object comprises definition and attribute value of basic information attribute of the station measurement, the consistency processing mode is that the data with high priority is used as the reference, and the data with low priority is discarded; and finally, extracting the maximum intersection of the basic attributes of the measuring stations of different services to form measuring station data, designating unified codes, and extracting the unified codes into a knowledge base to form a measuring station entity.
10. The method for hydrological data map reasoning and knowledge base construction according to claim 9, wherein: the personnel data refers to extracting unified user information of a mechanism into a knowledge graph to form personnel entities;
the transaction management data refers to forming a transaction data set by using a data set management tool in data management.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310398421.3A CN116702902A (en) | 2023-04-14 | 2023-04-14 | Hydrologic data map reasoning and knowledge base construction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310398421.3A CN116702902A (en) | 2023-04-14 | 2023-04-14 | Hydrologic data map reasoning and knowledge base construction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116702902A true CN116702902A (en) | 2023-09-05 |
Family
ID=87834692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310398421.3A Pending CN116702902A (en) | 2023-04-14 | 2023-04-14 | Hydrologic data map reasoning and knowledge base construction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702902A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2464056A1 (en) * | 2003-04-29 | 2004-10-29 | Vernon Rogers | Water resource management system and methods of use thereof |
| CN111368095A (en) * | 2020-02-28 | 2020-07-03 | 河海大学 | Decision support system architecture and method based on water conservancy knowledge-affair coupling network |
| CN112182234A (en) * | 2020-07-29 | 2021-01-05 | 长江勘测规划设计研究有限责任公司 | Drainage basin flood control planning data knowledge graph construction method |
| CN113094514A (en) * | 2021-04-13 | 2021-07-09 | 北京工业大学 | Water affair data intelligent discovery method based on domain knowledge graph |
| CN113377966A (en) * | 2021-08-11 | 2021-09-10 | 长江水利委员会水文局 | Water conservancy project scheduling regulation reasoning method based on knowledge graph |
| CN113656647A (en) * | 2021-06-02 | 2021-11-16 | 韦东庆 | Intelligent operation and maintenance oriented engineering archive data management platform, method and system |
| CN113672599A (en) * | 2020-09-30 | 2021-11-19 | 华斌 | Visual aid decision-making method for realizing government affair informatization project construction management by creating domain knowledge graph |
-
2023
- 2023-04-14 CN CN202310398421.3A patent/CN116702902A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2464056A1 (en) * | 2003-04-29 | 2004-10-29 | Vernon Rogers | Water resource management system and methods of use thereof |
| CN111368095A (en) * | 2020-02-28 | 2020-07-03 | 河海大学 | Decision support system architecture and method based on water conservancy knowledge-affair coupling network |
| CN112182234A (en) * | 2020-07-29 | 2021-01-05 | 长江勘测规划设计研究有限责任公司 | Drainage basin flood control planning data knowledge graph construction method |
| CN113672599A (en) * | 2020-09-30 | 2021-11-19 | 华斌 | Visual aid decision-making method for realizing government affair informatization project construction management by creating domain knowledge graph |
| CN113094514A (en) * | 2021-04-13 | 2021-07-09 | 北京工业大学 | Water affair data intelligent discovery method based on domain knowledge graph |
| CN113656647A (en) * | 2021-06-02 | 2021-11-16 | 韦东庆 | Intelligent operation and maintenance oriented engineering archive data management platform, method and system |
| CN113377966A (en) * | 2021-08-11 | 2021-09-10 | 长江水利委员会水文局 | Water conservancy project scheduling regulation reasoning method based on knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114579875B (en) | Equipment fault diagnosis and maintenance knowledge recommendation system based on knowledge graph | |
| CN113553420B (en) | Power grid fault processing rule recommendation method and system based on knowledge graph | |
| CN111078897A (en) | System for generating six-dimensional knowledge map | |
| CN110175324B (en) | Power grid operation instruction verification method and system based on data mining | |
| CN112182077B (en) | Intelligent operation and maintenance system based on data middling platform technology | |
| CN110502398A (en) | A kind of exchange fault forecasting system and method based on artificial intelligence | |
| CN112540975B (en) | Multi-source heterogeneous data quality detection method and system based on petri net | |
| CN110853744A (en) | Hospital quality control management system under big data | |
| CN113095524A (en) | Intelligent generation method, system and storage medium for maintenance work document of power equipment | |
| CN115718472A (en) | Fault scanning and diagnosing method for hydroelectric generating set | |
| CN113204329A (en) | Control method for driving business application by unified data model and application system thereof | |
| CN112241424A (en) | Air traffic control equipment application system and method based on knowledge graph | |
| CN113065580A (en) | Power plant equipment management method and system based on multi-information fusion | |
| CN116611813B (en) | Intelligent operation and maintenance management method and system based on knowledge graph | |
| CN116932523A (en) | Platform for integrating and supervising third party environment detection mechanism | |
| CN116702902A (en) | Hydrologic data map reasoning and knowledge base construction method | |
| CN112784129A (en) | Pump station equipment operation and maintenance data supervision platform | |
| CN114860891A (en) | Method and device for constructing space-time map of intelligent pipe network | |
| CN110298585B (en) | Hierarchical automatic auditing method for monitoring information of substation equipment | |
| CN112241428A (en) | Digital decision-making method and system | |
| CN112765232B (en) | Data management method and system for major equipment of nuclear power plant | |
| CN117934209B (en) | Regional power system carbon emission big data analysis method based on knowledge graph | |
| CN109379219A (en) | TMS and mobile O&M terminal towards power communication scene share exchange method | |
| Gao et al. | A Novel Portrait Technology-Based Modeling and Alarm Tagging Method for SDH Device in Smart Grid | |
| CN113298326B (en) | Intelligent electronic event supervision method, equipment and storage medium |
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 |