CN116662580A - Emergency scheduling intelligent assistant method and system based on knowledge graph - Google Patents
Emergency scheduling intelligent assistant method and system based on knowledge graph Download PDFInfo
- Publication number
- CN116662580A CN116662580A CN202310409248.2A CN202310409248A CN116662580A CN 116662580 A CN116662580 A CN 116662580A CN 202310409248 A CN202310409248 A CN 202310409248A CN 116662580 A CN116662580 A CN 116662580A
- Authority
- CN
- China
- Prior art keywords
- case
- fault
- cases
- knowledge
- equipment
- 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 62
- 238000003672 processing method Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000003491 array Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- 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
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Power Engineering (AREA)
- Animal Behavior & Ethology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a knowledge graph-based emergency dispatching intelligent assistant method and a knowledge graph-based emergency dispatching intelligent assistant system, which belong to the field of power distribution network fault dispatching treatment, and comprise the following steps that a user inputs identity information and the use permission of the user is judged; inputting equipment fault information; analyzing and structuring the equipment fault information; the knowledge search fault processing method pushes and processes business flow suggestions; searching a fault case by knowledge, and pushing a device fault case; the specification returns to the data format; and recommending the result to the user. The method of the intelligent assistant for emergency dispatching based on the knowledge graph is applied to power distribution network fault dispatching, can effectively improve the emergency processing capacity and dispatching intelligence level of a power grid, pushes and processes business process suggestions and equipment fault cases through a knowledge search fault processing method, helps a dispatcher to comprehensively know the type of faults of a treatment process and equipment when the power distribution network is faulty, and improves accuracy and prejudgement for subsequent treatment.
Description
Technical Field
The application relates to the field of power distribution network fault dispatching and handling, in particular to a knowledge graph-based intelligent assistant method and system for emergency dispatching.
Background
With the increasing scale of power systems, the power distribution network is a key for ensuring the power supply quality as a final link closely connected with the user terminal. Because of the complexity of power distribution network fault scheduling, the comprehensive perception of power grid state and data by scheduling personnel is required, fault information is taken as a key point, and according to work regulations such as scheduling regulations, safety regulations and the like, by combining fault plans, historical fault records and scheduling experience, each department is coordinated to make quick and accurate countermeasures and work deployment, and safe, stable and economic operation of the power distribution network is ensured to be recovered in a short time. The existing power distribution network fault dispatching management mode is seriously lagged behind the development requirement of the system.
The knowledge graph is proposed by google corporation in 2012, and is rapidly developed and widely applied in the fields of internet, finance, medicine and the like. The knowledge graph is a knowledge base for representing entities and interrelations thereof in the objective world in the form of a graph, and is one of knowledge expression modes of artificial intelligence symbols in the big data era. The intelligent knowledge extraction, reasoning, storage and retrieval system can effectively organize, manage and utilize massive information, and can achieve intelligent knowledge extraction, reasoning, storage and retrieval, and the characteristics and application scenes of the intelligent knowledge extraction, reasoning, storage and retrieval system are very matched with the requirements of an electric power system.
In the existing power distribution network fault dispatching treatment, the application of a knowledge graph is less, intelligent power distribution network fault emergency dispatching intelligent assistant auxiliary dispatcher who needs intelligence is used for helping a dispatcher to rapidly analyze the fault reason of power distribution network equipment, comprehensively master key information of fault treatment and improve emergency treatment capacity of a power grid, so that efficiency is improved.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The present application has been made in view of the above and/or existing problems with knowledge-graph-based emergency dispatch intelligent assistant methods.
Therefore, the problem to be solved by the application is how to provide a knowledge graph-based intelligent assistant method for emergency dispatch.
In order to solve the technical problems, the application provides the following technical scheme: an emergency dispatch intelligent assistant method based on a knowledge graph comprises the following steps,
the user inputs identity information, judges the user's use authority and inputs equipment fault information;
analyzing and structuring the equipment fault information, searching a fault processing method by knowledge, and pushing a business flow proposal to be processed;
knowledge searches for fault cases, pushes equipment fault cases, returns data formats in a standard, and recommends results to users.
As a preferable scheme of the knowledge graph-based emergency dispatch intelligent assistant method, the application comprises the following steps: the equipment fault information is an equipment fault file; the file type is confirmed, the file content is analyzed by utilizing the corresponding interface, and specific attribute information including the type of the fault equipment, the equipment number, the occurrence place, the equipment state and the fault phenomenon is extracted.
As a preferable scheme of the knowledge graph-based emergency dispatch intelligent assistant method, the application comprises the following steps: the push processing business flow proposal recommends fault occurrence factors corresponding to the fault equipment type and the state in the extracted specific attribute information as root entity nodes; scheduling rules, safety rules and expert experiences in the knowledge graph are called, and service flow suggestions are recommended according to task logic by combining the fault types and states of the power equipment.
As a preferable scheme of the knowledge graph-based emergency dispatch intelligent assistant method, the application comprises the following steps: the fault cases of the pushing equipment are obtained from a knowledge graph, and the case cluster in which the fault cases are located is selected for pushing the case with highest similarity; the case clusters where the fault cases are located comprise the same equipment fault case cluster and similar equipment fault case clusters.
As a preferable scheme of the knowledge graph-based emergency dispatch intelligent assistant method, the application comprises the following steps:
wherein simA (G i ,G j ) Overall similarity between two cases Gi, gj; w (W) k A weight coefficient for each item of specific attribute information to occupy the similarity of the overall specific attribute information; simA k (G i ,G j ) Similarity of each item of specific attribute information for case Gi and case Gj; k is 1, 2, …; n is the number of items of specific attribute information;
simA k (G i ,G j ) Adopts WordNet semantic concept tree distance divisionCalculating similarity simA of each specific attribute information of case Gi and case Gj k (G i ,G j )；
Where depth (Gi, K) is the depth of the kth item of specific attribute information of case Gi in the semantic concept tree; depth (Gj, K) is the depth of the K-th item of specific attribute information of the case Gj in the semantic concept tree; depth (lso (Gi, K, gj, K) is the depth of the most recent common raw data of the kth item of specific attribute information of case Gi and the kth item of specific attribute information of case Gj in the semantic concept tree, and K is 1, 2, ….
As a preferable scheme of the knowledge graph-based emergency dispatch intelligent assistant method, the application comprises the following steps: randomly selecting an unprocessed case from a case total set, searching all cases with overall similarity smaller than a first threshold value in the case total set, when the number of the searched cases is larger than or equal to a second threshold value, establishing a case cluster by taking the unprocessed case as a core, and adding the searched cases into a candidate set of the case cluster; and marking the unprocessed case as noise when the number of the searched cases is smaller than a second threshold value.
As a preferable scheme of the knowledge graph-based emergency dispatch intelligent assistant method, the application comprises the following steps: adding each unprocessed case in the candidate set to the case cluster; searching all cases with the overall similarity smaller than a first threshold value from the case total set, and continuously adding the searched cases into the candidate set when the number of the searched cases is larger than or equal to a second threshold value; repeatedly processing the unprocessed cases in the candidate set until the unprocessed cases do not exist in the candidate set; the retrieval of the untreated cases in the total set of cases is repeated until no untreated cases exist in the total set of cases.
The present application has been developed in view of the above-described and/or existing problems in knowledge-graph-based conforming emergency intelligent assistant systems.
The problem to be solved by the present application is therefore how to provide a knowledge graph based conforming emergency intelligent assistant system.
In order to solve the technical problems, the application provides the following technical scheme: a knowledge-graph-based emergency dispatch intelligent assistant system, which comprises,
the system comprises an interaction module, an information analysis module, a business process recommendation module, a case analysis module, a power equipment fault scheduling knowledge graph and a permission judgment module;
the interaction module is used for the interaction between the user and the system, and comprises prompting user information input and result display;
the permission judging module is used for judging the user permission;
the information analysis module is used for analyzing various files input by a user, extracting specific information and transmitting the specific information to the business process recommendation module and the case analysis module;
the business process recommendation module is used for pushing and processing business process suggestions;
the case analysis module is used for acquiring a case cluster in which the fault case is located by utilizing the knowledge graph, and selecting a case with highest similarity in the case cluster in which the fault case is located for pushing.
A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method as described above when executing the computer program.
A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method as described above.
The method has the beneficial effects that the method of the intelligent assistant for emergency dispatching based on the knowledge graph is applied to power distribution network fault dispatching, the knowledge graph technology is utilized to extract and manage fault information, and the method is used for assisting dispatching personnel in fault handling, so that the emergency handling capacity and the dispatching intelligence level of a power grid can be effectively improved; according to the method, through analyzing the equipment fault information, corresponding interfaces in the poi function library can be called according to different document types to analyze, so that the equipment fault information input quality is improved, data can be continuously input, and a knowledge graph is expanded; by means of the knowledge search fault processing method, service flow suggestions and equipment fault cases are pushed and processed, a dispatcher is helped to comprehensively know the processing flow and the type of equipment faults when the power distribution network is in fault, and accuracy and prejudgement of subsequent processing are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a flowchart of a method and system for a knowledge-graph-based emergency dispatch intelligent assistant in embodiment 4.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present application is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the application. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
The first embodiment of the application provides a knowledge graph-based emergency dispatch intelligent assistant method, which comprises the following steps:
s1, inputting identity information by a user, and judging the use authority of the user;
s2, inputting equipment fault information;
s3, analyzing and structuring the equipment fault information;
s4, pushing and processing business flow suggestions by a knowledge search fault processing method;
s5, searching a fault case by knowledge, and pushing the equipment fault case;
s6, returning the specification to a data format;
s7, recommending a result to the user.
Further, in step S3, the device failure information is a device failure file; the file type is confirmed, the file content is analyzed by utilizing the corresponding interface, and specific attribute information including the type of the fault equipment, the equipment number, the occurrence place, the equipment state and the fault phenomenon is extracted.
Further, in step S4, the push processing business flow suggests that the type and state of the fault device in the extracted specific attribute information are root entity nodes, and the corresponding fault occurrence factors are recommended; scheduling rules, safety rules and expert experiences in the knowledge graph are called, and service flow suggestions are recommended according to task logic by combining the fault types and states of the power equipment.
Further, in step S5, the fault case of the pushing device is obtained from the knowledge graph, and the case cluster in which the fault case is located is selected for pushing the case with the highest similarity in the case cluster in which the fault case is located. The case clusters where the fault cases are located comprise the same equipment fault case cluster and similar equipment fault case clusters.
The case cluster generation method clusters a plurality of cases through the similarity between every two cases, and comprises the following steps:
s5.1, randomly selecting an unprocessed case from a case total set, searching all cases with the overall similarity smaller than a first threshold value in the case total set, when the number of the searched cases is larger than or equal to a second threshold value, establishing a case cluster by taking the unprocessed case as a core, and adding the searched cases into a candidate set of the case cluster; marking the unprocessed case as noise when the number of searched cases is smaller than a second threshold;
s5.2, adding each unprocessed case in the candidate set into the case cluster, searching all cases with the overall similarity smaller than a first threshold value in the case total set, and continuing to add the searched cases into the candidate set when the number of the searched cases is larger than or equal to a second threshold value;
s5.3, repeating the step 2 until no untreated case exists in the candidate set;
s5.4 repeating steps 1 to 3 until no untreated cases exist in the total set of cases.
Example 2
The second embodiment of the present application further provides a system for applying the method of the emergency dispatch intelligent assistant based on the knowledge graph, which is characterized by comprising an interaction module 100, an information analysis module 200, a business process recommendation module 300, a case analysis module 400, a power equipment fault dispatch knowledge graph 500 and a permission determination module 600;
the interaction module 100 is used for interacting with the system by a user, and comprises prompting user information input and result display;
a right determination module 600, configured to determine a user right;
the information analysis module 200 is configured to analyze various files input by a user, extract specific information, and transmit the specific information to the business process recommendation module 300, and the case analysis module 400;
the business process recommending module 300 is used for pushing and processing business process suggestions;
the case analysis module 400 is configured to obtain a case cluster in which the fault case is located by using the knowledge graph, and select a case with the highest similarity in the case cluster in which the fault case is located for pushing.
Example 3
A third embodiment of the present application, which is different from the first two embodiments, is: and also comprises
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Example 4
Referring to fig. 1, a fourth embodiment of the present application will be clearly and completely described with reference to the drawings in the embodiment of the present application.
The method and the system for the intelligent assistant for the emergency dispatch based on the knowledge graph are suitable for power distribution network faults in power faults.
The application is based on the constructed knowledge graph of the power distribution network faults, the knowledge graph of the power distribution network faults can be constructed from top to bottom or from bottom to top, and a manual construction method based on the combination of key information extraction and expert experience is selected. The system overall framework of the method for dispatching the intelligent assistant by using the power equipment fault based on the knowledge graph is shown in fig. 1, and comprises a data layer, a knowledge graph layer, a knowledge reasoning layer and a man-machine interaction layer. The data layer unifies a physical model and a knowledge model required in the fault scheduling decision of the power distribution network, and establishes a relation link among multi-source data through the knowledge graph layer to form a fault scheduling auxiliary decision knowledge graph.
When the power distribution network fault scheduling knowledge graph is constructed, the power distribution network fault scheduling knowledge graph is divided into an entity part and an event part. The entity part comprises conceptual entities such as scheduling regulations, safety regulations and the like and physical entities such as a power grid topological structure, equipment, department personnel information and the like; the event part comprises fault handling, business logic, fault plans, historical fault records and the like. The fault scheduling knowledge entity part mainly exists in files such as scheduling regulations, safety regulations and the like, and the event part exists in a power grid structure and historical data text in scheduling expert experience.
The workload of knowledge extraction in the construction of the map is simplified by extracting the technical terms. The power term extraction is performed on the scheduling procedure and the security procedure by adopting a key word extraction technology combining TF-IDF and textRank to form a conceptual entity.
The power equipment fault scheduling intelligent assistant method based on the knowledge graph comprises the following steps of:
s1, inputting identity information by a user, and judging the use authority of the user;
s2, inputting equipment fault information;
s3, analyzing and structuring the equipment fault information;
s4, pushing and processing business flow suggestions by a knowledge search fault processing method;
s5, searching a fault case by knowledge, and pushing the equipment fault case;
s6, returning the specification to a data format;
s7, recommending a result to the user.
Specifically, step S1 may perform rights management on the caller to confirm that the logged-in user has the rights to obtain the system, which is particularly important when incorporated into a part of a large system running inside the power grid.
In step S2, when the dispatcher inputs power equipment failure information through the dialogue interface, the pair of power equipment failure information is first parsed, and specific attribute information is extracted to form a structured data representation. Various types of power files may also be uploaded at the dialog interface to update the database. When various power related files are uploaded, the file type is confirmed through the file name and the suffix name, the content in the file is analyzed through the corresponding interface, and then specific attribute information including fault equipment type, equipment number, occurrence place, equipment state and fault phenomenon is extracted.
Specifically, corresponding interfaces in the poi function library are called according to different document types to analyze.
The network document name, document type and use interface are shown in the following table:
in step S4, the push processing business flow suggests that the fault type and state of the power equipment in the extracted fault information are root entity nodes, and the corresponding fault occurrence factors are recommended; scheduling rules, safety rules and expert experiences in the knowledge graph are called, and service flow suggestions are recommended according to task logic by combining the fault types and states of the power equipment.
In step S5, the knowledge searches for a fault case, and the pushing device specifically obtains a case cluster where the fault case is located in the knowledge graph, and selects a case with the highest similarity in the case cluster where the fault case is located for pushing. The case clusters where the fault cases are located comprise the same equipment fault case cluster and similar equipment fault case clusters.
The case cluster generation method clusters a plurality of cases through the similarity between every two cases, and specifically comprises the following steps:
(1) Randomly selecting an unprocessed case from a case total set, searching all cases with overall similarity smaller than a first threshold value in the case total set, when the number of the searched cases is larger than or equal to a second threshold value, establishing a case cluster by taking the unprocessed case as a core, and adding the searched cases into a candidate set of the case cluster; marking the unprocessed case as noise when the number of searched cases is smaller than a second threshold;
(2) Adding the case into the case cluster for each unprocessed case in the candidate set, searching all cases with the overall similarity smaller than a first threshold value in the case total set, and continuously adding the searched cases into the candidate set when the number of the searched cases is larger than or equal to a second threshold value;
(3) Repeating the step 2 until no unprocessed case exists in the candidate set;
(4) Steps 1 through 3 are repeated until no untreated cases exist in the total set of cases.
The overall similarity of the two cases can be obtained by the similarity of each item of specific attribute information between the two cases and the weight coefficient of each item of specific attribute information accounting for the overall specific attribute information similarity. The method comprises the following steps:
wherein simA (G i ,G j ) Overall similarity between two cases Gi, gj; w (W) k A weight coefficient for each item of specific attribute information to occupy the similarity of the overall specific attribute information; simA k (G i ,G j ) Similarity of each item of specific attribute information for case Gi and case Gj; k is 1, 2, …; n is the number of items of specific attribute information.
simA k (G i ,G j ) Respectively calculating the similarity simA of each item of specific attribute information of the case Gi and the case Gj by adopting WordNet semantic concept tree distance k (G i ,G j )；
Where depth (Gi, K) is the depth of the kth item of specific attribute information of case Gi in the semantic concept tree; depth (Gj, K) is the depth of the K-th item of specific attribute information of the case Gj in the semantic concept tree; depth (lso (Gi, K, gj, K) is the depth of the most recent common raw data of the kth item of specific attribute information of case Gi and the kth item of specific attribute information of case Gj in the semantic concept tree, and K is 1, 2, ….
Taking this embodiment as an example, the extracted specific attribute information is a faulty device type, a device number, a place where the faulty device occurs, a device state, and a fault phenomenon, and n=5.
Further, the same equipment failure case cluster and the same equipment failure case cluster are different in Wk weight coefficients. The same equipment fault case cluster mainly focuses on the fault record of the equipment history, so that the two types of specific attribute information, namely the fault equipment type and the equipment number, have higher weights, the fault equipment type is 30%, the equipment number is 60%, the equipment state and the fault phenomenon weight are 10%, and the occurrence place is 0. The cluster of similar equipment fault cases is mainly characterized in that similar faults occur in similar equipment in historic records, and the types of the fault equipment, the states of the equipment and the weights of the fault phenomena are higher, for example, the types of the fault equipment are 30%, the states of the equipment are 30%, the faults are 30%, and the rest is 10%.
The intelligent assistant method and the intelligent assistant system for the emergency dispatch based on the knowledge graph are applied to power distribution network fault dispatch, the knowledge graph technology is utilized to extract and manage fault information, and the intelligent assistant method and the intelligent assistant system are used for assisting dispatcher in fault handling, so that the emergency handling capacity and the intelligent dispatching level of a power grid can be effectively improved.
It should be noted that the above embodiments are only for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present application may be modified or substituted without departing from the spirit and scope of the technical solution of the present application, which is intended to be covered in the scope of the claims of the present application.
Claims (10)
1. The intelligent assistant method for emergency dispatch based on the knowledge graph is characterized by comprising the following steps of: the method comprises the following steps:
the user inputs identity information, judges the user's use authority and inputs equipment fault information;
analyzing and structuring the equipment fault information, searching a fault processing method by knowledge, and pushing a business flow proposal to be processed;
knowledge searches for fault cases, pushes equipment fault cases, returns data formats in a standard, and recommends results to users.
2. The knowledge-graph-based emergency dispatch intelligent assistant method of claim 1, wherein: the equipment fault information is an equipment fault file; the file type is confirmed, the file content is analyzed by utilizing the corresponding interface, and specific attribute information including the type of the fault equipment, the equipment number, the occurrence place, the equipment state and the fault phenomenon is extracted.
3. The knowledge-graph-based emergency dispatch intelligent assistant method of claim 1, wherein: the push processing business flow proposal recommends fault occurrence factors corresponding to the fault equipment type and the state in the extracted specific attribute information as root entity nodes; scheduling rules, safety rules and expert experiences in the knowledge graph are called, and service flow suggestions are recommended according to task logic by combining the fault types and states of the power equipment.
4. The knowledge-graph-based emergency dispatch intelligent assistant method of claim 1, wherein: the fault cases of the pushing equipment are obtained from a knowledge graph, and the case cluster in which the fault cases are located is selected for pushing the case with highest similarity; the case clusters where the fault cases are located comprise the same equipment fault case cluster and similar equipment fault case clusters.
5. The knowledge-graph-based conforming emergency intelligent assistant method of claim 1, wherein:
wherein simA (G i ,G j ) Overall similarity between two cases Gi, gj; w (W) k A weight coefficient for each item of specific attribute information to occupy the similarity of the overall specific attribute information; simA k (G i ,G j ) Similarity of each item of specific attribute information for case Gi and case Gj; k is 1, 2, …; n is the number of items of specific attribute information;
simA k (G i ,G j ) Respectively calculating the similarity simA of each item of specific attribute information of the case Gi and the case Gj by adopting WordNet semantic concept tree distance k (G i ,G j )；
Where depth (Gi, K) is the depth of the kth item of specific attribute information of case Gi in the semantic concept tree; depth (Gj, K) is the depth of the K-th item of specific attribute information of the case Gj in the semantic concept tree; depth (lso (Gi, K, gj, K) is the depth of the most recent common raw data of the kth item of specific attribute information of case Gi and the kth item of specific attribute information of case Gj in the semantic concept tree, and K is 1, 2, ….
6. The knowledge-graph-based conforming emergency intelligent assistant method of claim 4, wherein: randomly selecting an unprocessed case from a case total set, searching all cases with overall similarity smaller than a first threshold value in the case total set, when the number of the searched cases is larger than or equal to a second threshold value, establishing a case cluster by taking the unprocessed case as a core, and adding the searched cases into a candidate set of the case cluster; and marking the unprocessed case as noise when the number of the searched cases is smaller than a second threshold value.
7. The knowledge-graph-based conforming emergency intelligent assistant method of claim 4, wherein: adding each unprocessed case in the candidate set to the case cluster; searching all cases with the overall similarity smaller than a first threshold value from the case total set, and continuously adding the searched cases into the candidate set when the number of the searched cases is larger than or equal to a second threshold value; repeatedly processing the unprocessed cases in the candidate set until the unprocessed cases do not exist in the candidate set; the retrieval of the untreated cases in the total set of cases is repeated until no untreated cases exist in the total set of cases.
8. Emergency dispatch intelligent assistant system based on knowledge graph, its characterized in that: the system comprises an interaction module (100), an information analysis module (200), a business process recommendation module (300), a case analysis module (400), a power equipment fault scheduling knowledge graph (500) and a permission judgment module (600);
the interaction module (100) is used for the user to interact with the system, and comprises prompting user information input and result display;
a rights determination module (600) for determining a user right;
the information analysis module (200) is used for analyzing various files input by a user, extracting specific information and transmitting the specific information to the business process recommendation module (300), and the case analysis module (400);
the business process recommending module (300) is used for pushing and processing business process suggestions;
and the case analysis module (400) is used for acquiring a case cluster in which the fault case is located by utilizing the knowledge graph, and selecting a case with highest similarity in the case cluster in which the fault case is located for pushing.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that: the processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program implementing the steps of the method of any of claims 1 to 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310409248.2A CN116662580A (en) | 2023-04-17 | 2023-04-17 | Emergency scheduling intelligent assistant method and system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310409248.2A CN116662580A (en) | 2023-04-17 | 2023-04-17 | Emergency scheduling intelligent assistant method and system based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116662580A true CN116662580A (en) | 2023-08-29 |
Family
ID=87725026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310409248.2A Pending CN116662580A (en) | 2023-04-17 | 2023-04-17 | Emergency scheduling intelligent assistant method and system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116662580A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117150042A (en) * | 2023-09-01 | 2023-12-01 | 海通证券股份有限公司 | Method, device, equipment and medium for recommending emergency plans based on knowledge graph |
-
2023
- 2023-04-17 CN CN202310409248.2A patent/CN116662580A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117150042A (en) * | 2023-09-01 | 2023-12-01 | 海通证券股份有限公司 | Method, device, equipment and medium for recommending emergency plans based on knowledge graph |
| CN117150042B (en) * | 2023-09-01 | 2024-04-16 | 海通证券股份有限公司 | Method, device, equipment and medium for recommending emergency plans based on knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428044B (en) | Method, device, equipment and storage medium for acquiring supervision and identification results in multiple modes | |
| US9720944B2 (en) | Method for facet searching and search suggestions | |
| US8407253B2 (en) | Apparatus and method for knowledge graph stabilization | |
| US7734556B2 (en) | Method and system for discovering knowledge from text documents using associating between concepts and sub-concepts | |
| CN112800170A (en) | Question matching method and device and question reply method and device | |
| CN110321420A (en) | The intelligent Answer System generated based on question sentence | |
| CN111209472A (en) | Railway accident fault association and accident fault reason analysis method and system | |
| CN116662580A (en) | Emergency scheduling intelligent assistant method and system based on knowledge graph | |
| Portugal et al. | Nfrfinder: a knowledge based strategy for mining non-functional requirements | |
| CN112100398A (en) | Patent blank prediction method and system | |
| CN116680386A (en) | Answer prediction method and device based on multi-round dialogue, equipment and storage medium | |
| Ribeiro et al. | Discovering IMRaD structure with different classifiers | |
| CN114880635A (en) | User security level identification method, system, electronic device and medium of model integrated with lifting tree construction | |
| CN111914859A (en) | Service multiplexing method, computing device and computer readable storage medium | |
| CN117609479A (en) | Model processing method, device, equipment, medium and product | |
| KR102113773B1 (en) | Method and apparatus for generating rules for conversation recognition and reasoning based on the rules | |
| CN111160028A (en) | Method, device, storage medium and equipment for judging semantic similarity of two texts | |
| Brinkmann et al. | Product Attribute Value Extraction using Large Language Models | |
| CN112287663B (en) | Text parsing method, equipment, terminal and storage medium | |
| CN115099344A (en) | Model training method and device, user portrait generation method and device, and equipment | |
| KR102106250B1 (en) | An apparatus for rule-based user inference reasoning for conversation awareness | |
| CN114862006A (en) | Social work service scheme automatic generation method and device based on artificial intelligence | |
| CN111199170B (en) | Formula file identification method and device, electronic equipment and storage medium | |
| CN113836261A (en) | Patent text novelty/creativity prediction method and device | |
| KR102078541B1 (en) | Issue interest based news value evaluation apparatus and method, storage media storing the same |
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 |