Accident emergency plan generation method and system based on knowledge graph

Abstract

The invention relates to the technical field of emergency management, and discloses a knowledge graph-based accident emergency plan generation method, which comprises the following steps of: calculating a betweenness centrality value of each original node in a basic emergency accident knowledge graph, and screening out isolated nodes according to the betweenness centrality value; traversing the basic emergency accident knowledge graph, acquiring original nodes which have no direct connection original edges with the isolated nodes, marking the original nodes as candidate nodes, and deducing whether a new potential entity relationship exists or not; when it is judged that the new relationship between the potential entities exists, the new relationship between the potential entities is mined, and a new relationship edge is created and added for the basic emergency accident knowledge graph according to the new relationship between the potential entities, so that the emergency accident knowledge graph is improved; the accident type or the accident condition is input into the improved emergency accident knowledge graph, and an emergency plan is automatically generated; according to the invention, the structure of the graph can be enriched, the overall integrity of the emergency accident knowledge graph is improved, and the generation accuracy of the emergency plan is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of emergency management technology, and more specifically, to a method for generating an accident emergency plan based on a knowledge graph. Background Art

[0002] With the continuous advancement of industrialization, the types of accidents involved in the production process are becoming increasingly complex. Traditional emergency plan generation methods are usually based on fixed rules or templates, lack flexibility and adaptability, and often fail to fully utilize knowledge from multiple data sources; knowledge graphs, as a structured knowledge representation method, can effectively organize and associate various types of accidents, hazards, emergency measures and other information, providing a theoretical basis for the formulation of accurate and dynamic accident emergency plans; however, the existing knowledge graph-based emergency plan generation methods still have the following problems: 1) Insufficient mining of node relationships in the graph, and failure to fully identify new potential relationships between entities; 2) Unable to dynamically adapt to changes in actual conditions, resulting in the lack of flexibility and real-time performance of the generated emergency plans.

[0003] Therefore, the present invention proposes a method and system for generating accident emergency plans based on knowledge graphs, aiming to improve the accuracy and real-time performance of emergency plans by mining potential knowledge relationships in graphs and dynamically optimizing graph structures. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for generating an accident emergency plan based on a knowledge graph.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for generating an accident emergency plan based on a knowledge graph, the method comprising:

[0007] S101: Calculate the betweenness centrality value of each original node in the basic emergency accident knowledge graph, and filter out isolated nodes according to the betweenness centrality value;

[0008] S102: traverse the basic emergency accident knowledge graph, obtain the original nodes that have no direct original edges with the isolated nodes, mark the original nodes that have no direct original edges with the isolated nodes as candidate nodes, and infer whether there is a new potential entity relationship between the isolated nodes and the candidate nodes;

[0009] S103: when it is determined that there is a new potential entity relationship, the new potential entity relationship between the isolated node and the candidate node is mined, and a new relationship edge is created and added to the basic emergency accident knowledge graph according to the new potential entity relationship between the isolated node and the candidate node, so as to form an optimized improved emergency accident knowledge graph;

[0010] S104: Obtain the accident type or accident situation of the current emergency event, input the accident type or accident situation into the optimized improved emergency accident knowledge graph, and automatically generate an emergency plan for the current emergency event.

[0011] Furthermore, the generation logic of the basic emergency accident knowledge graph is as follows:

[0012] Extracting knowledge data from emergency accident data sources, wherein the knowledge data includes entities, relationships between entities, and attributes;

[0013] Construct entity-relationship-attribute triples based on knowledge data;

[0014] The entities in the triples are taken as original nodes, and the relationships between entities are taken as original edges between original nodes to form a basic emergency accident knowledge graph.

[0015] Furthermore, the calculation of the betweenness centrality value of each original node in the basic emergency accident knowledge graph includes:

[0016] Traverse each pair of original nodes u and original nodes v in the basic emergency accident knowledge graph, and calculate all shortest path sets between them, wherein the shortest path set includes multiple shortest paths;

[0017] For each shortest path, count the number of times each original node appears in all shortest paths between node pairs u and v;

[0018] Obtain the number of all shortest paths between node u and node v according to the shortest path set, substitute the number of all shortest paths and the number of times each original node appears in all shortest paths between node pair u and v into the pre-built mathematical calculation model, and obtain the betweenness centrality value of each original node;

[0019] Wherein, the pre-built mathematical calculation model expression is:

[0020] ;

[0021] Normalized betweenness centrality:

[0022] ;

[0023] Where: is the betweenness centrality value of the w-th original node, is the normalized betweenness centrality value of the w-th original node, is the number of times the betweenness centrality value of the wth original node appears in the shortest path from the original node u to the original node v, is the number of all shortest paths between the original node u and the original node v, is the total number of original nodes in the graph.

[0024] Furthermore, the step of filtering out isolated nodes according to the betweenness centrality value includes:

[0025] Will The preset betweenness centrality threshold is compared;

[0026] like If it is less than or equal to the preset betweenness centrality threshold, the corresponding original node is determined to be an isolated node;

[0027] like If it is greater than the preset betweenness centrality threshold, the corresponding original node is determined to be a non-isolated node.

[0028] Furthermore, the inferring whether there is a new potential entity relationship between the isolated node and the candidate node includes:

[0029] Extract the neighbor node set of the isolated node in the basic emergency accident knowledge graph and mark it as the first neighbor node set;

[0030] Obtain the neighbor node set of the candidate node in the basic emergency accident knowledge graph and mark it as the second neighbor node set;

[0031] Calculate the Jaccard similarity between the first neighbor node set and the second neighbor node set;

[0032] The Jaccard similarity is compared with the preset Jaccard similarity threshold. If the Jaccard similarity is greater than or equal to the preset Jaccard similarity threshold, it is inferred that there is a new potential entity relationship between the isolated node and the candidate node. If the Jaccard similarity is less than the preset Jaccard similarity threshold, it is inferred that there is no new potential entity relationship between the isolated node and the candidate node.

[0033] Furthermore, mining out new potential entity relationships between isolated nodes and candidate nodes includes:

[0034] Locate the corpus sentences where isolated nodes and candidate nodes co-occur in the data source;

[0035] After word segmentation, the dependency tree is constructed to obtain the dependency tree of isolated nodes and candidate nodes.

[0036] Obtain the shortest dependency path of the isolated node and the candidate node in the dependency tree, obtain all predicate verbs in the dependency path, and respectively parse the dependency relationship of each predicate verb with respect to the isolated node and the candidate node, and obtain the weight of each dependency relationship to obtain multiple weights;

[0037] The multiple weights are sorted from large to small according to the numerical values, and the predicate verb corresponding to the first weight is used as the new potential entity relationship between the isolated node and the candidate node.

[0038] A knowledge graph-based accident emergency plan generation system is implemented based on the above-mentioned knowledge graph-based accident emergency plan generation method, and the system includes:

[0039] A screening module is used to obtain a pre-built basic emergency accident knowledge graph, calculate the betweenness centrality value of each original node in the basic emergency accident knowledge graph, and screen out isolated nodes according to the betweenness centrality value;

[0040] The inference module is used to traverse the basic emergency accident knowledge graph, obtain the original nodes that have no direct original edges with the isolated nodes, mark the original nodes that have no direct original edges with the isolated nodes as candidate nodes, and infer whether there is a new potential entity relationship between the isolated nodes and the candidate nodes;

[0041] The optimization module is used to mine the new potential entity relationship between the isolated node and the candidate node when it is determined that there is a new potential entity relationship, and to create and add new relationship edges to the basic emergency accident knowledge graph based on the new potential entity relationship between the isolated node and the candidate node, so as to form an optimized improved emergency accident knowledge graph;

[0042] The generation module is used to obtain the accident type or accident situation of the current emergency event, input the accident type or accident situation into the optimized improved emergency accident knowledge graph, and automatically generate an emergency plan for the current emergency event.

[0043] An electronic device comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the method for generating an accident emergency plan based on a knowledge graph as described above is implemented.

[0044] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements any of the above-mentioned methods for generating an accident emergency plan based on a knowledge graph.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows: by combining the knowledge graph technology, the present invention can effectively improve the automation, accuracy and real-time performance of the generation of accident emergency plans; by optimizing the accident knowledge graph, the integrity of the graph and the coverage of the emergency plan are improved, so that practical problems can be quickly and accurately identified and solved during the emergency response process; in addition, the method of the present invention has strong adaptability and can perform intelligent processing on accidents of different types and scales, greatly improving the emergency management level of high-risk industries. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of a method for generating an accident emergency plan based on a knowledge graph provided by the present invention;

[0047] Figure 2 A module diagram of an accident emergency plan generation system based on a knowledge graph provided by the present invention;

[0048] Figure 3 The present invention provides a schematic structural diagram of an electronic device. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Example 1

[0051] See also Figure 1 As shown, this embodiment discloses a method for generating an accident emergency plan based on a knowledge graph, and the method includes:

[0052] S101: Calculate the betweenness centrality value of each original node in the basic emergency accident knowledge graph, and filter out isolated nodes according to the betweenness centrality value;

[0053] In practice, the generation logic of the basic emergency accident knowledge graph is as follows:

[0054] Extracting knowledge data from emergency accident data sources, wherein the knowledge data includes entities, relationships between entities, and attributes;

[0055] It should be noted that: the emergency accident data source includes but is not limited to data documents in paper or electronic document form, such as: emergency manual, etc., wherein the data source in paper document form is manually entered by technicians into electronic document form;

[0056] In a specific implementation, the extracting of knowledge data from the emergency accident data source includes: calling predefined rules, and extracting entities, relationships between entities, and attributes from the data source according to the predefined rules (such as regular expressions);

[0057] It should be understood that the predefined rules limit and define the extraction rules of entities, relationships between entities, and attributes. For example, in the predefined rules, the word "lead-acid battery" is used as an entity, and there is a sentence in the data source that says "In the case of a lead-acid battery leakage accident, emergency personnel need to wear acid-proof gloves, goggles, acid-proof work clothes and masks, etc.", then the "lead-acid battery" in the corpus is extracted as an entity. Similarly, the extraction logic of the relationship and attributes between entities is also the same, and no further elaboration is made on this.

[0058] It should also be noted that: before extracting the knowledge data from the emergency accident data source, the data source data will be preprocessed, and the preprocessing operation includes but is not limited to word segmentation, and the removal of meaningless words and symbols, such as repeated words, stop words, onomatopoeia, onomatopoeia, "," "!" and "."; the word segmentation can be implemented by applying natural language processing tools, and the natural language processing tools include but are not limited to Jieba word segmentation, etc.;

[0059] Construct entity-relationship-attribute triples based on knowledge data;

[0060] The entities in the triples are taken as original nodes, and the relationships between entities are taken as original edges between original nodes to form a basic emergency accident knowledge graph;

[0061] It should be understood that each original node in the basic emergency accident knowledge graph represents an entity (such as accident type, emergency resources, operation steps, etc.), and the original edges between nodes represent the relationship between nodes (entities) (such as causal relationship, operation dependency, etc.);

[0062] In implementation, the calculation of the betweenness centrality value of each original node in the basic emergency accident knowledge graph includes:

[0063] Traverse each pair of original nodes u and original nodes v in the basic emergency accident knowledge graph, and calculate all shortest path sets between them, wherein the shortest path set includes multiple shortest paths;

[0064] It should be noted that the shortest path refers to the path between two nodes in a graph that is connected by the least number of edges. In a graph, the shortest path can be calculated using a variety of algorithms, including but not limited to the Dijkstra algorithm, the Floyd-Warshall algorithm, or the breadth-first search (BFS) algorithm.

[0065] For each shortest path, count the number of times each original node appears in all shortest paths between node pairs u and v;

[0066] Obtain the number of all shortest paths between node u and node v according to the shortest path set, substitute the number of all shortest paths and the number of times each original node appears in all shortest paths between node pair u and v into the pre-built mathematical calculation model, and obtain the betweenness centrality value of each original node;

[0067] Wherein, the pre-built mathematical calculation model expression is:

[0068] ;

[0069] Normalized betweenness centrality:

[0070] ;

[0071] Where: is the betweenness centrality value of the w-th original node, is the normalized betweenness centrality value of the w-th original node, is the number of times the betweenness centrality value of the wth original node appears in the shortest path from the original node u to the original node v, is the number of all shortest paths between the original node u and the original node v, is the total number of original nodes in the graph;

[0072] In implementation, the step of screening out isolated nodes according to the betweenness centrality value includes:

[0073] Will Compare with the preset betweenness centrality threshold;

[0074] like If it is less than or equal to the preset betweenness centrality threshold, the corresponding original node is determined to be an isolated node;

[0075] like If it is greater than the preset betweenness centrality threshold, the corresponding original node is determined to be a non-isolated node;

[0076] It should be noted that: The larger the value is, the more the original node acts as a bridge or intermediary in the shortest paths, connecting nodes in different parts of the graph, and is usually a key node in the graph. The smaller it is, the weaker the intermediary role of the corresponding original node in the network, or the smaller the role it plays in the path of information transmission between node pairs and the more isolated it is.

[0077] S102: traverse the basic emergency accident knowledge graph, obtain the original nodes that have no direct original edges with the isolated nodes, mark the original nodes that have no direct original edges with the isolated nodes as candidate nodes, and infer whether there is a new potential entity relationship between the isolated nodes and the candidate nodes;

[0078] For example, assuming that there is an isolated node and multiple original nodes, wherein the isolated node is “acid-proof gloves”, and the multiple original nodes are “goggles” and “acid-proof work clothes”, etc., and there is no directly connected edge between “acid-proof gloves” and “goggles”, while there is a directly connected edge between “acid-proof gloves” and “acid-proof work clothes”, then “goggles” is marked as an original node that is not directly connected to the isolated node (“acid-proof gloves”);

[0079] In implementation, the inferring whether there is a new potential entity relationship between the isolated node and the candidate node includes:

[0080] Extract the neighbor node set of the isolated node in the basic emergency accident knowledge graph and mark it as the first neighbor node set;

[0081] Obtain the neighbor node set of the candidate node in the basic emergency accident knowledge graph and mark it as the second neighbor node set;

[0082] Calculate the Jaccard similarity between the first neighbor node set and the second neighbor node set;

[0083] The Jaccard similarity is compared with the preset Jaccard similarity threshold. If the Jaccard similarity is greater than or equal to the preset Jaccard similarity threshold, it is inferred that there is a new potential entity relationship between the isolated node and the candidate node. If the Jaccard similarity is less than the preset Jaccard similarity threshold, it is inferred that there is no new potential entity relationship between the isolated node and the candidate node.

[0084] S103: when it is determined that there is a new potential entity relationship, the new potential entity relationship between the isolated node and the candidate node is mined, and a new relationship edge is created and added to the basic emergency accident knowledge graph according to the new potential entity relationship between the isolated node and the candidate node, so as to form an optimized improved emergency accident knowledge graph;

[0085] In implementation, mining new potential entity relationships between isolated nodes and candidate nodes includes:

[0086] Locate the corpus sentences where isolated nodes and candidate nodes co-occur in the data source;

[0087] After word segmentation, the dependency tree is constructed to obtain the dependency tree of isolated nodes and candidate nodes.

[0088] Obtain the shortest dependency path of the isolated node and the candidate node in the dependency tree, obtain all predicate verbs in the dependency path, and respectively parse the dependency relationship of each predicate verb with respect to the isolated node and the candidate node, and obtain the weight of each dependency relationship to obtain multiple weights;

[0089] It should be understood that: the construction of the dependency tree, the generation of the shortest dependency path and the parsing of the dependency relationship are implemented based on the existing dependency syntax parsing tool, and the dependency syntax parsing tool includes spaCy; wherein the dependency relationship includes at least a subject relationship, a verb-object relationship and a conditional modification relationship, wherein the weight of the subject relationship is 0.6, the weight of the conditional modification relationship is 0.8, and the weight of the verb-object relationship is 1.0;

[0090] The weights are sorted from large to small according to the numerical values, and the predicate verb corresponding to the first weight is used as the new potential entity relationship between the isolated node and the candidate node;

[0091] It should be understood that: after completing the structural optimization of the basic emergency accident knowledge graph, the original knowledge graph after structural optimization needs to be imported into a preset graph database, which is achieved by using the graph database API or batch import tool; the graph database can be selected in advance by the technicians according to the data scale, complexity, and performance requirements, and the graph database is not limited to a specific one of Neo4j, Amazon Neptune or ArangoDB, etc.;

[0092] S104: Obtain the accident type or accident situation of the current emergency event, input the accident type or accident situation into the optimized improved emergency accident knowledge graph, and automatically generate an emergency plan for the current emergency event;

[0093] It should be noted that the accident type or accident situation of the current emergency event is specifically input in the form of keywords. For example, the user enters the keyword "lead-acid battery leakage" for the accident type according to the current emergency event, and the emergency plan outputs the corresponding emergency resources, operating steps, etc. For example, according to "lead-acid battery leakage", the output emergency resources include acid-proof gloves, goggles, acid-proof work clothes and masks, etc.

[0094] Example 2

[0095] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a system for generating an accident emergency plan based on a knowledge graph. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The system includes:

[0096] A screening module 210 is used to calculate the betweenness centrality value of each original node in the basic emergency accident knowledge graph, and screen out isolated nodes according to the betweenness centrality value;

[0097] The inference module 220 is used to traverse the basic emergency accident knowledge graph, obtain the original nodes that have no direct original edges with the isolated nodes, mark the original nodes that have no direct original edges with the isolated nodes as candidate nodes, and infer whether there is a new potential entity relationship between the isolated nodes and the candidate nodes;

[0098] The optimization module 230 is used to mine the new potential entity relationship between the isolated node and the candidate node when it is determined that there is a new potential entity relationship, and create and add new relationship edges to the basic emergency accident knowledge graph based on the new potential entity relationship between the isolated node and the candidate node to form an optimized improved emergency accident knowledge graph;

[0099] A generation module 240 is used to obtain the accident type or accident situation of the current emergency event, input the accident type or accident situation into the optimized improved emergency accident knowledge graph, and automatically generate an emergency plan for the current emergency event;

[0100] Example 3

[0101] See also Figure 3 As shown, this embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements any one of the knowledge graph-based accident emergency plan generation methods provided by the above methods.

[0102] Since the electronic device introduced in this embodiment is an electronic device used to implement a method for generating an accident emergency plan based on a knowledge graph in an embodiment of the present invention, based on the method for generating an accident emergency plan based on a knowledge graph introduced in an embodiment of the present invention, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present invention will not be described in detail here. As long as a person skilled in the art implements an electronic device used by a method for generating an accident emergency plan based on a knowledge graph in an embodiment of the present invention, it belongs to the scope of protection of the present invention.

[0103] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0104] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0105] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0106] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0107] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0110] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0111] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating an accident emergency plan based on a knowledge graph, characterized in that: The method comprises: S101: Calculate the betweenness centrality value of each original node in the basic emergency accident knowledge graph, and filter out isolated nodes according to the betweenness centrality value; S102: traverse the basic emergency accident knowledge graph, obtain the original nodes that have no direct original edges with the isolated nodes, mark the original nodes that have no direct original edges with the isolated nodes as candidate nodes, and infer whether there is a new potential entity relationship between the isolated nodes and the candidate nodes; S103: when it is determined that there is a new potential entity relationship, the new potential entity relationship between the isolated node and the candidate node is mined, and a new relationship edge is created and added to the basic emergency accident knowledge graph according to the new potential entity relationship between the isolated node and the candidate node, so as to form an optimized improved emergency accident knowledge graph; S104: Obtain the accident type or accident situation of the current emergency event, input the accident type or accident situation into the optimized improved emergency accident knowledge graph, and automatically generate an emergency plan for the current emergency event.

2. According to the method for generating an accident emergency plan based on a knowledge graph according to claim 1, it is characterized in that: The generation logic of the basic emergency accident knowledge graph is as follows: Extracting knowledge data from emergency accident data sources, wherein the knowledge data includes entities, relationships between entities, and attributes; Construct entity-relationship-attribute triples based on knowledge data; The entities in the triples are taken as original nodes, and the relationships between entities are taken as original edges between original nodes to form a basic emergency accident knowledge graph.

3. According to the method for generating an accident emergency plan based on a knowledge graph according to claim 2, it is characterized in that: The calculation of the betweenness centrality value of each original node in the basic emergency accident knowledge graph includes: Traverse each pair of original nodes u and original nodes v in the basic emergency accident knowledge graph, and calculate all shortest path sets between them, wherein the shortest path set includes multiple shortest paths; For each shortest path, count the number of times each original node appears in all shortest paths between node pairs u and v; Obtain the number of all shortest paths between node u and node v according to the shortest path set, substitute the number of all shortest paths and the number of times each original node appears in all shortest paths between node pair u and v into the pre-built mathematical calculation model, and obtain the betweenness centrality value of each original node; Wherein, the pre-built mathematical calculation model expression is: ； Normalized betweenness centrality: ； Where: is the betweenness centrality value of the w-th original node, is the normalized betweenness centrality value of the w-th original node, is the number of times the betweenness centrality value of the wth original node appears in the shortest path from the original node u to the original node v, is the number of all shortest paths between the original node u and the original node v, is the total number of original nodes in the graph.

4. The method for generating an accident emergency plan based on a knowledge graph according to claim 3 is characterized in that: The step of filtering out isolated nodes according to the betweenness centrality value includes: Will Compare with the preset betweenness centrality threshold; like If it is less than or equal to the preset betweenness centrality threshold, the corresponding original node is determined to be an isolated node; like If it is greater than the preset betweenness centrality threshold, the corresponding original node is determined to be a non-isolated node.

5. The method for generating an accident emergency plan based on a knowledge graph according to claim 4, characterized in that: The inferring whether there is a new potential entity relationship between the isolated node and the candidate node includes: Extract the neighbor node set of the isolated node in the basic emergency accident knowledge graph and mark it as the first neighbor node set; Obtain the neighbor node set of the candidate node in the basic emergency accident knowledge graph and mark it as the second neighbor node set; Calculate the Jaccard similarity between the first neighbor node set and the second neighbor node set; The Jaccard similarity is compared with the preset Jaccard similarity threshold. If the Jaccard similarity is greater than or equal to the preset Jaccard similarity threshold, it is inferred that there is a new potential entity relationship between the isolated node and the candidate node. If the Jaccard similarity is less than the preset Jaccard similarity threshold, it is inferred that there is no new potential entity relationship between the isolated node and the candidate node.

6. The method for generating an accident emergency plan based on a knowledge graph according to claim 5, characterized in that: The mining of new potential entity relationships between isolated nodes and candidate nodes includes: Locate the corpus sentences where isolated nodes and candidate nodes co-occur in the data source; After word segmentation, the dependency tree is constructed to obtain the dependency tree of isolated nodes and candidate nodes. Obtain the shortest dependency path of the isolated node and the candidate node in the dependency tree, obtain all predicate verbs in the dependency path, and respectively parse the dependency relationship of each predicate verb with respect to the isolated node and the candidate node, and obtain the weight of each dependency relationship to obtain multiple weights; The multiple weights are sorted from large to small according to the numerical values, and the predicate verb corresponding to the first weight is used as the new potential entity relationship between the isolated node and the candidate node.

7. An accident emergency plan generation system based on knowledge graph, characterized in that: The system is implemented based on the method for generating an accident emergency plan based on a knowledge graph according to any one of claims 1 to 6, and the system comprises: A screening module is used to obtain a pre-built basic emergency accident knowledge graph, calculate the betweenness centrality value of each original node in the basic emergency accident knowledge graph, and screen out isolated nodes according to the betweenness centrality value; The inference module is used to traverse the basic emergency accident knowledge graph, obtain the original nodes that have no direct original edges with the isolated nodes, mark the original nodes that have no direct original edges with the isolated nodes as candidate nodes, and infer whether there is a new potential entity relationship between the isolated nodes and the candidate nodes; The optimization module is used to mine the new potential entity relationship between the isolated node and the candidate node when it is determined that there is a new potential entity relationship, and to create and add new relationship edges to the basic emergency accident knowledge graph based on the new potential entity relationship between the isolated node and the candidate node, so as to form an optimized improved emergency accident knowledge graph; The generation module is used to obtain the accident type or accident situation of the current emergency event, input the accident type or accident situation into the optimized improved emergency accident knowledge graph, and automatically generate an emergency plan for the current emergency event.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, it implements the accident emergency plan generation method based on the knowledge graph as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed, implements the method for generating an accident emergency plan based on a knowledge graph as described in any one of claims 1 to 6.

Images