Waterlogging scheduling method and device based on knowledge graph, equipment and storage medium

Abstract

The invention provides a waterlogging scheduling method and device based on a knowledge graph, equipment and a storage medium, and relates to the technical field of urban disaster monitoring. The method comprises the steps that waterlogging data sources are obtained, and the waterlogging data sources comprise a plurality of data sources; constructing an ontology library corresponding to each data source according to the plurality of data sources, and performing knowledge filling on each ontology library to obtain a knowledge graph corresponding to each ontology library; performing knowledge fusion on the knowledge maps corresponding to the ontology libraries to obtain a waterlogging scheduling knowledge map; and performing knowledge retrieval or knowledge reasoning on the waterlogging scheduling knowledge graph to obtain a waterlogging target scheduling scheme. According to the method provided by the invention, the problem of how to quickly and accurately identify and predict the waterlogging area and timely determine the waterlogging scheduling strategy is solved.

Description

Technical Field

[0001] The present application relates to the technical field of urban disaster monitoring, and in particular to a method, device, equipment and storage medium for urban flood control based on a knowledge graph. Background Art

[0002] Under the dual influence of global climate change and rapid urbanization, extreme rainstorms occur frequently, and urban waterlogging disasters show a significant trend of intensification, posing a serious threat to the sustainable development of cities and the safety of people's lives and property. Urban waterlogging dispatch is particularly important. Urban waterlogging dispatch usually refers to a series of prevention and response measures taken when a city encounters heavy rainfall or other situations that cause excessive waterlogging, in order to reduce the impact of waterlogging on urban operations and residents' lives.

[0003] Most of the existing urban waterlogging dispatching is calculated through models, and as the simulation accuracy improves, the requirements for model operation time and computing power also increase accordingly. However, the disaster situation may change rapidly and the corresponding dispatching measures should also change accordingly. Therefore, it is particularly important to quickly and accurately identify and predict urban waterlogging areas, and take corresponding measures for flood control and drainage according to the predicted waterlogging areas in a timely manner.

[0004] How to quickly and accurately identify and predict waterlogging areas and determine waterlogging dispatching strategies in a timely manner is a problem that the present invention urgently needs to solve. Summary of the invention

[0005] The present application provides a waterlogging scheduling method, device, equipment and storage medium based on a knowledge graph to solve the problem of how to quickly and accurately identify and predict waterlogging areas and promptly determine waterlogging scheduling strategies.

[0006] In a first aspect, the present application provides a method for flood control scheduling based on a knowledge graph, the method comprising:

[0007] Acquire an internal waterlogging data source, wherein the internal waterlogging data source includes multiple data sources;

[0008] Based on multiple data sources, construct an ontology library corresponding to each data source, and fill each ontology library with knowledge to obtain a knowledge graph corresponding to each ontology library;

[0009] The knowledge graphs corresponding to each ontology library are integrated to obtain the waterlogging dispatching knowledge graph; and knowledge retrieval or knowledge reasoning is performed on the waterlogging dispatching knowledge graph to obtain the waterlogging target dispatching plan.

[0010] In a possible design, each ontology library is filled with knowledge to obtain the knowledge graph corresponding to each ontology library, including:

[0011] Through machine learning methods, knowledge is extracted from the data sources corresponding to each ontology library, and multiple formal triples corresponding to each ontology library are obtained; each formal triple is used to indicate the knowledge information of the corresponding entity;

[0012] Through the pre-stored graph database, the knowledge of multiple formal triples corresponding to each ontology library is stored to obtain the knowledge graph corresponding to each ontology library; wherein each knowledge graph includes: the corresponding ontology library, and the corresponding multiple formal triples.

[0013] In a possible design, the multiple data sources include a first data source, a second data source, and a third data source; wherein the first data source includes data of the underlying surface of the urban landmark and the drainage system; the second data source includes data of historical waterlogging scheduling plans; the third data source includes data of urban waterlogging scheduling process detection and precipitation process;

[0014] Based on multiple data sources, construct an ontology library corresponding to each data source, including:

[0015] According to multiple data sources, object data corresponding to each data source are obtained; wherein the object data includes a first object corresponding to the first data source, a second object corresponding to the second data source, and a third object corresponding to the third data source; wherein the first object includes objects of surface units, pipe networks, rivers and lakes, rainwater pumping stations, and storage tanks; the second object includes objects of drainage facilities, as well as control objects, enabling condition objects, scheduling operation mode objects, and scheduling operation effect objects of drainage settings; the third object includes objects of precipitation processes, water level objects and flow objects of typical points of the surface, pipe networks, and rivers and lakes;

[0016] Determine the multiple objects of the first data source, the second data source, and the third data source as their respective entity nodes, and determine the relationships among the multiple objects of the first data source, the second data source, and the third data source as their respective node relationships; the multiple entity nodes include a first entity node corresponding to the first data source, a second entity node corresponding to the second data source, and a third entity node corresponding to the third data source; the multiple node relationships include a first node relationship corresponding to the first data source, a second node relationship corresponding to the second data source, and a third node relationship corresponding to the third data source;

[0017] According to the first entity node and the first node relationship, a first ontology library corresponding to the first data source is constructed, according to the second entity node and the second node relationship, a second ontology library corresponding to the second data source is constructed, and according to the third entity node and the third node relationship, a third ontology library corresponding to the third data source is constructed.

[0018] In a possible design, the first node relationship includes the flow direction between multiple surface units, the topological relationship of the pipe network, the hydraulic connection between rivers and lakes, the positional relationship between the rainwater pumping station, the regulating reservoir and multiple surface units, and the hydraulic connection between the rainwater pumping station and the rivers and lakes;

[0019] Constructing a first ontology library corresponding to the first data source according to the first entity node and the first node relationship, including:

[0020] Acquire first data, wherein the first data includes data of surface units, pipe networks, rivers and lakes, rainwater pumping stations, and storage tanks;

[0021] Screening the first data to obtain characteristic parameters corresponding to each data in the first data;

[0022] Determine a plurality of characteristic parameters in the first data as node attributes of the first entity node;

[0023] A first ontology library is constructed according to the first entity node, the first node relationship, and the node attribute of the first entity node.

[0024] In a possible design, the knowledge graph corresponding to each ontology library includes: a first knowledge graph corresponding to the first ontology library, a second knowledge graph corresponding to the second ontology library, and a third knowledge graph corresponding to the third ontology library;

[0025] A plurality of form triples, including: a first form triple corresponding to a first ontology library, a second form triple corresponding to a second ontology library, and a third form triple corresponding to a third ontology library; wherein the first form triple includes a triple relationship formed by an entity, a relationship, and an entity, and a triple relationship formed by an entity, an attribute, and a property value; the second form triple includes a triple relationship formed by an entity, a relationship, and an entity; and the third form triple includes a triple relationship formed by an entity, a relationship, and an entity;

[0026] The knowledge graphs corresponding to each ontology library are integrated to obtain the knowledge graph of waterlogging dispatch, including:

[0027] The first entity node and the first node relationship corresponding to the first ontology library, the second entity node and the second node relationship corresponding to the second ontology library, and the third entity node and the third node relationship corresponding to the third ontology library are integrated to obtain multiple ontologies and the overall integration relationship between the multiple ontologies, and a total ontology library is constructed; wherein each ontology refers to a new entity after the entities with the same concept are merged;

[0028] Perform knowledge information fusion on the first form triples, the second form triples and the third form triples to obtain ontology data;

[0029] Based on multiple ontologies, total fusion relations and ontology data, knowledge is stored through a graph database to obtain a knowledge graph for waterlogging dispatching.

[0030] In a possible design, the waterlogging dispatch knowledge graph stores a plurality of triplet knowledge sets corresponding to each of the waterlogging dispatches;

[0031] Perform knowledge retrieval or knowledge reasoning on the waterlogging dispatch knowledge graph to obtain the waterlogging target dispatch plan, including:

[0032] According to the precipitation process data, knowledge retrieval or knowledge reasoning is performed through the graph database to obtain the triple knowledge set corresponding to the precipitation process data;

[0033] The triplet knowledge set is integrated to obtain the waterlogging target dispatching plan.

[0034] In a possible design, the waterlogging target dispatching scheme includes a first waterlogging dispatching scheme or a second waterlogging dispatching scheme;

[0035] The first waterlogging dispatching plan is a waterlogging dispatching plan obtained by searching the graph database for knowledge;

[0036] The second waterlogging dispatching plan is a waterlogging dispatching plan obtained by performing knowledge reasoning on the graph database, wherein the second waterlogging dispatching plan is obtained by jointly processing the graph database and experience results.

[0037] In a second aspect, the present application provides a waterlogging dispatching device based on a knowledge graph, comprising:

[0038] A data acquisition module is used to acquire a waterlogging data source, wherein the waterlogging data source includes multiple data sources;

[0039] The knowledge graph module is used to construct an ontology library corresponding to each data source based on multiple data sources, and to fill each ontology library with knowledge to obtain a knowledge graph corresponding to each ontology library;

[0040] The waterlogging dispatching module is used to fuse the knowledge graphs corresponding to each ontology library to obtain the waterlogging dispatching knowledge graph; and perform knowledge retrieval or knowledge reasoning on the waterlogging dispatching knowledge graph to obtain the waterlogging target dispatching plan.

[0041] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0042] Memory stores computer-executable instructions;

[0043] The processor executes computer execution instructions stored in the memory to implement a knowledge graph-based waterlogging scheduling method according to the first aspect of the invention.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, they are used to implement a knowledge graph-based waterlogging scheduling method according to the invention content of the first aspect.

[0045] In a fifth aspect, the present application provides a computer program product, including: a computer program, which, when executed by a processor, is used to implement a knowledge graph-based waterlogging scheduling method according to the invention content of the first aspect.

[0046] The present application provides a method, device, equipment and storage medium for waterlogging dispatching based on knowledge graph, which obtains waterlogging data source, wherein the waterlogging data source includes multiple data sources; constructs an ontology library corresponding to each data source according to multiple data sources, and fills each ontology library with knowledge respectively, to obtain the knowledge graph corresponding to each ontology library; performs knowledge fusion on the knowledge graph corresponding to each ontology library to obtain the waterlogging dispatching knowledge graph; and performs knowledge retrieval or knowledge reasoning on the waterlogging dispatching knowledge graph to obtain the waterlogging target dispatching plan. The following technical effects are achieved: obtain multiple data sources, process from multiple data, the data can come from historical data, and other data, so that the prediction results of subsequent steps are more accurate; establish knowledge graphs for each data source respectively, establish knowledge graphs from three perspectives, each knowledge graph corresponds to multiple entities and relationships, which can correspond to dispatching methods, so as to facilitate the rapid adoption of dispatching measures according to the waterlogging area in the future; fuse the three knowledge graphs, perform ontology fusion and attribute fusion, so that the waterlogging related data can be more accurate, and there is no computing power requirement, it can be used in various scenarios, and it has strong versatility. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A schematic diagram of the system architecture of a waterlogging scheduling method based on a knowledge graph provided in an embodiment of the present application;

[0049] Figure 2 Schematic diagram of the process of the waterlogging dispatching method based on the knowledge graph provided in the embodiment of the present application Figure 1 ;

[0050] Figure 3 Schematic diagram of the process of the waterlogging dispatching method based on the knowledge graph provided in the embodiment of the present application Figure 2;

[0051] Figure 4 Schematic diagram of the process of the waterlogging dispatching method based on the knowledge graph provided in the embodiment of the present application Figure 3 ;

[0052] Figure 5 The urban drainage basic ontology library of the waterlogging scheduling method based on the knowledge graph provided in the embodiment of the present application;

[0053] Figure 6 The basic ontology library of urban waterlogging dispatching for the waterlogging dispatching method based on knowledge graph provided in the embodiment of the present application;

[0054] Figure 7 The basic ontology library of urban precipitation waterlogging for the waterlogging scheduling method based on knowledge graph provided in the embodiment of the present application;

[0055] Figure 8 A schematic diagram of the structure of a waterlogging dispatching device based on a knowledge graph provided in an embodiment of the present application;

[0056] Fig. 9 A schematic diagram of the structure of the electronic device hardware provided in an embodiment of the present application.

[0057] Reference numerals:

[0058] 100-waterlogging dispatch server; 110-mode layer; 120-data layer;

[0059] 800-waterlogging dispatching device based on knowledge graph; 810-data acquisition module; 820-knowledge graph module; 830-waterlogging dispatching module;

[0060] 900 - electronic device; 910 - processor; 920 - memory; 930 - communication component; 940 - bus. DETAILED DESCRIPTION

[0061] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0062] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with basically the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more.

[0063] It should be noted that the "at..." in the embodiment of the present application can be the instant when a certain situation occurs, or it can be a period of time after a certain situation occurs, and the embodiment of the present application does not specifically limit this. In addition, the waterlogging scheduling method based on the knowledge graph provided in the embodiment of the present application is only an example, and the waterlogging scheduling method based on the knowledge graph can also include more or less content.

[0064] In order to clearly describe the technical solutions of the embodiments of the present application, some terms and technologies involved in the embodiments of the present application are briefly introduced below:

[0065] Knowledge graph: Knowledge graph is a technical method to represent knowledge in the form of a graph model, which is used to describe things, concepts and the relationships between them in the real world. The knowledge graph consists of nodes and edges, where nodes represent entities (such as people, places, events, etc.) or abstract concepts, and edges represent the relationships between entities. The knowledge graph is essentially a semantic network that can accurately describe the relationships between people, things, and objects, allowing computers to understand and process complex real-world information. The knowledge graph can be logically divided into two levels: the model layer and the data layer.

[0066] Schema layer: The schema layer is built on the data layer and is used to store refined knowledge. An ontology library is usually used to manage the schema layer of the knowledge graph.

[0067] Data layer: The data layer of the knowledge graph refers to the basic data structure and storage method that supports the knowledge graph. It is the underlying component of the knowledge graph and is responsible for storing entities, attributes, and relationships between entities in the knowledge graph. The design of the data layer directly affects the performance, scalability, and maintainability of the knowledge graph. In this application, the knowledge represented by a series of formal triples can be stored in a graph database.

[0068] Knowledge extraction: Knowledge extraction is an important part of the knowledge graph construction process. It involves automatically or semi-automatically identifying and extracting structured knowledge from data from various sources. The goal of knowledge extraction is to obtain entities, relationships, and other valuable information from unstructured or semi-structured data sources and convert them into a form that can be used to build a knowledge graph. Knowledge extraction from different sources and different types of data to obtain knowledge that can be used for knowledge graph storage and retrieval includes entity extraction, relationship extraction, and attribute extraction.

[0069] Entity extraction: Automatically identify entity information from data sources.

[0070] Relationship extraction: extract the relationship between two or more entities from the data source, connect the entities through the relationship, and form a network knowledge structure.

[0071] Attribute extraction: Attribute extraction is to extract attribute information of specific entities from the data source to supplement the entity information.

[0072] Formal triples: Formal triples in knowledge graphs are a basic form of data representation. A triple is usually composed of three parts, and this structure can concisely and effectively express the relationship information between entities. In this application, the first form triple includes multiple triples; the second form triple includes multiple triples; the third form triple includes multiple triples. In this application, the formal triple can be represented as the knowledge extracted from the ontology library.

[0073] Knowledge fusion: Knowledge fusion is a key technology in the process of knowledge graph construction. It refers to the merging of knowledge or data from different sources into a consistent and coherent whole. The purpose of knowledge fusion is to solve information redundancy, eliminate contradictions, improve data quality, and enrich the content of the knowledge graph by integrating data from multiple sources. The heterogeneous and diversified knowledge from multiple knowledge graphs is disambiguated and processed to achieve the merging of different knowledge graphs, including ontology fusion at the model layer and knowledge fusion at the data layer.

[0074] Knowledge reasoning: Starting from the existing entity relationship data in the knowledge graph, new relationships between different entities are established through computer reasoning. Commonly used algorithms include logic-based reasoning, graph-based reasoning, and deep learning-based reasoning.

[0075] Urban waterlogging dispatch: Urban waterlogging dispatch usually refers to a series of prevention and response measures taken when a city encounters heavy rainfall or other situations that cause excessive waterlogging, in order to reduce the impact of waterlogging on urban operations and residents' lives.

[0076] Under the condition of global climate change, extreme weather occurs frequently, and disasters related to floods and waterlogging are becoming more and more common. Under the premise of rapid urbanization, the prediction and dispatching methods for urban flood disasters are particularly important.

[0077] In the prior art, urban waterlogging prediction is usually performed based on models, and the prediction of waterlogged areas based on models is mainly achieved through the following implementation methods:

[0078] First, the acquired data is pre-processed to obtain the data required for building the model;

[0079] Secondly, an urban waterlogging simulation model is established and the parameters of the constructed urban waterlogging simulation model are calibrated;

[0080] Finally, the urban waterlogging simulation model is simulated and the accuracy is estimated.

[0081] However, urban waterlogging disasters are showing a significant trend, posing a serious threat to the sustainable development of cities and the safety of people's lives and property. Urban waterlogging disasters have certain characteristics of suddenness, flooding time, and serious impact. Simulating urban waterlogging based only on models has the following technical problems:

[0082] First, based on flood numerical and scheduling models, the model's calculation speed is slow, and urban waterlogging disasters are often sudden, so the calculation time is particularly important. The model calculation time is long, making it difficult to quickly predict and schedule according to the predicted situation.

[0083] Secondly, cities occupy a large area, and the problem of accurately solving each regional problem is placed in the urban waterlogging model. The higher the accuracy requirement of the model, the higher the corresponding calculation time and computing power requirements, which makes it difficult to meet the needs of flood control and drainage emergencies.

[0084] Therefore, how to quickly and accurately identify and predict waterlogging areas and determine waterlogging dispatching strategies in a timely manner is a problem that the present invention urgently needs to solve.

[0085] Based on this, the embodiments of the present application provide a knowledge graph-based urban flood scheduling method, device, equipment and storage medium, which can be used in the field of urban disaster monitoring technology, aiming to solve the above technical problems of the prior art.

[0086] Figure 1 A schematic diagram of the system architecture of the waterlogging dispatching method based on knowledge graph provided in the embodiment of the present application. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present application can be applied, in order to help those skilled in the art understand the technical content of the present application, but it does not mean that the embodiments of the present application cannot be used in other devices, systems, environments or scenarios.

[0087] like Figure 1 As shown, the system architecture of the waterlogging dispatching method based on the knowledge graph includes: a waterlogging dispatching server 100. In the embodiment of the present application, the waterlogging dispatching server can be equipped with a variety of software and systems that provide service support, including: a model layer 110 and a data layer 120.

[0088] The schema layer 110 defines the basic structure of the knowledge graph, describing entities, attributes, and the relationships between them.

[0089] The data layer 120 is where specific instances are actually stored, and it contains actual data filled in according to the structure defined by the model layer.

[0090] The model layer 110 provides a structured framework so that the data in the data layer 120 can be stored and queried according to certain logic and specifications. The data in the data layer 120 is obtained through data mining and manual entry, and is stored in the knowledge graph after cleaning and standardization.

[0091] Figure 2 Schematic diagram of the process of the waterlogging dispatching method based on the knowledge graph provided in the embodiment of the present application Figure 1 .like Figure 3 As shown, the method includes:

[0092] S201, obtaining waterlogging data source.

[0093] Among them, the waterlogging data source includes multiple data sources.

[0094] Specifically, the waterlogging data sources are obtained: a first data source, a second data source, and a third data source.

[0095] S202. Based on multiple data sources, construct an ontology library corresponding to each data source, and fill each ontology library with knowledge to obtain a knowledge graph corresponding to each ontology library.

[0096] Specifically, based on multiple data sources, an ontology library corresponding to each data source is constructed, wherein the ontology library includes an ontology library corresponding to the first data source, an ontology library corresponding to the second data source, and an ontology library corresponding to the third data source;

[0097] For each ontology library, a machine learning-based method is used to extract entities, relationships, and attributes from the collected and organized data sources, so as to obtain the formal triples corresponding to each data source. A graph database is used for knowledge storage to obtain the ontology library corresponding to each ontology library.

[0098] S203, performing knowledge fusion on the knowledge graphs corresponding to each ontology library to obtain a waterlogging dispatching knowledge graph; and performing knowledge retrieval or knowledge reasoning on the waterlogging dispatching knowledge graph to obtain a waterlogging target dispatching plan.

[0099] Specifically, the knowledge of the knowledge graphs corresponding to the three ontology libraries is integrated to construct the knowledge graph of waterlogging dispatch. The knowledge graph of waterlogging dispatch is used for retrieval and knowledge reasoning to obtain the waterlogging process and drainage dispatch plan.

[0100] The present application provides a method for waterlogging dispatching based on knowledge graph, which obtains waterlogging data source, wherein the waterlogging data source includes multiple data sources; constructs an ontology library corresponding to each data source according to the multiple data sources, and fills each ontology library with knowledge respectively, to obtain the knowledge graph corresponding to each ontology library; performs knowledge fusion on the knowledge graph corresponding to each ontology library to obtain the waterlogging dispatching knowledge graph; and performs knowledge retrieval or knowledge reasoning on the waterlogging dispatching knowledge graph to obtain the waterlogging target dispatching scheme. The following technical effects are achieved: obtain multiple data sources, process from multiple data, the data can come from historical data and other data, so that the prediction results of subsequent steps are more accurate; establish knowledge graphs for each data source respectively, establish knowledge graphs from three perspectives, each knowledge graph corresponds to multiple entities and relationships, which can correspond to dispatching methods, so as to facilitate the rapid adoption of dispatching measures according to the waterlogging area in the future; fuse the three knowledge graphs, perform ontology fusion and attribute fusion, so that the waterlogging related data can be more accurate, and there is no computing power requirement, it can be used in various scenarios, and it has strong versatility.

[0101] Figure 3 Schematic diagram of the process of the waterlogging dispatching method based on the knowledge graph provided in the embodiment of the present application Figure 2 In this embodiment Figure 2 Based on the embodiment, the specific steps of the waterlogging dispatching method based on the knowledge graph are described in detail, such as Figure 3 As shown, this embodiment provides a method for flood control scheduling based on a knowledge graph, including:

[0102] S301, obtaining waterlogging data source.

[0103] Among them, the waterlogging data source includes multiple data sources.

[0104] The principles of S301 and S201 are the same and will not be described again here.

[0105] By acquiring a variety of data sources and inputting them into subsequent knowledge graphs for waterlogged area prediction, a wider range of factors can be considered in the prediction, thereby improving the accuracy of the prediction.

[0106] S302: Obtain object data corresponding to each data source according to multiple data sources.

[0107] Among them, the object data includes a first object corresponding to the first data source, a second object corresponding to the second data source, and a third object corresponding to the third data source; among them, the first object includes objects of surface units, pipeline networks, rivers and lakes, rainwater pumping stations and storage tanks; the second object includes objects of drainage facilities, as well as control objects, enabling condition objects, scheduling operation mode objects and scheduling operation effect objects of drainage settings; the third object includes objects of precipitation processes, water level objects and flow objects of typical points of the surface, pipeline networks, rivers and lakes.

[0108] Specifically, based on multiple data sources, an ontology library corresponding to each data source is constructed. Based on the first data source, the object of the first data source and the first object data are obtained; based on the second data source, the object of the second data source and the second object data are obtained; based on the third data source, the object of the third data source and the third object data are obtained.

[0109] S303: Determine the multiple objects of the first data source, the second data source, and the third data source as their own entity nodes, and determine the relationships among the multiple objects of the first data source, the second data source, and the third data source as their own node relationships.

[0110] The multiple entity nodes include a first entity node corresponding to the first data source, a second entity node corresponding to the second data source, and a third entity node corresponding to the third data source; the multiple node relationships include a first node relationship corresponding to the first data source, a second node relationship corresponding to the second data source, and a third node relationship corresponding to the third data source.

[0111] Specifically, the first object of the first data source is determined as a first entity node, and the relationship between the first objects is determined as a first node relationship; the second object of the second data source is determined as a second entity node, and the relationship between the second objects is determined as a second node relationship; the third object of the third data source is determined as a third entity node, and the relationship between the third objects is determined as a third node relationship.

[0112] By dividing various data sources into entities, relationships, and attributes, the subsequent establishment of the ontology library can be made clearer.

[0113] S304: Obtain first data.

[0114] The first data includes the data of surface units, pipe networks, rivers and lakes, rainwater pumping stations and storage tanks. The first node relationship includes the flow direction between multiple surface units, the topological relationship of the pipe network, the hydraulic connection between rivers and lakes, the positional relationship between rainwater pumping stations, storage tanks and multiple surface units, and the hydraulic connection between rainwater pumping stations and rivers and lakes.

[0115] Specifically, a first ontology library corresponding to the first data source is constructed according to the first entity node and the first node relationship, and first data corresponding to the first data source is obtained.

[0116] The source and object of the first data source are described in detail, so that the objects considered by the first data source are complete and diverse, taking into account the relationship between rainwater passing through the surface and other facilities.

[0117] S305: Screen the first data to obtain characteristic parameters corresponding to each data in the first data.

[0118] Specifically, the first data is screened to obtain characteristic parameters corresponding to multiple objects in the first data.

[0119] By screening the data, we can get the desired data, and use the data as the basis for the subsequent knowledge graph building, which is conducive to quickly obtaining the desired knowledge graph and the corresponding scheduling plan.

[0120] S306: Determine multiple characteristic parameters in the first data as node attributes of the first entity node.

[0121] Specifically, the first data is determined as a node attribute of the first entity node, that is, the characteristic parameter of the first data source is defined as a node attribute of the first entity node.

[0122] Each first object corresponds to a characteristic parameter to ensure that the first ontology library is established correctly and completely.

[0123] S307: Construct a first ontology library according to the first entity node, the first node relationship, and the node attribute of the first entity node.

[0124] Specifically, according to the first entity node, the first node relationship and the node attribute of the first entity node, the first ontology library is obtained, and the first ontology library is the urban drainage basic ontology library.

[0125] The first ontology library is established according to the relationship, entity and attribute, so that more factors are considered in establishing the first ontology library and the first ontology library is complete.

[0126] S308: construct a second ontology library corresponding to the second data source according to the second entity node and the second node relationship, and construct a third ontology library corresponding to the third data source according to the third entity node and the third node relationship.

[0127] Specifically, according to the second entity node and the relationship between the second node, the second ontology library corresponding to the second data source, namely the basic ontology library for urban waterlogging scheduling, is constructed; according to the third entity node and the relationship between the third node, the basic ontology library for urban precipitation waterlogging corresponding to the third data source is constructed.

[0128] By establishing the second ontology library and the third ontology library respectively, we can obtain the basic ontology library of urban waterlogging scheduling and the basic ontology library of urban precipitation waterlogging, which makes the establishment and classification of subsequent knowledge graphs clearer.

[0129] S309: extracting knowledge from the data sources corresponding to each ontology library through a machine learning method to obtain a plurality of formal triples corresponding to each ontology library.

[0130] Among them, each formal triple is used to indicate the knowledge information of the corresponding entity.

[0131] Specifically, knowledge is filled in each ontology library to obtain the knowledge graph corresponding to each ontology library. Based on the machine learning method, knowledge is extracted from the first ontology library, that is, entity extraction, relationship extraction and attribute extraction are performed on the first data source to obtain formal triples, where the formal triples corresponding to the first ontology library include: formal triples of entity, relationship and entity; formal triples of entity, attribute and property value.

[0132] Based on the machine learning method, knowledge is extracted from the second ontology library, that is, entity extraction and relationship extraction are performed on the second data source to obtain formal triples, wherein the formal triples corresponding to the second ontology library include: formal triples of entities, relationships and entities.

[0133] Based on the machine learning method, knowledge is extracted from the third ontology library, that is, entity extraction and relationship extraction are performed on the third data source to obtain formal triples, wherein the formal triples corresponding to the second ontology library include: formal triples of entities, relationships and entities.

[0134] The machine learning method is used to obtain the formal triples corresponding to each ontology library, making the acquisition of formal triples more accurate. The technology of machine learning is relatively mature, which is conducive to the acquisition of formal triples.

[0135] S310. Through the pre-stored graph database, knowledge is stored for multiple formal triples corresponding to each ontology library to obtain a knowledge graph corresponding to each ontology library.

[0136] Among them, each knowledge graph includes: a corresponding ontology library, and corresponding multiple formal triples.

[0137] Specifically, each formal triple is stored in a graph database to obtain a first knowledge graph corresponding to the formal triple corresponding to each first ontology library, a second knowledge graph corresponding to the formal triple corresponding to each second ontology library, and a third knowledge graph corresponding to the formal triple corresponding to each third ontology library.

[0138] A graph database is a database system specifically used for storing and querying graph structures. In the construction and application of knowledge graphs, it can process complex relational data quickly and efficiently, and can be used for rapid query and update operations, significantly reducing query time.

[0139] S311, fuse the first entity node and the first node relationship corresponding to the first ontology library, the second entity node and the second node relationship corresponding to the second ontology library, and the third entity node and the third node relationship corresponding to the third ontology library to obtain multiple ontologies and the overall fusion relationship between the multiple ontologies, and construct an overall ontology library.

[0140] Among them, ontology refers to entities with the same concepts; the total fusion relationship refers to all the relationships between ontologies. The knowledge graph corresponding to each ontology library includes: the first knowledge graph corresponding to the first ontology library, the second knowledge graph corresponding to the second ontology library, and the third knowledge graph corresponding to the third ontology library; multiple formal triples include: the first formal triple corresponding to the first ontology library, the second formal triple corresponding to the second ontology library, and the third formal triple corresponding to the third ontology library; among them, the first formal triple includes the triple relationship formed by entity, relationship and entity, and the triple relationship formed by entity, attribute and property value; the second formal triple includes the triple relationship formed by entity, relationship and entity; the third formal triple includes the triple relationship formed by entity, relationship and entity;

[0141] Specifically, the knowledge graphs corresponding to each ontology library are fused to obtain the knowledge graph of waterlogging dispatch. Based on the first knowledge graph, the second knowledge graph and the third knowledge graph, the knowledge of different knowledge graphs is fused to obtain the ontology and the total fusion relationship corresponding to the ontology, and a new ontology library, namely the total ontology library, is constructed. That is, the entity objects from different knowledge graphs are first integrated, followed by entity disambiguation and entity alignment, to obtain the ontology of the waterlogging dispatch knowledge graph and the total fusion relationship corresponding to the ontology.

[0142] The ontology of the three knowledge graphs is integrated so that entities with the same concept but different names are integrated into the ontology, so that the same ontology and the corresponding relationships can be accurately matched.

[0143] S312, fusing the first form triples, the second form triples and the third form triples to obtain ontology data.

[0144] Specifically, the formal triples contain data such as entities, relationships, and attributes. The knowledge of the first formal triples of the first knowledge graph, the second formal triples of the second knowledge graph, and the third formal triples of the third knowledge graph are fused to obtain ontology data. That is, attributes and data are compared and analyzed to perform attribute fusion.

[0145] Fusion of data with the same ontology can realize data availability and make subsequent knowledge graph retrieval results more accurate.

[0146] S313. Based on multiple ontologies, total fusion relationships and ontology data, knowledge is stored through a graph database to obtain a knowledge graph for waterlogging dispatching.

[0147] Specifically, based on the fused ontology, the total relationship corresponding to the ontology and the ontology data, a new formal triple is obtained, and the triple is filled into the data layer of the knowledge graph. The graph database is used for knowledge storage to construct the waterlogging scheduling knowledge graph.

[0148] Based on the newly obtained ontology, total relationship and data, new data layer data storage is performed to obtain a new knowledge graph for waterlogging scheduling, so as to facilitate real-time retrieval and prediction based on precipitation process data.

[0149] S314. Based on the precipitation process data, knowledge retrieval or knowledge reasoning is performed through a graph database to obtain a triple knowledge set corresponding to the precipitation process data.

[0150] The waterlogging dispatching knowledge graph includes a total ontology library and formal triples. The waterlogging dispatching knowledge graph stores multiple waterlogging dispatching schemes and the formal triple knowledge set corresponding to each waterlogging dispatching scheme.

[0151] Specifically, knowledge retrieval or knowledge reasoning is performed on the waterlogging dispatch knowledge graph to obtain the waterlogging target dispatching plan. According to the acquired precipitation process data, the graph database selects the knowledge retrieval or knowledge reasoning method according to the precipitation process data to obtain the formal triple corresponding to the precipitation process data.

[0152] The corresponding formal triples can be obtained through the specific precipitation process data, the data corresponding to the entity can be quickly obtained, and the waterlogging scheduling plan can be obtained based on the formal triples.

[0153] S315. Integrate the triplet knowledge set to obtain a waterlogging target scheduling plan.

[0154] Specifically, the obtained triplet knowledge set is integrated and processed to obtain the waterlogging target scheduling plan.

[0155] In a possible design, the waterlogging target dispatching scheme includes a first waterlogging dispatching scheme or a second waterlogging dispatching scheme;

[0156] The first waterlogging dispatching plan is a waterlogging dispatching plan obtained by searching the graph database for knowledge;

[0157] The second waterlogging dispatching plan is a waterlogging dispatching plan obtained by performing knowledge reasoning on the graph database, wherein the second waterlogging dispatching plan is obtained by jointly processing the graph database and experience results.

[0158] Specifically, the final waterlogging target dispatching scheme includes two types: one is obtained by the graph database through knowledge retrieval of the waterlogging dispatching knowledge graph, which is used when the precipitation process data does not exceed the historical data; the other is obtained by the graph database through knowledge reasoning based on the waterlogging dispatching knowledge graph, which is applicable to the case where the precipitation process data exceeds the historical data. Among them, the second waterlogging dispatching scheme refers to a waterlogging dispatching scheme obtained after the graph database performs knowledge reasoning. At this time, the waterlogging dispatching scheme is checked or corrected through artificial experience results to obtain the final dispatching scheme.

[0159] The present application provides a waterlogging dispatching method based on a knowledge graph, which obtains waterlogging target dispatching plans through two situations respectively, and can realize timely adjustment of the waterlogging dispatching plans under different situations, making the prediction more accurate.

[0160] For the convenience of explanation, a specific embodiment is introduced here:

[0161] Figure 4 Schematic diagram of the process of the waterlogging dispatching method based on the knowledge graph provided in the embodiment of the present application Figure 3 .like Figure 4 shown.

[0162] S401. Collect first data, construct a first ontology library corresponding to the first data, and extract knowledge from the first ontology library to obtain an urban drainage knowledge graph.

[0163] Collect the data of the first data source, that is, the data related to the urban surface underlying surface and drainage system. The first data includes the surface (ground elevation, land use type), pipe network (drainage pipe network and its ancillary facilities), river (river and lake water system and its culvert), drainage pump station and other data, sort out and analyze the flow direction of urban surface water, drainage pipe network topology, river and lake water system topology relationship and related characteristic parameters. Determine the first data source object as an entity node, the characteristic parameter as a node attribute, and the relationship between entities as a node relationship to build an urban drainage basic ontology library.

[0164] Taking the surface as an example, the surface is divided into multiple surface units according to the surface elevation and land use type. The surface units are determined as entity nodes, the characteristic parameters of the surface units are determined as node attributes, and the flow direction of water between the surfaces is determined as node relationships. Taking the pipe network and rivers and lakes as an example, the pipe network and rivers and lakes are divided into multiple pipe sections and river sections. The pipe sections and river sections are determined as entity nodes, the characteristic parameters are determined as node attributes, and the pipe network topological relationship and the hydraulic connection between rivers and lakes are determined as node relationships; taking the rainwater pumping station and the regulating reservoir as an example, the rainwater pumping station and the regulating reservoir are defined as entity nodes, the characteristic parameters are node attributes, and the positional relationship between the rainwater pumping station and the surface and the hydraulic connection with the regulating reservoir and the river are determined as node relationships. Based on the above-mentioned entity nodes, node attributes and node relationships, a basic ontology library for urban drainage is constructed. The ontology library can be as follows Figure 5 As shown, Figure 5 The urban drainage basic ontology library of the waterlogging dispatching method based on the knowledge graph provided in the embodiment of this application. Figure 5 As shown, the ellipse represents an entity, the solid line represents the relationship between entities, the rectangle represents the attribute value, and the dotted line represents the relationship between entities and attributes. Taking surface unit b as an example, the flow direction of water between surface unit a and surface unit b is the node relationship between surface unit a and surface unit b, the control relationship between rainwater pumping station c and surface unit b is also the node relationship between rainwater pumping station c and surface unit b, and the flow direction relationship of water between surface unit b and river section j is the node relationship between surface unit b and river section j; the relationship between surface unit b and parameter b is the relationship between entity and attribute, and parameter b is the data of the surface unit.

[0165] A machine learning-based method is used to perform entity extraction, relationship extraction, and attribute extraction on the first data source to obtain formal triplets of entities, relationships, and formal triplets of entities, attributes, and property values. A graph database is used for knowledge storage to obtain an urban drainage knowledge graph.

[0166] S402: Collect the second data, construct a second ontology library corresponding to the second data, and extract knowledge from the second ontology library to obtain a knowledge graph of urban waterlogging dispatching.

[0167] Collect the second data source, namely the data related to the historical urban waterlogging dispatching plan. The second data source includes the basic information of drainage facilities, waterlogging dispatching plans and historical waterlogging dispatching cases, and sort out and analyze the waterlogging dispatching rules, such as the control objects of drainage facilities, activation conditions, dispatching operation mode, dispatching operation effect, etc.

[0168] Urban drainage facilities include river and lake culverts, drainage pumping stations, and storage tanks. Taking the rainwater pumping station as an example, the water level of the surface unit where the rainwater pumping station is located is used to determine whether the activation conditions of the rainwater pumping station and its affiliated storage tank are met, and the corresponding scheduling method and scheduling effect are matched according to the activation conditions. Therefore, the rainwater pumping station and its control objects, activation conditions, scheduling methods, scheduling effects, etc. can be set as entity nodes, and their corresponding relationships can be set as node relationships. Figure 6 As shown, Figure 6 A basic ontology library for urban waterlogging dispatching of a waterlogging dispatching method based on a knowledge graph provided in an embodiment of the present application. Figure 6 Only the rainwater pumping station is used as an example. Among them, the surface unit a is the drainage facility control object, the water level is the state of the drainage facility control object, and h1 <H<h2,H> h2 is the activation condition of the drainage facility, the rainwater pump station is the dispatching facility of the drainage facility, the dispatching operation mode is the dispatching operation mode called by the rainwater pump station and the dispatching operation effect of the final dispatching operation mode. Among them, the rainwater pump station b has a dispatching mode in both cases.

[0169] Other drainage facilities can be processed similarly to obtain the basic ontology library of urban waterlogging dispatch. Using a machine learning-based method, the second data source is subjected to entity extraction and relationship extraction to obtain the formal ternary combination entities between entities, relationships and entities, and a graph database is used for knowledge storage to obtain the knowledge graph of urban waterlogging dispatch.

[0170] S403: Collect third data, construct a third ontology library corresponding to the third data, and extract knowledge from the third ontology library to obtain a knowledge graph of urban waterlogging caused by precipitation.

[0171] Collect the third data source, namely the historical urban waterlogging process monitoring data and the corresponding precipitation process data. By sorting and analyzing the historical waterlogging process monitoring data, we can obtain the water level and flow monitoring data of typical points on the surface, pipe network and river. According to the urban drainage basic ontology library, the water level and flow corresponding to the precipitation process, surface unit, pipe section and river section are used as entity nodes, and their corresponding relationships are used as node relationships to establish the urban precipitation waterlogging basic ontology library. Figure 7 As shown, Figure 7 The basic ontology library of urban precipitation waterlogging for the waterlogging scheduling method based on knowledge graph provided in the embodiment of the present application. Figure 7 Only some objects (surface units, pipe sections and river sections) are used as examples.

[0172] A machine learning-based method is used to extract entities and relationships from the third data source to obtain formal triples of entities, relationships and entities, and entities are stored in a graph database to obtain a knowledge graph of urban rainfall waterlogging.

[0173] S404. Based on the urban drainage knowledge graph, the urban waterlogging scheduling knowledge graph and the urban precipitation waterlogging knowledge graph, the knowledge is integrated to obtain the waterlogging drainage scheduling knowledge graph.

[0174] Based on the basic knowledge graph of urban drainage, the basic knowledge graph of waterlogging dispatch, and the knowledge graph of precipitation waterlogging, the knowledge of different knowledge graphs is successively integrated into ontology and data. First, the ontology containing the same concept from different knowledge graphs is integrated into one ontology, and the ontology from different knowledge graphs is mapped, and the mapping rules between the ontologies are established to complete the integration of the ontology libraries of different knowledge graphs; then, through the comparative analysis of entity objects and their attributes from different knowledge graphs, entity disambiguation, entity alignment, and attribute fusion are performed to form new formal triples between entities, relationships and entities, and formal triples of entities, attributes, and property values. According to the fused ontology library, the new triples are matched and filled into the data layer, and the graph database is used for knowledge storage to construct the knowledge graph of waterlogging drainage dispatch.

[0175] S405. Based on the precipitation process data, knowledge retrieval and knowledge reasoning are performed through the waterlogging dispatch knowledge graph to obtain the corresponding waterlogging dispatch plan.

[0176] According to the precipitation process data collected by the third data source, knowledge retrieval or knowledge reasoning is performed through the waterlogging knowledge graph stored in the graph database to obtain the target waterlogging dispatching plan. The specific use of knowledge retrieval or knowledge reasoning is determined by the graph database. Under normal circumstances, knowledge retrieval is used. When it exceeds the application scope, knowledge reasoning is used. Among them, the application scope is only historical data. The application scope can refer to Figure 6 Conditions shown, but specific application range depends on the situation.

[0177] The present application provides a waterlogging scheduling method based on a knowledge graph, which obtains a waterlogging data source, wherein the waterlogging data source includes multiple data sources; based on the multiple data sources, an ontology library corresponding to each data source is constructed, and knowledge is filled in each ontology library respectively to obtain a knowledge graph corresponding to each ontology library; knowledge fusion is performed on the knowledge graph corresponding to each ontology library to obtain a waterlogging scheduling knowledge graph; and knowledge retrieval or knowledge reasoning is performed on the waterlogging scheduling knowledge graph to obtain a waterlogging target scheduling plan. The following technical effects are achieved: multiple data sources are obtained and processed from multiple data. The data can come from historical data and other data, so that the prediction results of subsequent steps are more accurate; knowledge graphs are established for each data source respectively, and the knowledge graphs are established from three perspectives. Each knowledge graph corresponds to multiple entities and relationships, which can correspond to scheduling methods, so that scheduling measures can be quickly taken according to the waterlogged areas in the future; the three knowledge graphs are integrated to perform entity fusion and attribute fusion, which can make the waterlogging-related data more accurate, and there is no computing power requirement, and it can be used in a variety of scenarios with strong versatility; when the functions corresponding to separate knowledge graphs are needed, only one or two knowledge graphs can be used, and the corresponding data and the corresponding scheduling methods can be quickly obtained based on the knowledge of the knowledge graph; when the data in the precipitation process is too large and exceeds the previous historical data, knowledge reasoning is used to analyze and mine the historical data to generate a scheduling plan, and the generated scheduling plan is manually checked and corrected in combination with expert experience to reduce errors and improve the accuracy of the prediction.

[0178] The embodiment of the present invention can divide the electronic device or the main control device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0179] Figure 8 This is a schematic diagram of the structure of the waterlogging dispatching device based on the knowledge graph provided in the embodiment of the present application. Figure 8 As shown, the waterlogging scheduling device 800 based on the knowledge graph includes a data acquisition module 810, a knowledge graph module 820 and a waterlogging scheduling module 830.

[0180] The data acquisition module 810 is used to acquire a waterlogging data source, wherein the waterlogging data source includes multiple data sources;

[0181] The knowledge graph module 820 is used to construct an ontology library corresponding to each data source according to multiple data sources, and to fill each ontology library with knowledge to obtain a knowledge graph corresponding to each ontology library;

[0182] The waterlogging dispatching module 830 is used to perform knowledge fusion on the knowledge graphs corresponding to each ontology library to obtain the waterlogging dispatching knowledge graph; and perform knowledge retrieval or knowledge reasoning on the waterlogging dispatching knowledge graph to obtain the waterlogging target dispatching plan.

[0183] In one possible design, the knowledge graph module 820 includes:

[0184] An extraction module is used to extract knowledge from the data source corresponding to each ontology library through a machine learning method to obtain a plurality of formal triples corresponding to each ontology library; wherein each formal triple is used to indicate the knowledge information of the corresponding entity;

[0185] The storage module is used to store knowledge of multiple formal triples corresponding to each ontology library through a pre-stored graph database to obtain a knowledge graph corresponding to each ontology library; wherein each knowledge graph includes: a corresponding ontology library and corresponding multiple formal triples.

[0186] In a possible design, the multiple data sources include a first data source, a second data source, and a third data source; wherein the first data source includes data of the underlying surface of the urban landmark and the drainage system; the second data source includes data of historical waterlogging scheduling plans; the third data source includes data of urban waterlogging scheduling process detection and precipitation process;

[0187] The knowledge graph module 820 includes:

[0188] An object data module is used to obtain object data corresponding to each data source according to multiple data sources; wherein the object data includes a first object corresponding to the first data source, a second object corresponding to the second data source, and a third object corresponding to the third data source; wherein the first object includes objects of surface units, pipe networks, rivers and lakes, rainwater pumping stations, and storage tanks; the second object includes objects of drainage facilities, as well as control objects, enabling condition objects, scheduling operation mode objects, and scheduling operation effect objects of drainage settings; the third object includes objects of precipitation processes, water level objects and flow objects of typical points of the surface, pipe networks, and rivers and lakes;

[0189] The node determination module is used to determine the multiple objects of the first data source, the second data source and the third data source as their respective entity nodes, and determine the relationships between the multiple objects of the first data source, the second data source and the third data source as their respective node relationships; the multiple entity nodes include a first entity node corresponding to the first data source, a second entity node corresponding to the second data source, and a third entity node corresponding to the third data source; the multiple node relationships include a first node relationship corresponding to the first data source, a second node relationship corresponding to the second data source, and a third node relationship corresponding to the third data source;

[0190] The ontology construction module is used to construct a first ontology library corresponding to the first data source according to the first entity node and the first node relationship, to construct a second ontology library corresponding to the second data source according to the second entity node and the second node relationship, and to construct a third ontology library corresponding to the third data source according to the third entity node and the third node relationship.

[0191] In a possible design, the first node relationship includes the flow direction between multiple surface units, the topological relationship of the pipe network, the hydraulic connection between rivers and lakes, the positional relationship between the rainwater pumping station, the regulating reservoir and multiple surface units, and the hydraulic connection between the rainwater pumping station and the rivers and lakes;

[0192] Construct the ontology module, including:

[0193] A first data module is used to obtain first data, wherein the first data includes data of surface units, pipe networks, rivers and lakes, rainwater pumping stations and storage tanks;

[0194] A first screening module, used to screen the first data to obtain a characteristic parameter corresponding to each data in the first data;

[0195] A first node module, used to determine a plurality of characteristic parameters in the first data as node attributes of a first entity node;

[0196] The first ontology library module is used to construct a first ontology library according to the first entity node, the first node relationship, and the node attribute of the first entity node.

[0197] In a possible design, the knowledge graph corresponding to each ontology library includes: a first knowledge graph corresponding to the first ontology library, a second knowledge graph corresponding to the second ontology library, and a third knowledge graph corresponding to the third ontology library;

[0198] A plurality of form triples, including: a first form triple corresponding to a first ontology library, a second form triple corresponding to a second ontology library, and a third form triple corresponding to a third ontology library; wherein the first form triple includes a triple relationship formed by an entity, a relationship, and an entity, and a triple relationship formed by an entity, an attribute, and a property value; the second form triple includes a triple relationship formed by an entity, a relationship, and an entity; and the third form triple includes a triple relationship formed by an entity, a relationship, and an entity;

[0199] The waterlogging dispatching module 830 includes:

[0200] An ontology fusion module is used to fuse the first entity node and the first node relationship corresponding to the first ontology library, the second entity node and the second node relationship corresponding to the second ontology library, and the third entity node and the third node relationship corresponding to the third ontology library to obtain a plurality of ontologies and the overall fusion relationship between the plurality of ontologies, and to construct an overall ontology library; wherein each ontology refers to a new entity after the entities with the same concept are merged;

[0201] A data fusion module, used for fusing the first form triples, the second form triples and the third form triples to obtain ontology data;

[0202] The graph storage module is used to store knowledge through a graph database based on multiple ontologies, total fusion relationships and ontology data to obtain a knowledge graph for waterlogging scheduling.

[0203] In a possible design, the waterlogging dispatch knowledge graph stores a plurality of triplet knowledge sets corresponding to each of the waterlogging dispatches;

[0204] The waterlogging dispatching module 830 includes:

[0205] The knowledge collection module is used to retrieve or reason about the precipitation process data through the graph database to obtain the triple knowledge collection corresponding to the precipitation process data.

[0206] The scheme determination module is used to integrate the triple knowledge set to obtain the waterlogging target scheduling scheme.

[0207] In a possible design, the waterlogging target dispatching scheme includes a first waterlogging dispatching scheme or a second waterlogging dispatching scheme;

[0208] The first waterlogging dispatching plan is a waterlogging dispatching plan obtained by searching the graph database for knowledge;

[0209] The second waterlogging dispatching plan is a waterlogging dispatching plan obtained by performing knowledge reasoning on the graph database, wherein the second waterlogging dispatching plan is obtained by jointly processing the graph database and experience results.

[0210] The present embodiment provides a waterlogging dispatching device based on a knowledge graph, which can execute the waterlogging dispatching method based on a knowledge graph of the above-mentioned embodiment. Its implementation principle and technical effects are similar, and will not be described in detail in this embodiment.

[0211] In the specific implementation of the aforementioned knowledge graph-based waterlogging scheduling method, each module can be implemented as a processor, and the processor can execute computer execution instructions stored in the memory, so that the processor executes the aforementioned knowledge graph-based waterlogging scheduling method.

[0212] Fig. 9 This is a schematic diagram of the structure of the electronic device hardware provided in the embodiment of the present application. Fig. 9 As shown, the electronic device 900 includes: at least one processor 910 and a memory 920. The electronic device 900 also includes a communication component 930. The processor 910, the memory 920 and the communication component 930 are connected via a bus 940.

[0213] In the specific implementation process, at least one processor 910 executes the computer execution instructions stored in the memory 920, so that at least one processor 910 executes a waterlogging scheduling method based on a knowledge graph as executed by the electronic device side above.

[0214] The specific implementation process of the processor 910 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0215] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0216] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0217] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0218] The above-mentioned functions implemented by the electronic device and the main control device introduce the scheme provided by the embodiment of the present invention. It can be understood that in order to implement the above-mentioned functions, the electronic device or the main control device includes a hardware structure and / or software module corresponding to the execution of each function. In combination with the units and algorithm steps of each example described in the embodiment disclosed in the embodiment of the present invention, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present invention.

[0219] The present application also provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, they are used to implement the above-mentioned waterlogging scheduling method based on knowledge graph.

[0220] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof.

[0221] Such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0222] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in an electronic device or a main control device.

[0223] The present application also provides a computer program product, which includes: a computer program, which is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium. When the computer program is executed by the processor, it is used to implement the above-mentioned knowledge graph-based waterlogging scheduling method.

[0224] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by hardware related to program instructions. The above program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above method embodiments are executed; and the above storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0225] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A waterlogging dispatching method based on knowledge graph, characterized in that: The method comprises: Acquire a waterlogging data source, wherein the waterlogging data source includes a plurality of data sources; According to the multiple data sources, construct an ontology library corresponding to each of the data sources, and fill each of the ontology libraries with knowledge to obtain a knowledge graph corresponding to each of the ontology libraries; The knowledge graphs corresponding to each ontology library are fused to obtain a waterlogging dispatching knowledge graph; and knowledge retrieval or knowledge reasoning is performed on the waterlogging dispatching knowledge graph to obtain a waterlogging target dispatching plan.

2. The method according to claim 1, characterized in that The step of filling each ontology library with knowledge to obtain a knowledge graph corresponding to each ontology library comprises: By using a machine learning method, knowledge is extracted from the data source corresponding to each ontology library, so as to obtain a plurality of formal triples corresponding to each ontology library; wherein each formal triple is used to indicate knowledge information of a corresponding entity; Through the pre-stored graph database, knowledge storage is performed on the multiple formal triples corresponding to each ontology library to obtain the knowledge graph corresponding to each ontology library; wherein each knowledge graph includes: the corresponding ontology library, and the corresponding multiple formal triples.

3. The method according to claim 2, characterized in that The multiple data sources include a first data source, a second data source and a third data source; wherein the first data source includes data of the underlying surface of the city landmark and the drainage system; the second data source includes data of historical waterlogging scheduling plans; the third data source includes data of the urban waterlogging scheduling process detection and the precipitation process; The step of constructing an ontology library corresponding to each of the data sources according to the plurality of data sources includes: According to the multiple data sources, object data corresponding to each of the data sources are obtained; wherein the object data includes a first object corresponding to the first data source, a second object corresponding to the second data source, and a third object corresponding to the third data source; wherein the first object includes objects of surface units, pipe networks, rivers and lakes, rainwater pumping stations, and storage tanks; the second object includes objects of drainage facilities, and control objects, enabling condition objects, scheduling operation mode objects, and scheduling operation effect objects of the drainage settings; the third object includes objects of precipitation processes, and water level objects and flow objects of typical points of the surface, pipe networks, and rivers and lakes; Determine the multiple objects of the first data source, the second data source, and the third data source as their respective entity nodes, and determine the relationships among the multiple objects of the first data source, the second data source, and the third data source as their respective node relationships; the multiple entity nodes include a first entity node corresponding to the first data source, a second entity node corresponding to the second data source, and a third entity node corresponding to the third data source; the multiple node relationships include a first node relationship corresponding to the first data source, a second node relationship corresponding to the second data source, and a third node relationship corresponding to the third data source; A first ontology library corresponding to the first data source is constructed based on the first entity node and the first node relationship, a second ontology library corresponding to the second data source is constructed based on the second entity node and the second node relationship, and a third ontology library corresponding to the third data source is constructed based on the third entity node and the third node relationship.

4. The method according to claim 3, characterized in that The first node relationship includes the water flow direction between the plurality of the surface units, the topological relationship of the pipe network, the hydraulic connection between the rivers and lakes, the positional relationship between the rainwater pumping station, the regulating reservoir and the plurality of the surface units, and the hydraulic connection between the rainwater pumping station and the rivers and lakes; The step of constructing a first ontology library corresponding to the first data source according to the first entity node and the first node relationship includes: Acquire first data, wherein the first data includes data of the surface unit, the pipe network, the river and lake, the rainwater pumping station, and the storage tank; Screening the first data to obtain characteristic parameters corresponding to each data in the first data; Determine the plurality of characteristic parameters in the first data as node attributes of the first entity node; The first ontology library is constructed according to the first entity nodes, the first node relationships, and node attributes of the first entity nodes.

5. The method according to claim 4, characterized in that The knowledge graph corresponding to each of the ontology libraries includes: a first knowledge graph corresponding to the first ontology library, a second knowledge graph corresponding to the second ontology library, and a third knowledge graph corresponding to the third ontology library; The plurality of said formal triples include: a first formal triple corresponding to the first ontology library, a second formal triple corresponding to the second ontology library, and a third formal triple corresponding to the third ontology library; wherein the first formal triple includes a triple relationship formed by an entity, a relationship and an entity, and a triple relationship formed by an entity, an attribute and a property value; the second formal triple includes a triple relationship formed by an entity, a relationship and an entity; the third formal triple includes a triple relationship formed by an entity, a relationship and an entity; The knowledge graphs corresponding to each ontology library are fused to obtain a knowledge graph for waterlogging dispatching, including: Performing ontology fusion on the first entity node and the first node relationship corresponding to the first ontology library, the second entity node and the second node relationship corresponding to the second ontology library, and the third entity node and the third node relationship corresponding to the third ontology library, to obtain a plurality of ontologies and a total fusion relationship between the plurality of ontologies, and constructing a total ontology library; wherein each ontology refers to a new entity after entities with the same concept are merged; Performing knowledge information fusion on the first form triple, the second form triple and the third form triple to obtain ontology data; According to the multiple ontologies, the total fusion relationship and the ontology data, knowledge is stored through the graph database to obtain the waterlogging scheduling knowledge graph.

6. The method according to claim 5, characterized in that The waterlogging dispatch knowledge graph stores a plurality of triplet knowledge sets corresponding to respective waterlogging dispatches; The performing of knowledge retrieval or knowledge reasoning on the waterlogging dispatching knowledge graph to obtain a waterlogging target dispatching plan includes: According to the precipitation process data, knowledge retrieval or knowledge reasoning is performed through the graph database to obtain a triple knowledge set corresponding to the precipitation process data; The triplet knowledge set is integrated to obtain the waterlogging target scheduling plan.

7. The method according to claim 6, characterized in that The waterlogging target scheduling plan includes a first waterlogging scheduling plan or a second waterlogging scheduling plan; The first waterlogging dispatching plan is a waterlogging dispatching plan obtained by performing knowledge retrieval on the graph database; The second waterlogging dispatching plan is a waterlogging dispatching plan obtained by performing knowledge reasoning on the graph database, wherein the second waterlogging dispatching plan is obtained by jointly processing the graph database and empirical results.

8. A waterlogging dispatching device based on knowledge graph, characterized in that: include: A data acquisition module, used to acquire a waterlogging data source, wherein the waterlogging data source includes multiple data sources; A knowledge graph module is used to construct an ontology library corresponding to each of the data sources according to the multiple data sources, and to fill each of the ontology libraries with knowledge to obtain a knowledge graph corresponding to each of the ontology libraries; The waterlogging dispatching module is used to perform knowledge fusion on the knowledge graphs corresponding to each ontology library to obtain a waterlogging dispatching knowledge graph; and perform knowledge retrieval or knowledge reasoning on the waterlogging dispatching knowledge graph to obtain a waterlogging target dispatching plan.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; When the processor executes the computer-executable instructions stored in the memory, it is used to implement a waterlogging scheduling method based on a knowledge graph as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement a knowledge graph-based waterlogging scheduling method as described in any one of claims 1 to 7.

Images