Method and system for constructing space-time node switch graph based on graph database

Abstract

The invention discloses a method and a system for constructing a space-time node switch graph based on a graph database, and relates to the field of power system modeling, and the method comprises the following steps: aggregating data related to power system topology, and combining hierarchical nodes and relation loops; constructing a basic graph model, associating physical equipment through topological connection, and generating a node switch graph model; the model is initialized into a static model, attributes of nodes and edges are updated according to the real-time switching state and equipment operation data, and a space-time diagram structure is formed; constructing a space-time node switch attribute graph model, and introducing time evolution to form a space-time node switch evolution graph model; according to the method, the time sequence change and the dynamic characteristics of the power system can be more accurately represented, the functions of real-time monitoring, fault diagnosis and optimal scheduling are provided, and the reliability, the safety and the efficiency of the system are remarkably improved; the flexibility of modeling and management is enhanced, problems can be found in time, measures can be taken, and therefore the operation strategy and the energy utilization rate of a power system are optimized.

Description

Technical Field

[0001] The present invention relates to the field of power system modeling, and in particular to a method and system for constructing a spatiotemporal node switch graph based on a graph database. Background Art

[0002] In power system modeling, building a power grid topology model is of great significance for the digitalization and real-time operation management of the power system. The use of a graph database can more intuitively present the topological structure between devices and support real-time updates and dynamic adjustments to adapt to changes and expansions in the power system.

[0003] In traditional power system modeling methods, node switch graph models are often used to represent the power grid topology. This model represents power devices as nodes, and the connections between devices as switches. However, the traditional node switch graph model lacks the representation of spatiotemporal attributes and cannot accurately reflect the timing changes and dynamic characteristics of the power system. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to more accurately represent the time sequence changes and dynamic characteristics of the power system by introducing time and space attributes.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for constructing a spatiotemporal node switch graph based on a graph database, comprising:

[0008] Aggregate data related to the power system topology, merge hierarchical nodes according to the conceptual type of the data; find relationship loops, merge the loops, and form a merged relationship;

[0009] Build a basic graph model based on the aggregated power data;

[0010] Based on the basic graph model, the physical devices are associated through topological connection points to build a node switch graph model;

[0011] The node switch graph model generated by initialization is a static model. According to the real-time switch status data and equipment operation measurement data, the attributes of nodes and edges are updated over time to form a spatiotemporal graph structure.

[0012] Based on the spatiotemporal graph structure, a spatiotemporal node switch attribute graph model is constructed;

[0013] The spatiotemporal node switch attribute graph model is further expanded, the time evolution of node and edge attributes is introduced, and a spatiotemporal node switch evolution graph model is constructed.

[0014] As a preferred solution for the method of constructing a spatiotemporal node switch graph based on a graph database, wherein:

[0015] The relational data related to the power system topology includes:

[0016] Abstract object: organization / relationship node model; physical object: device node model; measurement object: measurement node model.

[0017] As a preferred solution for the method of constructing a spatiotemporal node switch graph based on a graph database, wherein:

[0018] The construction of the basic graph model includes:

[0019] Physical device nodes, logical management nodes and analysis and calculation nodes are defined and associated; physical objects are defined as physical device nodes, abstract objects are defined as logical management nodes, and measurement objects and results of operations based on measurement data are defined as analysis and calculation nodes.

[0020] As a preferred solution for the method of constructing a spatiotemporal node switch graph based on a graph database, wherein:

[0021] The constructing of the node switch graph model comprises:

[0022] The physical devices in the power grid topology physical model are modeled as nodes in the graph, and the switches and circuit breakers are modeled as edges in the graph to form a node switch graph model; all physical devices are associated with topological connection points to establish topological connection relationships between devices.

[0023] As a preferred solution for the method of constructing a spatiotemporal node switch graph based on a graph database, wherein:

[0024] The forming of the space-time graph structure comprises:

[0025] The properties of nodes and edges are set with time labels, and the actual measurement values ​​are collected at the minute level and imported into the graph model. The properties of nodes and edges in the node switch graph model are updated over time.

[0026] As a preferred solution for the method of constructing a spatiotemporal node switch graph based on a graph database, wherein:

[0027] The construction of the spatiotemporal node switch attribute graph model includes:

[0028] The space-time graph is defined as:

[0029] G(t)=(V(t),E(t))=(X(t),A))

[0030] Where V(t) is the node set at time t, E(t) is the edge set at time t; X(t) represents the time-varying node features at time t, A is the static topology of the graph; X(t) is a set of time-varying attributes of V(t) and E(t).

[0031] As a preferred solution for the method of constructing a spatiotemporal node switch graph based on a graph database, wherein:

[0032] The construction of the spatiotemporal node switch evolution graph model comprises:

[0033] The mathematical representation of the space-time graph is further extended to include the time evolution of node and edge attributes. The attributes of the node v_i(t) are represented by the vector a_i(t), and the attributes of the edge e_j(t) are represented by the vector b_j(t). The space-time graph is represented as:

[0034] G(t)=(V(t,a(t)),E(t,b(t)))

[0035] Where a(t) = [a_1(t), a_2(t), ..., a_n(t)] and b(t) = [b_1(t), b_2(t), ..., b_m(t)] represent the attribute vectors of all nodes and edges at time t; let a set of time indexes τ = {t_1, t_2, ..., t_c}, where each t_c represents a time point, and the evolution of the space-time graph over time is defined by functions and state transition equations:

[0036] V tk,tl ∈υ t ,f:G(t)×τ→G(t′)

[0037] In the graph G(t), the temporal feature set of the node is denoted as υ_t, where each node V_{t_k,t_l} represents the change of the node attribute from time t_k to t_l.

[0038] In a second aspect, an embodiment of the present invention provides a system for constructing a spatiotemporal node switch graph based on a graph database, including:

[0039] The power data aggregation module is used to aggregate data related to the power system topology, merge hierarchical nodes according to the conceptual type of the data, find relationship loops, merge the loops, and form a merged relationship;

[0040] A basic graph model building module is used to build a basic graph model based on aggregated power data;

[0041] A node switch graph model building module is used to associate physical devices through topological connection points based on the basic graph model to build a node switch graph model;

[0042] The spatiotemporal graph structure generation module is used to initialize the generated node switch graph model as a static model. According to the real-time switch status data and equipment operation measurement data, the attributes of the nodes and edges are updated over time to form a spatiotemporal graph structure.

[0043] A spatiotemporal node switch attribute graph model construction module is used to construct a spatiotemporal node switch attribute graph model based on the spatiotemporal graph structure;

[0044] The spatiotemporal node switch evolution graph model construction module is used to further expand the spatiotemporal node switch attribute graph model, introduce the time evolution of node and edge attributes, and construct the spatiotemporal node switch evolution graph model.

[0045] In a third aspect, an embodiment of the present invention provides a computing device, including:

[0046] Memory and processor;

[0047] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the one or more programs are executed by the one or more processors, the one or more processors implement the method for constructing a spatiotemporal node switch graph based on a graph database as described in any embodiment of the present invention.

[0048] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the method of constructing a spatiotemporal node switch graph based on a graph database.

[0049] Beneficial effects of the present invention: The technical solution of the present invention can more accurately represent the time series changes and dynamic characteristics of the power system by introducing spatiotemporal attributes and utilizing the advantages of the graph database, and provide functions such as real-time monitoring, fault diagnosis and optimized scheduling, thereby improving the reliability, safety and efficiency of the power system; by using a spatiotemporal graph model with spatiotemporal attributes for nodes and edges, the time series changes and dynamic characteristics of the power system can be more accurately represented. This helps to better understand and analyze the operating status of the power system; the graph database supports real-time updates and dynamic adjustments: the use of the graph database can more intuitively present the topological structure between devices, and supports real-time updates and dynamic adjustments to adapt to the changes and expansion of the power system. This provides more efficient and flexible modeling and management capabilities; through the query and analysis functions of the graph database, the power system can be monitored and fault diagnosed in real time. This helps to find problems in a timely manner and take corresponding measures to improve the reliability and safety of the system; the spatiotemporal node switch graph model constructed based on the graph database can be used for the optimized scheduling of the power system. Through the analysis and calculation of the model, an optimized operation strategy can be obtained to improve the efficiency and energy utilization of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0051] Figure 1 It is an overall flow chart of the method for constructing a spatiotemporal node switch graph based on a graph database according to the first embodiment of the present invention;

[0052] Figure 2 It is a schematic diagram of constructing a spatiotemporal node switch graph according to the method for constructing a spatiotemporal node switch graph based on a graph database described in the first embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0056] Example 1

[0057] Reference Figure 1-Figure 2 , which is the first embodiment of the present invention, provides a method for constructing a spatiotemporal node switch graph based on a graph database, comprising:

[0058] S1: Aggregate data related to the power system topology, merge hierarchical nodes according to the conceptual type of the data; find relationship loops, merge the loops, and form a merged relationship;

[0059] In an embodiment of the present application, relational data related to the power system topology includes an abstract object: an organization / relationship node model; a physical object: an equipment node model; and a measurement object: a measurement node model.

[0060] Specifically, relational data related to power system topology include:

[0061] (1) Abstract objects (organization / relationship node model): interval class, voltage level class, plant class, control area class, reference voltage class;

[0062] (2) Physical object (device node model):

[0063] Single-ended components: synchronous generators, loads, parallel compensation, and grounding switches;

[0064] Two-terminal components: circuit breakers, switch types, AC lines (including AC line segments and AC line endpoints), DC lines (including DC line segments and DC line endpoints, converters), transformers (including transformer windings, transformer tap types), series compensators

[0065] (3) Measurement objects (measurement node models): telemetry class, telesignaling class, other telemetry class, and other telesignaling class.

[0066] Node aggregation: merge hierarchical nodes according to concept types (physical concepts and abstract concepts).

[0067] Relationship merging: Based on the relationship conduction principle, find the relationship loops, merge the loops, and form a merged relationship.

[0068] S2: Build a basic graph model based on the aggregated power data;

[0069] In an embodiment of the present application, constructing a basic graph model includes: defining and associating physical device nodes, logical management nodes, and analysis and computing nodes; defining physical objects as physical device nodes, abstract objects as logical management nodes, and measurement objects and results of operations based on measurement data as analysis and computing nodes.

[0070] S3: Based on the basic graph model, the physical devices are associated through topological connection points to build a node switch graph model;

[0071] In an embodiment of the present application, constructing a node switch graph model includes:

[0072] The physical devices in the power grid topology physical model are modeled as nodes in the graph, and the switches and circuit breakers are modeled as edges in the graph to form a node switch graph model; all physical devices are associated with topological connection points to establish topological connection relationships between devices.

[0073] Specifically, the physical devices in the power grid topology physical model include transformers, busbars, generators, loads, lines, etc.

[0074] It should be noted that the number of switches and circuit breakers is several times the number of transformers, busbars, generators, loads, lines, etc. If the switches and circuit breakers in the physical device nodes are modeled as edges, the number of vertices and corresponding edges in the graph database will be greatly reduced, which can reduce the number of hops in the graph traversal and greatly improve the query access efficiency of the graph database.

[0075] S4: The node switch graph model generated by initialization is a static model. According to the real-time switch status data and equipment operation measurement data, the attributes of nodes and edges are updated over time to form a spatiotemporal graph structure;

[0076] In the embodiment of the present application, forming a spatiotemporal graph structure includes:

[0077] The properties of nodes and edges are set with time labels, and the actual measurement values ​​are collected at the minute level and imported into the graph model. The properties of nodes and edges in the node switch graph model are updated over time.

[0078] Specifically, the node switch graph model generated by initialization is a static model that is loaded once. According to the real-time updated switch status data (telesignaling) and equipment operation measurement data (telemetry), the attributes of nodes and edges will change over time, and the node switch graph model will also be updated in real time accordingly. The graph structure with time-series changes can be considered as a space-time graph.

[0079] Historical measurement data can be stored in a database or on a blockchain. This can be done automatically after the schema model is written.

[0080] It should be noted that because graph databases are relatively resource-intensive, historical measurement data of a short time scale, such as 96 points a day, can be stored in the graph database (historical measurements can also be modeled as vertices); historical data of a longer time scale is best stored in a relational database or blockchain.

[0081] S5: Based on the spatiotemporal graph structure, a spatiotemporal node switch attribute graph model is constructed;

[0082] In an embodiment of the present application, constructing a spatiotemporal node switch attribute graph model includes:

[0083] The space-time graph is defined as:

[0084] G(t)=(V(t),E(t))=(X(t),A))

[0085] Where V(t) is the set of nodes at time t, E(t) is the set of edges at time t. X(t) represents the time-varying node features at time t, A is the static topology of the graph. X(t) is a set of time-varying attributes of V(t) and E(t).

[0086] It should be noted that in the space-time graph, each node and each edge has space-time attributes, which means that they can represent both spatial association and temporal continuity through attributes. The space-time node switch graph keeps the graph structure unchanged during the continuous time section update, but the node attributes will change. Figure 2 As shown in , the connection state attribute of the switch node will change from the connected state (1) at time t0 and t1 to the disconnected state (0) at time t2, and the active power and reactive power on the transmission line will also have different values ​​at different time sections. In a timing graph, nodes and edges can have various attributes, such as V(t) = v_1(t), v_2(t), ..., v_i(t), where v_i(t) represents the attribute of node i at time t. Similarly, edge attributes can be expressed as E(t) = e_1(t), e_2(t), ..., e_j(t), where e_j(t) represents the attribute of edge e at time t.

[0087] S6: Further expand the spatiotemporal node switch attribute graph model, introduce the time evolution of node and edge attributes, and construct a spatiotemporal node switch evolution graph model;

[0088] In an embodiment of the present application, constructing a spatiotemporal node switch evolution graph model includes:

[0089] The mathematical representation of the space-time graph is further extended to include the time evolution of node and edge attributes. The attributes of the node v_i(t) are represented by the vector a_i(t), and the attributes of the edge e_j(t) are represented by the vector b_j(t). The space-time graph is represented as:

[0090] G(t)=(V(t,a(t)),E(t,b(t)))

[0091] Where a(t) = [a_1(t), a_2(t), ..., a_n(t)] and b(t) = [b_1(t), b_2(t), ..., b_m(t)] represent the attribute vectors of all nodes and edges at time t; let a set of time indexes τ = {t_1, t_2, ..., t_c}, where each t_c represents a time point, and the evolution of the space-time graph over time is defined by functions and state transition equations:

[0092] V tk,tl ∈υ t ,f:G(t)×τ→G(t′)

[0093] In the graph G(t), the temporal feature set of the node is denoted as υ_t, where each node V_{t_k,t_l} represents the change of the node attribute from time t_k to t_l.

[0094] It should be noted that the evolution of the space-time graph over time can also be defined by other rule-based methods; the construction process of the space-time node switch graph is a virtual replication based on the actual operating data and graph model of the power system, which aims to simulate and predict the behavior, performance and status of the power system based on synchronized real-time data. Therefore, the constructed space-time node switch graph can be considered as a true digital twin of the power system.

[0095] The above is a schematic scheme of the method for constructing a spatiotemporal node switch graph based on a graph database in this embodiment. It should be noted that the technical scheme of the system for constructing a spatiotemporal node switch graph based on a graph database and the technical scheme of the method for constructing a spatiotemporal node switch graph based on a graph database belong to the same concept. For details not described in detail in the technical scheme of the system for constructing a spatiotemporal node switch graph based on a graph database in this embodiment, please refer to the description of the technical scheme of the method for constructing a spatiotemporal node switch graph based on a graph database.

[0096] In this embodiment, the system for constructing a spatiotemporal node switch graph based on a graph database includes:

[0097] The power data aggregation module is used to aggregate data related to the power system topology, merge hierarchical nodes according to the conceptual type of the data, find relationship loops, merge the loops, and form a merged relationship;

[0098] A basic graph model building module is used to build a basic graph model based on aggregated power data;

[0099] A node switch graph model building module is used to associate physical devices through topological connection points based on the basic graph model to build a node switch graph model;

[0100] The spatiotemporal graph structure generation module is used to initialize the generated node switch graph model as a static model. According to the real-time switch status data and equipment operation measurement data, the attributes of the nodes and edges are updated over time to form a spatiotemporal graph structure.

[0101] A spatiotemporal node switch attribute graph model construction module is used to construct a spatiotemporal node switch attribute graph model based on the spatiotemporal graph structure;

[0102] The spatiotemporal node switch evolution graph model construction module is used to further expand the spatiotemporal node switch attribute graph model, introduce the time evolution of node and edge attributes, and construct the spatiotemporal node switch evolution graph model.

[0103] This embodiment further provides a computing device, which is applicable to the method of constructing a spatiotemporal node switch graph based on a graph database, and includes:

[0104] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method of constructing a spatiotemporal node switch graph based on a graph database as proposed in the above embodiment.

[0105] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for constructing a spatiotemporal node switch graph based on a graph database as proposed in the above embodiment is implemented.

[0106] The storage medium proposed in this embodiment and the method for constructing a spatiotemporal node switch graph based on a graph database proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0107] Example 2

[0108] The following is an embodiment of the present invention, which provides a method for constructing a spatiotemporal node switch graph based on a graph database. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0109] In the 2749 bus system in a western province, this time-space node switch diagram method is used. When the topology remains unchanged, the state estimation calculation time is about 130 milliseconds. When the topology changes, the calculation time is about 250 milliseconds, the flow calculation time is about 40 milliseconds, and the detailed flow calculation time for 100 anticipated faults is less than 650 milliseconds, significantly improving the data processing performance.

[0110] Comparison between the graph calculation method based on this node switch graph model and the current calculation method: the total calculation time for state estimation, online power flow and anticipated fault analysis is increased by more than 20 times, the data reading time is reduced to 0, the core calculation time is increased by 10 times, and the result output time is increased by nearly 50 times.

[0111] It can be seen that the spatiotemporal node switch graph model constructed based on the graph database significantly improves the computational efficiency and reliability of the power system, and provides effective support for real-time monitoring, fault diagnosis and optimal scheduling.

[0112] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing a spatiotemporal node switch graph based on a graph database, characterized in that: include: Aggregate data related to the power system topology, merge hierarchical nodes according to the conceptual type of the data; find relationship loops, merge the loops, and form a merged relationship; Build a basic graph model based on the aggregated power data; Based on the basic graph model, the physical devices are associated through topological connection points to build a node switch graph model; The node switch graph model generated by initialization is a static model. According to the real-time switch status data and equipment operation measurement data, the attributes of nodes and edges are updated over time to form a spatiotemporal graph structure. Based on the spatiotemporal graph structure, a spatiotemporal node switch attribute graph model is constructed; The spatiotemporal node switch attribute graph model is further expanded, the time evolution of node and edge attributes is introduced, and a spatiotemporal node switch evolution graph model is constructed.

2. The method for constructing a spatiotemporal node switch graph based on a graph database according to claim 1, characterized in that: The relational data related to the power system topology includes: Abstract object: organization / relationship node model; physical object: device node model; measurement object: measurement node model.

3. The method for constructing a spatiotemporal node switch graph based on a graph database according to claim 2, characterized in that: The construction of the basic graph model includes: Physical device nodes, logical management nodes and analysis and calculation nodes are defined and associated; physical objects are defined as physical device nodes, abstract objects are defined as logical management nodes, and measurement objects and results of operations based on measurement data are defined as analysis and calculation nodes.

4. The method for constructing a spatiotemporal node switch graph based on a graph database according to claim 3, characterized in that: The constructing of the node switch graph model comprises: The physical devices in the power grid topology physical model are modeled as nodes in the graph, and the switches and circuit breakers are modeled as edges in the graph to form a node switch graph model; all physical devices are associated with topological connection points to establish topological connection relationships between devices.

5. The method for constructing a spatiotemporal node switch graph based on a graph database according to claim 4, characterized in that: The forming of the space-time graph structure comprises: The properties of nodes and edges are set with time labels, and the actual measurement values ​​are collected at the minute level and imported into the graph model. The properties of nodes and edges in the node switch graph model are updated over time.

6. The method for constructing a spatiotemporal node switch graph based on a graph database according to claim 5, characterized in that: The construction of the spatiotemporal node switch attribute graph model includes: The space-time graph is defined as: G(t)=(V(t),E(t))=(X(t),A)) Where V(t) is the node set at time t, E(t) is the edge set at time t; X(t) represents the time-varying node features at time t, A is the static topology of the graph; X(t) is a set of time-varying attributes of V(t) and E(t).

7. The method for constructing a spatiotemporal node switch graph based on a graph database according to claim 6, characterized in that: The construction of the spatiotemporal node switch evolution graph model comprises: The mathematical representation of the space-time graph is further extended to include the time evolution of node and edge attributes. The attributes of the node v_i(t) are represented by the vector a_i(t), and the attributes of the edge e_j(t) are represented by the vector b_j(t). The space-time graph is represented as: G(t)=(V(t,a(t)),E(t,b(t))) Where a(t) = [a_1(t), a_2(t), ..., a_n(t)] and b(t) = [b_1(t), b_2(t), ..., b_m(t)] represent the attribute vectors of all nodes and edges at time t; let a set of time indexes τ = {t_1, t_2, ..., t_c}, where each t_c represents a time point, and the evolution of the space-time graph over time is defined by functions and state transition equations: V tk,tl ∈υ t ,f:G(t)×τ→G(t′) In the graph G(t), the temporal feature set of the node is denoted as υ_t, where each node V_{t_k,t_l} represents the change of the node attribute from time t_k to t_l.

8. A system using the method for constructing a spatiotemporal node switch graph based on a graph database as described in any one of claims 1 to 7, characterized in that: include: The power data aggregation module is used to aggregate data related to the power system topology, merge hierarchical nodes according to the conceptual type of the data, find relationship loops, merge the loops, and form a merged relationship; A basic graph model building module is used to build a basic graph model based on aggregated power data; A node switch graph model building module is used to associate physical devices through topological connection points based on the basic graph model to build a node switch graph model; The spatiotemporal graph structure generation module is used to initialize the generated node switch graph model as a static model. According to the real-time switch status data and equipment operation measurement data, the attributes of the nodes and edges are updated over time to form a spatiotemporal graph structure. A spatiotemporal node switch attribute graph model construction module is used to construct a spatiotemporal node switch attribute graph model based on the spatiotemporal graph structure; The spatiotemporal node switch evolution graph model construction module is used to further expand the spatiotemporal node switch attribute graph model, introduce the time evolution of node and edge attributes, and construct the spatiotemporal node switch evolution graph model.

9. A computing device comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for constructing a spatiotemporal node switch graph based on a graph database as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for constructing a spatiotemporal node switch graph based on a graph database as described in any one of claims 1 to 7.

Images