Model training method and device, business execution method and device and storage medium

Abstract

According to the model training method, the business execution method, the business execution device and the storage medium, the initial graph of the target object can be acquired, and the initial graph and the preset external control information are input into the to-be-trained target model, so that the target model carries out business execution according to the initial graph; predicting updated attribute information corresponding to each node of the target object under external control corresponding to the external control information, and updating the initial graph according to the updated attribute information to obtain an updated graph, and determining a loss value according to the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and training the target model according to the loss value.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a model training method, a business execution method, a device, and a storage medium. Background Art

[0002] In recent years, with the rapid development of computer technology, simulation technology has made significant progress, and simulation tools have emerged in an endless stream. At present, simulation tools often simulate and analyze objects based on the finite element method, that is, by decomposing the object into many small parts (called finite elements) and analyzing based on these finite elements, the behavior and performance of the object under different conditions are simulated.

[0003] For example, simulation tools can be used to simulate the behavior of objects under various external control conditions (such as pressure changes, temperature changes, etc.), so as to analyze the deformation process of objects under pressure, the heating and curing process of composite materials, etc.

[0004] However, when using existing simulation tools for simulation, the local features of the object are often not captured effectively, resulting in low simulation accuracy. Summary of the invention

[0005] This specification provides a model training method, a business execution method, a device and a storage medium to partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This specification provides a model training method, including:

[0008] Acquire an initial graph of the target object, the initial graph is a heterogeneous graph consisting of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the target object, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to the multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the target object at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the target object at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the target object;

[0009] Inputting the initial graph and the preset external control information into the target model to be trained, so that the target model predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information according to the initial graph, and updates the initial graph according to the updated attribute information to obtain an updated graph;

[0010] The loss value is determined based on the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and the target model is trained based on the loss value, and there is a positive correlation between the loss value and the deviation.

[0011] Optionally, obtaining an initial image of the target object specifically includes:

[0012] Performing finite element mesh division on the target object to obtain mesh units corresponding to the target object;

[0013] For each grid unit, based on the initial material property information and initial unit state information corresponding to the target object at the grid unit, a grid unit node corresponding to the grid unit is constructed; and, for each vertex, based on the initial position information and initial vertex state information corresponding to the target object at the vertex, a vertex node corresponding to the vertex is constructed;

[0014] Based on the association relationship between each grid unit and each vertex in the target object, an edge between each grid unit node and each vertex node is constructed to obtain an initial graph of the target object.

[0015] Optionally, the initial graph and the preset external control information are input into the target model to be trained, so that the target model predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information according to the initial graph, specifically including:

[0016] The initial graph and the preset external control information are input into the target model to be trained, so that the target model determines the attribute association relationship between different initial attribute information corresponding to each node for each node, and predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information based on the node association relationship corresponding to each edge contained in the initial graph and the attribute association relationship corresponding to each node.

[0017] Optionally, determining the loss value according to the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object specifically includes:

[0018] Determine a first loss value according to a deviation between updated attribute information corresponding to each node in the updated graph and label attribute information corresponding to each node in the label graph corresponding to the target object, and determine a second loss value according to preset physical constraint information and updated attribute information corresponding to at least some of the nodes in the updated graph, wherein the first loss value is positively correlated with the deviation, and the more the updated attribute information corresponding to at least some of the nodes in the updated graph conforms to the physical constraint condition corresponding to the physical constraint information, the smaller the second loss value;

[0019] A loss value is determined according to the first loss value and the second loss value.

[0020] This specification provides a service execution method, including:

[0021] Acquire an initial graph of the object to be simulated, the initial graph is a heterogeneous graph consisting of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the object to be simulated, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to the multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the object to be simulated at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the object to be simulated at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the object to be simulated;

[0022] Inputting the initial graph and the preset external control information into a pre-trained target model, so that the target model predicts updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information according to the initial graph, and updating the initial graph according to the updated attribute information to obtain an updated graph, wherein the target model is trained by the above-mentioned model training method;

[0023] According to the attribute information corresponding to each node contained in the updated graph, a target simulation service is performed on the object to be simulated.

[0024] Optionally, the initial graph and the preset external control information are input into a pre-trained target model so that the target model predicts updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information according to the initial graph, specifically including:

[0025] The initial graph and preset external control information are input into a pre-trained target model so that the target model determines, for each node, the attribute association relationship between different initial attribute information corresponding to the node, and predicts the updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information based on the node association relationship corresponding to each edge contained in the initial graph and the attribute association relationship corresponding to each node.

[0026] This specification provides a model training device, including:

[0027] Acquisition module: used to acquire an initial graph of a target object, wherein the initial graph is a heterogeneous graph consisting of a plurality of nodes and edges between the nodes, wherein each node records initial attribute information corresponding to the node, and the nodes include vertex nodes and grid unit nodes, wherein each grid unit node corresponds to a grid unit divided in the target object, and the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to a plurality of vertex nodes, and the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the target object at the grid unit, and the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the target object at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the target object;

[0028] Prediction module: used for inputting the initial graph and the preset external control information into the target model to be trained, so that the target model predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information according to the initial graph, so as to update the initial graph according to the updated attribute information to obtain the updated graph;

[0029] Training module: used to determine the loss value according to the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and train the target model according to the loss value, and there is a positive correlation between the loss value and the deviation.

[0030] This specification provides a service execution device, including:

[0031] Acquisition module: used to acquire an initial graph of the object to be simulated, the initial graph is a heterogeneous graph composed of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the object to be simulated, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the object to be simulated at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the object to be simulated at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the object to be simulated;

[0032] Prediction module: used for inputting the initial graph and the preset external control information into the pre-trained target model, so that the target model predicts the updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information according to the initial graph, and updates the initial graph according to the updated attribute information to obtain the updated graph, and the target model is trained by the above-mentioned model training method;

[0033] Execution module: used for executing target simulation service on the object to be simulated according to the attribute information corresponding to each node contained in the updated graph.

[0034] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned model training method or business execution method.

[0035] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned model training method or business execution method when executing the program.

[0036] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0037] The model training method provided in this specification can obtain an initial graph of a target object, input the initial graph and preset external control information into a target model to be trained, so that the target model can predict, based on the initial graph, the updated attribute information corresponding to each node of the target object under external control corresponding to the external control information, so as to update the initial graph based on the updated attribute information to obtain an updated graph, determine the loss value based on the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and train the target model based on the loss value.

[0038] It can be seen that in the above model training process, the target model can obtain relatively rich attribute information corresponding to each grid unit node and attribute information corresponding to each vertex node from the initial graph of the target object. In addition, the node association relationship between each grid unit node and each vertex node can be obtained from the initial graph, and then the updated attribute information of each node corresponding to the target object under external control can be predicted based on the relatively rich attribute information and node association relationship, thereby greatly improving the prediction accuracy of the target model. In addition, the above target model can quickly predict the relatively rich local features corresponding to the target object under external control, thereby greatly improving the prediction efficiency of the target model. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0040] Figure 1 A flowchart of a model training method provided in this specification;

[0041] Figure 2 A schematic diagram of an initial diagram provided for this specification;

[0042] Figure 3 A schematic diagram of the process of a business execution method provided in this specification;

[0043] Figure 4 A schematic diagram of a model training device provided in this specification;

[0044] Figure 5 A schematic diagram of a service execution device provided in this specification;

[0045] Figure 6 A method corresponding to the Figure 1 or Figure 3 Schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0047] In recent years, with the rapid development of computer technology, simulation technology has made significant progress, and simulation tools have emerged in an endless stream. At present, simulation tools often simulate and analyze objects based on the finite element method, that is, by decomposing the object into many small parts (called finite elements) and analyzing based on these finite elements, the behavior and performance of the object under different conditions can be simulated. For example, simulation tools can be used to simulate the behavior of objects under various external controls (such as pressure changes, temperature changes, etc.), so as to analyze the deformation process of the object under pressure, the heating and curing process of composite materials, etc. However, when using existing simulation tools for simulation, the local characteristics of the object are often not effectively captured, resulting in low simulation accuracy.

[0048] Therefore, this specification provides a model training method, which can effectively solve the problems in the prior art.

[0049] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0050] Figure 1 A flow chart of a model training method provided in this specification includes the following steps:

[0051] S101: Acquire an initial graph of a target object, wherein the initial graph is a heterogeneous graph consisting of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the target object, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the target object at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the target object at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the target object.

[0052] The execution subject of the model training method involved in this specification can be a terminal device such as a desktop computer, a laptop computer, or a client installed in the terminal device, or a server. The following only takes the server as the execution subject as an example to illustrate the model training method in the embodiment of this specification.

[0053] In this specification, the server can first obtain an initial graph of the target object, and use the obtained initial graph as sample data to perform model training on the target model, so as to perform corresponding simulation services based on the output results of the trained target model. Among them, the initial graph is a heterogeneous graph composed of multiple nodes and edges between each node, and the edge between any two nodes can be used to characterize the node association relationship between the two nodes in the target object. Correspondingly, in the initial graph, for each node, the initial attribute information corresponding to the node is recorded in the node. In addition, the nodes in the initial graph can be divided into two types: vertex nodes and grid unit nodes, wherein each grid unit node corresponds to a grid unit divided in the target object, and the grid unit corresponding to each grid unit node is a closed area surrounded by vertices corresponding to multiple vertex nodes. The specific initial graph of the target object can be referred to as follows Figure 2 .

[0054] Figure 2 This is a schematic diagram of an initial diagram provided in this specification.

[0055] Depend on Figure 2 It can be seen that the target object may correspond to multiple divided grid units, and the grid unit is a closed area surrounded by eight vertices. Accordingly, the initial graph of the target object contains grid unit nodes corresponding to each grid unit and vertex nodes corresponding to each vertex, wherein the vertex node corresponding to each vertex can be connected to the grid unit node corresponding to the grid unit where the vertex is located. At the same time, the vertex node corresponding to each vertex can also be connected to the vertex node corresponding to the adjacent vertex of the vertex, and the grid unit node corresponding to each grid unit can be connected to the grid unit node corresponding to the adjacent grid unit of the grid unit. Of course, Figure 2 It is just a form of initial graph. In practical applications, different initial graphs can be obtained according to actual needs, and this manual will not list them one by one here.

[0056] In the initial graph, the initial attribute information corresponding to the grid unit node may include the initial material attribute information and initial unit state information corresponding to the target object at the grid unit. The material attribute information may refer to the thermal conductivity, specific heat capacity, hardness, Young's modulus, Poisson's ratio, etc. corresponding to the target object at the grid unit, and the unit state information may refer to the temperature, degree of solidification, stress, etc. corresponding to the target object at the grid unit. The initial material attribute information refers to the material attribute information of the target object at the initial time (i.e., not under external control), and the initial unit state information refers to the unit state information of the target object at the initial time (i.e., not under external control). In the above description of the material attribute information and the unit state information, no distinction is made between the states of the target object, that is, it can be an explanation of the material attribute information and the unit state information of the target object at the initial time (i.e., not under external control), or it can be an explanation of the material attribute information and the unit state information of the target object under external control (i.e., the updated attribute information corresponding to the grid unit node mentioned later).

[0057] For each vertex node, the initial attribute information corresponding to the vertex node may include the initial position information (such as coordinate information) and initial vertex state information of the target object at the vertex corresponding to the vertex node, and the vertex state information may refer to the temperature, stress, etc. of the target object at the vertex. The initial vertex state information refers to the vertex state information of the target object at the initial time (i.e., not under external control). In the above description of the vertex state information, no distinction is made between the states of the target object, that is, it can be an explanation of the vertex state information of the target object at the initial time (i.e., not under external control), or it can be an explanation of the vertex state information of the target object under external control (i.e., the updated attribute information corresponding to the vertex node mentioned later).

[0058] For example, in order to simulate the curing of a target object (such as an epoxy resin-based composite material) under heating conditions, an initial graph corresponding to the epoxy resin-based composite material can be constructed. In the initial graph corresponding to the epoxy resin-based composite material, the initial attribute information corresponding to the vertex node in the initial graph may include the initial coordinate information of the target object at the vertex corresponding to the vertex node, the initial temperature at the vertex corresponding to the vertex node, and the initial attribute information corresponding to the grid unit node in the initial graph may include the initial temperature of the target object at the grid unit corresponding to the grid unit node (the average value of the temperature at each vertex in the grid unit), the initial degree of curing, the initial curing rate, and the initial thermal conductivity. The corresponding node association relationship in the initial graph may be, for example, the association relationship between the positions of the nodes, the thermal conduction relationship between the temperatures corresponding to the nodes, etc.

[0059] For another example, in order to simulate the deformation of a target object (such as plastic, rubber and other polymer materials) under pressure, an initial graph corresponding to plastic, rubber and other polymer materials can be constructed, wherein the attribute information corresponding to the vertex node in the initial graph may include the initial coordinate information of the target object at the vertex corresponding to the vertex node, the initial stress and initial strain at the vertex corresponding to the vertex node, and the attribute information corresponding to the grid unit node in the initial graph includes the initial stress (the average value of the stress at each vertex in the grid unit), the initial strain (the average strain at each vertex in the grid unit), the initial Young's modulus and the initial Poisson's ratio of the target object at the grid unit corresponding to the grid unit node. The node association relationship in the initial graph may be, for example, the association relationship between the positions of the nodes, the association relationship between the stresses corresponding to the nodes, the association relationship between the strains, etc.

[0060] It should be noted that the initial graph of the target object can be directly obtained from the graph database. Of course, the initial graph can also be constructed based on the finite element mesh division result by dividing the target object into finite elements.

[0061] Specifically, the server can perform finite element meshing on the target object to obtain the grid units corresponding to the target object. For each grid unit, the grid unit node corresponding to the grid unit can be constructed based on the initial material property information and initial unit state information corresponding to the target object at the grid unit. In addition, for each vertex, the vertex node corresponding to the vertex can be constructed based on the initial position information and initial vertex state information corresponding to the target object at the vertex. Furthermore, based on the association relationship between each grid unit and each vertex in the target object, the edge between each grid unit node and each vertex node can be constructed to obtain the initial graph of the target object. For example, the edge between each grid unit node and each vertex node in the initial graph can be constructed based on the association relationship between adjacent vertices, the association relationship between adjacent grid units, and the association relationship between each vertex and the grid unit where the vertex is located.

[0062] In addition, since there are multiple types of nodes (such as vertex nodes and grid unit nodes) and edge types (such as edges between adjacent vertex nodes, edges between adjacent grid unit nodes, and edges between grid unit nodes and vertex nodes) mentioned above, the initial graph in this specification can be in the form of a heterogeneous graph, where a heterogeneous graph refers to a graph containing multiple types of nodes or edges.

[0063] S102: Input the initial graph and preset external control information into the target model to be trained, so that the target model predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information based on the initial graph, and updates the initial graph according to the updated attribute information to obtain an updated graph.

[0064] In this specification, in order to simulate the state of the target object under external control such as temperature changes and pressure changes, the corresponding external control information can be input into the target model during the model training process, so that the trained target model can predict various information of the target object under external control corresponding to the external control information.

[0065] The server can input the initial graph of the target object and the preset external control information into the target model to be trained (such as a heterogeneous graph network model). The target model can predict the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information based on the input initial graph, so as to update the initial graph according to the predicted updated attribute information to obtain the updated graph. Among them, the external control information can be preset temperature change control information (such as: the change information of the temperature applied over time), preset pressure change control information (such as: the change information of the pressure applied over time), etc.

[0066] Specifically, the target model can determine the attribute association relationship between different initial attribute information corresponding to each node. For example, the attribute association relationship can be the association relationship between the temperature and the curing rate corresponding to the grid unit node (the curing rate also increases with the increase in temperature), or the association relationship between the temperature and the position information corresponding to the vertex node (the change in temperature causes the position of the vertex corresponding to the vertex node to change accordingly). For another example, the attribute association relationship can be the association relationship between the stress and Young's modulus corresponding to the grid unit node (the Young's modulus also changes with the change in stress), or the association relationship between the stress and the position information corresponding to the vertex node (the position information corresponding to the vertex node also changes with the change in stress).

[0067] Then, based on the node association relationship corresponding to each edge contained in the initial graph and the attribute association relationship corresponding to each node, the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information can be predicted.

[0068] In addition, in actual application, a time interval can often be preset, and then the target model can predict the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information according to the preset time interval (i.e., predict the updated attribute information at each time), until the preset end condition is met (such as: reaching the specified prediction end time). For example, the target model can predict the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information every 5ms.

[0069] It should be noted that, for example, when simulating directly heating the surface of the target object (i.e., applying corresponding temperature control) to perform heating and curing simulation, since it directly acts on the surface of the target object, the temperature represented in the corresponding temperature control information can be directly used as the temperature of the grid unit or vertex on the surface of the target object. In order to identify the grid unit or vertex on the surface of the target object in this process, a setting flag can be set in the attribute information of each node. When the setting flag is 1, the node can be determined to be the node corresponding to the grid unit or vertex on the surface of the target object. When the setting flag is 0, the node can be determined to be the node corresponding to the grid unit or vertex inside the target object.

[0070] After predicting the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information, the initial graph of the target object can be updated according to the updated attribute information to obtain the updated graph.

[0071] S103: Determine a loss value based on the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and train the target model based on the loss value, wherein the loss value is positively correlated with the deviation.

[0072] The server can determine the loss value based on the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and then train the target model by gradually reducing the loss value, wherein the loss value and the deviation are positively correlated.

[0073] Of course, in order to improve the prediction accuracy of the trained target model, in addition to training the target model by referring to the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, the target model can also be trained by referring to the preset physical constraint information.

[0074] Specifically, the server may determine the first loss value according to the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object. The first loss value may specifically refer to the following formula:

[0075] l = RMSE(D p , D r )

[0076] Among them, l can be used to represent the first loss value, RMSE() can be used to represent the first loss function, D p Can be used to represent updated attribute information, D r Can be used to represent tag attribute information.

[0077] Furthermore, the second loss value can be determined based on the preset physical constraint information and the updated attribute information corresponding to at least some of the nodes in the updated graph, and the second loss value is smaller when the updated attribute information corresponding to at least some of the nodes in the updated graph conforms more to the physical constraint conditions corresponding to the physical constraint information, wherein the physical constraint information can characterize the physical laws between the updated attribute information corresponding to at least some of the nodes in the updated graph. For example: in order to simulate the deformation of the target object under pressure, the physical constraint conditions corresponding to the physical constraint information can be σ-[D]ε=0, wherein σ can be used to characterize the stress of the target object at the vertex corresponding to the vertex node, ε can be used to characterize the strain of the target object at the vertex corresponding to the vertex node, and [D] can be used to characterize the preset parameter matrix.

[0078] Correspondingly, the second loss value during model training can be specifically referred to the following formula:

[0079] L=MSE(σ-[D]ε,0)

[0080] Among them, L can be used to characterize the second loss value, MSE() can be used to characterize the second loss function, σ can be used to characterize the stress of the target object at the vertex corresponding to the vertex node, ε can be used to characterize the strain of the target object at the vertex corresponding to the vertex node, and [D] can be used to characterize the preset parameter matrix.

[0081] It can be seen from this that when the stress σ and strain at the vertex corresponding to the vertex node more conform to the physical constraint condition σ-[D]ε=0, the second loss value is smaller.

[0082] Then, the loss value can be determined according to the first loss value and the second loss value. The loss value can be specifically referred to the following formula:

[0083] L ′ =l+ε*L

[0084] Among them, L ′It can be used to characterize the loss value, l can be used to characterize the first loss value, L can be used to characterize the second loss value, and ε can be used to characterize the preset weight coefficient.

[0085] In addition, in actual application, in order to simulate the behavior of the target object under different external control conditions (such as pressure changes, temperature changes, magnetic field changes, etc.), different target models can be trained separately, so as to predict the attribute information of each grid unit and each vertex of the target object under the external control conditions through the trained target model, so as to perform corresponding simulation tasks on the target object according to the predicted attribute information.

[0086] It can be seen from this that in the above model training process, the target model can obtain relatively rich attribute information corresponding to each grid unit node and the attribute information corresponding to each vertex node from the initial graph of the target object. In addition, the node association relationship between each grid unit node and each vertex node can be obtained from the initial graph. Then, based on the relatively rich attribute information and node association relationship obtained, the updated attribute information of each node corresponding to the target object under external control can be predicted, thereby greatly improving the prediction accuracy of the target model and enhancing the accuracy of the simulation.

[0087] In addition, the above target model can quickly predict the richer local features corresponding to the target object under external control, thereby greatly improving the prediction efficiency of the target model.

[0088] In addition, during the above model training process, in addition to making predictions based on the correlation between each node, the target model can also make predictions based on the attribute correlation between different attribute information corresponding to each node, that is, it can capture richer local information and further improve the prediction accuracy of the trained target model.

[0089] The above mainly introduces the model training method. After the model training is completed, it can be deployed for business execution. Next, a business execution method provided in this specification will be described.

[0090] Figure 3 A flowchart of a business execution method provided in this specification includes the following steps:

[0091] S301: Acquire an initial graph of the object to be simulated, wherein the initial graph is a heterogeneous graph composed of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the object to be simulated, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to the multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the object to be simulated at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the object to be simulated at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the object to be simulated.

[0092] For the service execution method provided in this specification, the execution subject can be a server or a terminal device such as a desktop computer or a laptop computer. The following only takes the server as an example to explain the subsequent content in detail.

[0093] In this specification, the target model trained by the above model training method can be deployed in the server. In practical applications, the server can obtain the initial graph of the object to be simulated, so that the obtained initial graph and external control information can be input into the target model, so that the target model predicts the attribute information of each grid unit and each vertex of the object to be simulated under the corresponding external control, so that after receiving the simulation instruction, the corresponding simulation service can be executed based on the predicted attribute information of each grid unit and each vertex.

[0094] S302: Input the initial graph and preset external control information into a pre-trained target model, so that the target model predicts the updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information based on the initial graph, and updates the initial graph according to the updated attribute information to obtain an updated graph. The target model is trained by the above-mentioned model training method.

[0095] In actual application, the server can input the preset external control information and the initial graph into the target model. The target model can often predict the attribute information of each node at different times in the corresponding external control process of the simulated object by obtaining the attribute information of each node in the initial graph and the node association relationship corresponding to each edge, so as to perform simulation services on the simulated object based on the attribute information of each node at different times.

[0096] S303: Execute a target simulation service on the object to be simulated according to the attribute information corresponding to each node contained in the updated graph.

[0097] The server can perform target simulation services on the simulated object according to the predicted attribute information corresponding to each node. For example, the specific shape of the target object after heating and curing or compressive deformation can be simulated according to the corresponding position information in the vertex node. Of course, the entire heating and curing process or compressive deformation process of the target object can also be simulated according to the predicted attribute information corresponding to each node at different times.

[0098] Moreover, when executing the target simulation business, corresponding data analysis can also be performed based on the predicted attribute information corresponding to each node. For example, a curve showing the change of curing degree with temperature can be fitted based on the predicted temperature at the vertex corresponding to the vertex node, the temperature at the grid unit corresponding to the grid unit node, the curing degree, etc., so as to analyze the heating and curing process.

[0099] The above are one or more implementation methods of this specification. Based on the same idea, this specification also provides a corresponding model training device and a business execution device, such as Figure 4 , Figure 5 shown.

[0100] Figure 4 A schematic diagram of a model training device provided in this specification includes:

[0101] Acquisition module 401: used to acquire an initial graph of a target object, wherein the initial graph is a heterogeneous graph consisting of a plurality of nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the target object, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to a plurality of vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the target object at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the target object at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the target object;

[0102] Prediction module 402: used to input the initial graph and the preset external control information into the target model to be trained, so that the target model predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information according to the initial graph, and updates the initial graph according to the updated attribute information to obtain the updated graph;

[0103] Training module 403: used to determine the loss value according to the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and train the target model according to the loss value, and there is a positive correlation between the loss value and the deviation.

[0104] Optionally, the acquisition module 401 is specifically used to: perform finite element meshing on the target object to obtain mesh units corresponding to the target object; for each mesh unit, based on the initial material property information and initial unit state information corresponding to the target object at the mesh unit, construct a mesh unit node corresponding to the mesh unit; and, for each vertex, based on the initial position information and initial vertex state information corresponding to the target object at the vertex, construct a vertex node corresponding to the vertex; based on the association relationship between each mesh unit and each vertex in the target object, construct an edge between each mesh unit node and each vertex node to obtain the initial graph of the target object.

[0105] Optionally, the prediction module 402 is specifically used to: input the initial graph and preset external control information into the target model to be trained, so that the target model determines the attribute association relationship between different initial attribute information corresponding to each node for each node, and predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information based on the node association relationship corresponding to each edge contained in the initial graph and the attribute association relationship corresponding to each node.

[0106] Optionally, the training module 403 is specifically used to: determine a first loss value based on the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and determine a second loss value based on preset physical constraint information and the updated attribute information corresponding to at least some of the nodes in the updated graph, wherein there is a positive correlation between the first loss value and the deviation, and the more the updated attribute information corresponding to at least some of the nodes in the updated graph conforms to the physical constraint conditions corresponding to the physical constraint information, the smaller the second loss value; determine the loss value based on the first loss value and the second loss value.

[0107] Figure 5 A schematic diagram of a service execution device provided in this specification includes:

[0108] Acquisition module 501: used to acquire an initial graph of the object to be simulated, the initial graph is a heterogeneous graph composed of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the object to be simulated, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the object to be simulated at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the object to be simulated at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the object to be simulated;

[0109] Prediction module 502: used to input the initial graph and the preset external control information into a pre-trained target model, so that the target model predicts the updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information according to the initial graph, and updates the initial graph according to the updated attribute information to obtain an updated graph, wherein the target model is trained by the above-mentioned model training method;

[0110] Execution module 503: used to execute a target simulation service on the object to be simulated according to the attribute information corresponding to each node contained in the updated graph.

[0111] Optionally, the prediction module 502 is specifically used to: input the initial graph and preset external control information into a pre-trained target model, so that the target model determines the attribute association relationship between different initial attribute information corresponding to each node for each node, and predicts the updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information based on the node association relationship corresponding to each edge contained in the initial graph and the attribute association relationship corresponding to each node.

[0112] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 The model training method shown or Figure 3 The business execution method shown.

[0113] This manual also provides Figure 6 The one shown corresponds to Figure 1 or Figure 3 A schematic diagram of the electronic device. Figure 6As shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The model training method shown or Figure 3 The business execution method shown.

[0114] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0115] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0116] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0117] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0118] For the convenience of description, the above device is described by dividing it into various units according to its functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0119] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0120] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0124] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0125] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0126] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0127] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0129] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0130] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A model training method, characterized in that: include: Acquire an initial graph of the target object, the initial graph is a heterogeneous graph consisting of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the target object, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to the multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the target object at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the target object at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the target object; Inputting the initial graph and the preset external control information into the target model to be trained, so that the target model predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information according to the initial graph, and updates the initial graph according to the updated attribute information to obtain an updated graph; The loss value is determined based on the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and the target model is trained based on the loss value, and there is a positive correlation between the loss value and the deviation.

2. The method according to claim 1, characterized in that Get the initial image of the target object, including: Performing finite element mesh division on the target object to obtain mesh units corresponding to the target object; For each grid unit, based on the initial material property information and initial unit state information corresponding to the target object at the grid unit, a grid unit node corresponding to the grid unit is constructed; and, for each vertex, based on the initial position information and initial vertex state information corresponding to the target object at the vertex, a vertex node corresponding to the vertex is constructed; Based on the association relationship between each grid unit and each vertex in the target object, an edge between each grid unit node and each vertex node is constructed to obtain an initial graph of the target object.

3. The method according to claim 1, characterized in that Inputting the initial graph and the preset external control information into the target model to be trained, so that the target model predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information according to the initial graph, specifically including: The initial graph and the preset external control information are input into the target model to be trained, so that the target model determines the attribute association relationship between different initial attribute information corresponding to each node for each node, and predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information based on the node association relationship corresponding to each edge contained in the initial graph and the attribute association relationship corresponding to each node.

4. The method according to claim 1, characterized in that Determining the loss value according to the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object specifically includes: Determine a first loss value according to a deviation between updated attribute information corresponding to each node in the updated graph and label attribute information corresponding to each node in the label graph corresponding to the target object, and determine a second loss value according to preset physical constraint information and updated attribute information corresponding to at least some of the nodes in the updated graph, wherein the first loss value is positively correlated with the deviation, and the more the updated attribute information corresponding to at least some of the nodes in the updated graph conforms to the physical constraint condition corresponding to the physical constraint information, the smaller the second loss value; A loss value is determined according to the first loss value and the second loss value.

5. A service execution method, characterized in that: include: Acquire an initial graph of the object to be simulated, the initial graph is a heterogeneous graph consisting of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the object to be simulated, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to the multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the object to be simulated at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the object to be simulated at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the object to be simulated; Inputting the initial graph and the preset external control information into a pre-trained target model, so that the target model predicts updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information according to the initial graph, and updating the initial graph according to the updated attribute information to obtain an updated graph, wherein the target model is trained by the method according to any one of claims 1 to 4 above; According to the attribute information corresponding to each node contained in the updated graph, a target simulation service is performed on the object to be simulated.

6. The method according to claim 5, characterized in that Inputting the initial graph and the preset external control information into a pre-trained target model so that the target model predicts updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information according to the initial graph, specifically including: The initial graph and preset external control information are input into a pre-trained target model so that the target model determines, for each node, the attribute association relationship between different initial attribute information corresponding to the node, and predicts the updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information based on the node association relationship corresponding to each edge contained in the initial graph and the attribute association relationship corresponding to each node.

7. A model training device, characterized in that: include: Acquisition module: used to acquire an initial graph of a target object, wherein the initial graph is a heterogeneous graph consisting of a plurality of nodes and edges between the nodes, wherein each node records initial attribute information corresponding to the node, and the nodes include vertex nodes and grid unit nodes, wherein each grid unit node corresponds to a grid unit divided in the target object, and the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to a plurality of vertex nodes, and the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the target object at the grid unit, and the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the target object at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the target object; Prediction module: used for inputting the initial graph and the preset external control information into the target model to be trained, so that the target model predicts the updated attribute information corresponding to each node of the target object under the external control corresponding to the external control information according to the initial graph, so as to update the initial graph according to the updated attribute information to obtain the updated graph; Training module: used to determine the loss value according to the deviation between the updated attribute information corresponding to each node in the updated graph and the label attribute information corresponding to each node in the label graph corresponding to the target object, and train the target model according to the loss value, and there is a positive correlation between the loss value and the deviation.

8. A service execution device, characterized in that: include: Acquisition module: used to acquire an initial graph of the object to be simulated, the initial graph is a heterogeneous graph composed of multiple nodes and edges between the nodes, each node records initial attribute information corresponding to the node, the nodes include vertex nodes and grid unit nodes, each grid unit node corresponds to a grid unit divided in the object to be simulated, the grid unit corresponding to the grid unit node is a closed area surrounded by vertices corresponding to multiple vertex nodes, the initial attribute information corresponding to the grid unit node includes initial material attribute information and initial unit state information corresponding to the object to be simulated at the grid unit, the initial attribute information corresponding to each vertex node includes initial position information and initial vertex state information of the object to be simulated at the vertex corresponding to the vertex node, and the edge between any two nodes is used to characterize the node association relationship between the two nodes in the object to be simulated; Prediction module: used for inputting the initial graph and the preset external control information into a pre-trained target model, so that the target model predicts the updated attribute information corresponding to each node of the object to be simulated under the external control corresponding to the external control information according to the initial graph, and updates the initial graph according to the updated attribute information to obtain an updated graph, wherein the target model is trained by any one of the methods of claims 1 to 4 above; Execution module: used for executing target simulation service on the object to be simulated according to the attribute information corresponding to each node contained in the updated graph.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

Images