Digital-twin-driven multi-model synchronous teaching method and system, terminal and medium

Abstract

The application belongs to the technical field of model teaching, and specifically discloses a digital twin driven multi-model synchronous teaching method and system, a terminal and a medium. The method comprises the following steps: obtaining modeling information of a target device, constructing a three-dimensional geometric model, a behavior model and a signal model based on the modeling information; establishing a mapping relationship between the behavior model and corresponding components in the three-dimensional geometric model, and establishing an association relationship between the signal model and the behavior model; in the teaching process, the state of the behavior model is changed according to the instruction, and the state update of the three-dimensional geometric model and the signal model is triggered synchronously; the signal flow path in the current working state is determined and mapped to the corresponding component position of the three-dimensional geometric model, and the collaborative teaching output of the device is realized. By taking the behavior state as the unified control core, the synchronous update and consistent operation of the multi-model in the same working state are realized. The structure, working logic and signal processing process of the device can be kept consistent and corresponding in any working state.

Description

Technical Field

[0001] This invention belongs to the field of model teaching technology, specifically relating to a method, system, terminal, and medium for multi-model synchronous teaching driven by digital twins. Background Technology

[0002] As the integration and functional complexity of complex equipment systems continue to increase, the structural composition, workflow, and signal processing mechanisms of these devices are increasingly exhibiting multi-level, multi-mode, and strongly coupled characteristics. To meet the needs of understanding principles, providing operational training, and teaching maintenance during equipment research and development, use, and maintenance, digital teaching technology is gradually evolving from traditional two-dimensional drawings and static three-dimensional models towards multi-model collaborative teaching driven by digital twins.

[0003] In existing technologies, for equipment teaching and simulation needs, three-dimensional geometric models are usually used to express the external structure and component hierarchy of the equipment, and flowcharts, state machines or scripts are used to describe the operation sequence and state change process of the equipment at different working stages. In scenarios involving signal processing, signal flow diagrams or signal simulation modules can also be used to model the signal generation, transmission and processing process.

[0004] However, the existing technologies mentioned above still have certain shortcomings in practical applications: On the one hand, the existing teaching methods are mostly based on pre-made videos, GIFs or script-driven animation demonstrations. The teaching process is essentially a pre-recorded or pre-arranged display content, which is difficult to dynamically deduce and respond in real time according to the current working status of the device or the user's operation behavior. It is impossible to realize the linkage update between the structural state, behavioral state and signal processing process during the teaching process, which limits the interactivity and scalability of the teaching system.

[0005] On the other hand, existing technologies typically rely on a large number of manually preset mapping relationships, fixed rules, or script configurations to specify the participating components and signal flows in different working states when realizing structural display and signal flow switching. When the equipment model, working mode, or teaching needs change, manual configuration or scene creation is required again, resulting in high implementation costs and a large maintenance workload, making it difficult to adapt to the teaching needs of complex equipment in multiple states and modes. Summary of the Invention

[0006] The present invention addresses the problems in the prior art and provides a digital twin-driven multi-model synchronous teaching method, system, terminal, and medium to solve the problems in the above-mentioned background art that the pre-recorded or pre-orchestrated display content is difficult to dynamically deduce and respond in real time according to the current working state of the device or the user's operation behavior, and it is impossible to achieve the联动 update between the structural state, behavioral state, and signal processing process during the teaching process, which limits the interactivity and scalability of the teaching system. At the same time, it solves the problem in the prior art that when implementing the structural display and signal process switching, it usually relies on a large number of manually preset mapping relationships, fixed rules, or script configurations to specify the participating components and signal processes in different working states, making it difficult to meet the teaching requirements in the multi-state and multi-mode of complex devices.

[0007] The technical solution adopted by the present invention is as follows:

[0008] In the first aspect, the present application provides a digital twin-driven multi-model synchronous teaching method, which includes the following steps:

[0009] Obtain the modeling information of the target device, where the modeling information includes structural information, workflow information, and signal processing information;

[0010] Construct a three-dimensional geometric model based on the structural information to represent the external structure of the device and the hierarchical relationship of components;

[0011] Construct a behavior model based on the workflow information to represent the operating state of the target device and the sequence and transition relationship of state changes in different working stages;

[0012] Construct a signal model based on the signal processing information to represent the signal generation, transmission, and processing process of the device in different working modes;

[0013] Establish a mapping relationship between the behavior model and the corresponding components in the three-dimensional geometric model;

[0014] Establish an association relationship between the signal model and the behavior model;

[0015] During the teaching process, receive an instruction for the target device, drive the behavior model to change its state according to the instruction, where the state change is used to represent the change in the operating state of the target device, and synchronously trigger the corresponding state update of the three-dimensional geometric model and the signal model;

[0016] Based on the updated signal model, determine the signal flow path of the target device in the current working state, and map the signal flow path to the corresponding component or structural position of the three-dimensional geometric model;

[0017] According to the mapping relationship between the signal flow path and the three-dimensional geometric model, perform collaborative teaching output on the structural state, working principle, and signal processing process of the target device.

[0018] Furthermore, establishing the mapping relationship between corresponding components in the behavioral model and the 3D geometric model, and establishing the association relationship between the signal model and the behavioral model, includes:

[0019] Define each work stage or work state in the behavior model as a behavior state node;

[0020] Configure at least one corresponding set of structural component identifiers for each behavior state node. The set of structural component identifiers is used to indicate the three-dimensional geometric model components that participate in the work in that behavior state.

[0021] When the behavior model changes state, the three-dimensional geometric model components that need to be activated, displayed, or used for teaching are determined based on the set of structural component identifiers corresponding to the current behavior state node.

[0022] Configure a corresponding signal processing mode or signal flow identifier for each behavior state node;

[0023] When the behavior model undergoes a state transition, based on the signal processing mode or signal flow identifier corresponding to the current behavior state node, the signal flow path or signal processing unit that needs to be activated in the signal model is determined, and the association between the signal model and the behavior model is established.

[0024] Furthermore, when establishing associations between behavioral state nodes in the behavioral model and the 3D geometric model and signal model, the generation of the structural component identifier set and the signal processing element set includes at least one of the following methods:

[0025] Based on manual configuration, according to the design data of the target device or teaching needs, pre-configure the corresponding set of structural component identifiers for each behavioral state node in the behavioral model, as well as the signal processing mode or signal flow identifier corresponding to the behavioral state node.

[0026] Based on the automatic parsing method, the structural component identifiers associated with the current behavior state node are parsed from the component hierarchy or assembly relationship of the three-dimensional geometric model, and the corresponding set of structural component identifiers is generated. Simultaneously, the signal interface relationship or signal connection relationship corresponding to the structural component identifier is parsed to determine the signal processing elements associated with the behavior state node.

[0027] Based on the rule generation method, according to the preset component participation rules and signal processing rules, and according to the working mode, working stage or functional type corresponding to the behavior state node, the structural component identifiers that meet the rule conditions are selected from the component set of the three-dimensional geometric model to generate the corresponding structural component identifier set; and the signal processing unit or signal flow path that matches the structural component identifier set is selected from the signal model.

[0028] Furthermore, the generation of both the structural component identifier set and the signal processing element set adopts an automatic parsing-based approach. When the behavior model undergoes a state transition, the behavior state nodes are parsed and inferred based on the inference model. Combining the structural component identifier set and the signal processing element set, the motion actions of each structural component corresponding to the current behavior state are determined, specifically including:

[0029] The behavioral state nodes that undergo state transitions in the behavioral model are input into the inference model. The behavioral state nodes are then parsed to obtain the behavioral semantic information that represents the behavioral state.

[0030] Based on behavioral semantic information, the action type and action constraint information corresponding to the behavioral state are obtained through reasoning model, and the signal processing mode or signal flow type corresponding to the behavioral state are obtained through synchronous reasoning.

[0031] For each structural component in the structural component identifier set, the motion action corresponding to each structural component in the current behavior state is determined by combining the component hierarchy or assembly relationship of each structural component in the three-dimensional geometric model.

[0032] Based on the signal processing mode or signal flow type, determine the signal processing unit or signal flow path that needs to be activated in the current behavior state from the set of signal processing elements, and establish the relationship between the signal model and the behavior model.

[0033] Output motion descriptions or motion parameters corresponding to each structural component to drive the corresponding structural component in the three-dimensional geometric model to undergo motion changes consistent with the behavior state, and synchronously drive the signal model to perform signal processing teaching according to the determined signal flow path.

[0034] Furthermore, the inference model is a trained model. The action relationships between the behavior model and the 3D geometric model, as well as the signal relationships between the behavior model and the signal model, are established through the inference model during the behavior state node parsing and inference process. Specifically, this includes:

[0035] During the model training phase, a training dataset containing behavioral state description samples and corresponding semantic annotations is obtained. The semantic annotations include at least behavioral semantic annotations and signal semantic annotations. The behavioral semantic annotations include at least action type, action object type and action constraint information. The signal semantic annotations include at least signal processing mode or signal flow type.

[0036] Based on the training dataset, the inference model is trained to establish the correspondence between the behavioral state description and the behavioral semantic annotation and signal semantic annotation, thus obtaining the trained inference model.

[0037] When the behavior model undergoes a state transition, the state description corresponding to the behavior state node is input into the trained inference model;

[0038] During the running phase, the trained inference model receives a state description. By extracting semantic elements from the state description, it identifies the action type, action object type, and action constraint information corresponding to the behavior state, and simultaneously identifies the signal processing mode or signal flow type corresponding to the behavior state.

[0039] The extracted behavioral semantic elements are combined and standardized to obtain structural action semantic information used to represent the behavioral state. The structural action semantic information is used to indicate the motion of structural components in the three-dimensional geometric model.

[0040] The extracted signal semantic elements are combined and standardized to obtain signal semantic information that represents the behavioral state. The signal semantic information is used to indicate the signal processing unit or signal flow path that needs to be activated in the signal model. The action association relationship between the behavior model and the three-dimensional geometric model, as well as the signal association relationship between the behavior model and the signal model, are established respectively.

[0041] Furthermore, based on the signal semantic information output by the inference model, the signal flow path or signal processing unit corresponding to the current behavioral state is selected and activated in the signal model to achieve the coordinated operation of the signal model and the behavioral model, including:

[0042] In the signal model, multiple signal flow paths or combinations of multiple signal processing units are pre-constructed, and corresponding flow identifiers or mode identifiers are configured for each signal flow path or signal processing unit.

[0043] After the behavior model undergoes a state transition, signal semantic information is acquired, and a signal flow identifier or pattern identifier that matches the current behavior state is determined based on the signal semantic information.

[0044] Based on signal flow identifiers or pattern identifiers, select the corresponding signal flow path or signal processing unit from multiple signal flow paths or combinations of multiple signal processing units in the signal model;

[0045] Enable the selected signal flow path or signal processing unit to enable the signal model to perform signal generation, transmission or processing according to the determined signal flow path, and achieve signal processing teaching consistent with the current behavior state.

[0046] Furthermore, when a behavioral model undergoes a state change, the behavioral state node serves as a unified trigger source to perform synchronous update control on the 3D geometric model and the signal model, thereby achieving consistent operation of multiple models under the current behavioral state. Specifically, this includes:

[0047] When a behavioral model undergoes a state change, a corresponding state change event is generated, and the state change event is used as the trigger condition for multi-model synchronous updates.

[0048] Based on state change events, the motion update of structural components corresponding to the current behavior state node in the 3D geometric model is synchronously triggered, and the activation or switching of signal flow paths or signal processing units corresponding to the current behavior state in the trigger signal model is also triggered.

[0049] Secondly, this application provides a digital twin-driven multi-model synchronous teaching system for implementing the digital twin-driven multi-model synchronous teaching method as described in the first aspect. The system includes:

[0050] The modeling module is used to acquire modeling information of the target device. The modeling information includes structural information, workflow information and signal processing information. Based on the structural information, a three-dimensional geometric model is constructed to represent the device's external structure and component hierarchy. Based on the workflow information, a behavioral model is constructed to represent the sequence of state changes and state transition relationships of the device in different working stages. Based on the signal processing information, a signal model is constructed to represent the signal generation, transmission and processing processes of the device in different working modes.

[0051] The model association module is used to establish the mapping relationship between the behavior model and the corresponding components in the 3D geometric model, and to establish the association relationship between the signal model and the behavior model;

[0052] The element parsing module is used to automatically generate a set of structural component identifiers and a set of signal processing elements when establishing a connection between behavioral state nodes in the behavioral model and the 3D geometric model and signal model.

[0053] The reasoning module is used to parse and reason about the behavior state nodes when the behavior model changes state, and output structural action semantic information and signal semantic information to represent the current behavior state.

[0054] The structure-driven module is used to determine the motion action of each structural component in the current behavior state based on the semantic information of structural actions, combined with the set of structural component identifiers and the component hierarchy or assembly relationship in the 3D geometric model, and drive the corresponding structural components in the 3D geometric model to update their motion.

[0055] The signal driving module is used to select and enable the signal flow path or signal processing unit corresponding to the current behavior state in the signal model based on the signal semantic information, so that the signal model can perform signal generation, transmission or processing according to the determined signal flow path.

[0056] The synchronization control module is used to synchronously trigger the structural update of the 3D geometric model and the signal flow switching of the signal model when the state of the behavior model changes, using the behavior state node as a unified trigger source, so as to perform consistent control of the running state of multiple models.

[0057] The teaching output module is used to collaboratively teach and output the structural state, working principle, and signal processing of the target device based on the synchronous update results of the three-dimensional geometric model and the signal model.

[0058] Thirdly, this application provides a terminal, including:

[0059] Memory for storing multi-model synchronous teaching programs driven by digital twins;

[0060] A processor is configured to implement the steps of the digital twin-driven multi-model synchronous teaching method as described in the first aspect when executing the digital twin-driven multi-model synchronous teaching system.

[0061] Fourthly, this application provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the digital twin-driven multi-model synchronous teaching method as described in the first aspect.

[0062] As can be seen from the above technical solutions, the advantages of the present invention are:

[0063] This application constructs a behavior model and uses behavior state nodes as a unified trigger source to synchronously drive the update of the three-dimensional geometric model and signal model when the behavior state changes. This ensures that the structural form, working logic and signal processing of the device remain consistent in any working state, avoiding the problem of separate triggering and mutual separation of structural display and signal flow in the prior art, thereby improving the overall coherence and technical consistency of the teaching process.

[0064] This application does not rely on pre-recorded videos or fixed animation scripts, but rather uses dynamic state switching based on behavioral models to drive the movement of structural components and the execution of signal flows. This allows the teaching content to be updated in real time as the behavioral state changes, supports dynamic simulation of different working modes and stages of the equipment, and helps to improve the interactivity and adaptability of the teaching system.

[0065] This application automatically parses the component hierarchy, assembly relationship, and signal interface relationship of the three-dimensional geometric model to generate a set of structural component identifiers and a set of signal processing elements. This reduces the reliance on manual configuration of mapping relationships and manual arrangement of teaching scenarios. When the equipment model changes or the working mode expands, there is no need for a large amount of reconfiguration, which effectively reduces the implementation cost and subsequent maintenance cost of the teaching system.

[0066] This application uses a trained reasoning model to analyze and reason about behavioral states, and outputs structural action semantic information and signal semantic information in a unified manner. This automatically determines the motion actions of structural components and the corresponding signal processing modes, realizing the automatic conversion of behavioral semantics into executable teaching content. This avoids the problem of relying on manual rules or scripts to specify structural actions and signal processes one by one in the prior art.

[0067] Based on the signal semantic information output by the inference model, this application dynamically selects and enables the signal flow path or signal processing unit that matches the current behavior state in the signal model, so that the signal processing process can automatically switch with the change of behavior state, which is conducive to accurately presenting the real signal processing logic of the device under different working states.

[0068] This application performs synchronous update control of the 3D geometric model and signal model when the behavior state changes, and performs consistency verification of the operating state of multiple models, avoiding teaching deviations caused by asynchronous model updates, which helps to improve the stability and reliability of the digital twin teaching system in complex equipment scenarios. Attached Figure Description

[0069] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0070] Figure 1 This is a flowchart illustrating the steps of the digital twin-driven multi-model synchronous teaching method in this embodiment.

[0071] Figure 2 This is an architecture diagram of a digital twin-driven multi-model synchronous teaching system in this embodiment. Detailed Implementation

[0072] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0073] Please see Figure 1 As shown, this application provides a digital twin-driven multi-model synchronous teaching method, including:

[0074] Step S1: Obtain the modeling information of the target device, which includes structural information, workflow information, and signal processing information;

[0075] In a specific implementation, the modeling information may be derived from the equipment's design data, digital model files, system documentation, or simulation configuration files. The structural information is used to describe the overall shape and structure of the equipment, the composition relationship of its components, and the assembly hierarchy. The workflow information is used to describe the operation sequence, state changes, and state transition logic of the equipment in different working stages. The signal processing information is used to describe the signal generation method, transmission path, and processing logic of the equipment in different working modes.

[0076] In one embodiment, for a complex device, the structural information includes the three-dimensional structural data of each functional module of the device and their assembly relationship, the workflow information includes the state switching sequence of the device from standby state, startup state to running state, and the signal processing information includes the signal processing links and processing unit configurations used by the device in different working modes.

[0077] Step S2: Construct a three-dimensional geometric model based on structural information to characterize the external structure and hierarchical relationship of the equipment components;

[0078] A behavioral model is constructed based on workflow information to characterize the operating status of the target equipment and the sequence of state changes and state transition relationships at different working stages.

[0079] Based on signal processing information, a signal model is constructed to characterize the signal generation, transmission and processing processes of the device under different operating modes;

[0080] In a specific implementation, the three-dimensional geometric model is used to spatially represent the external structure and internal components of the equipment. The components in the model form a hierarchical structure according to the actual assembly relationship. The behavioral model is used to abstractly describe the state change process of the equipment in different working stages. The states are connected through state transition relationships. The signal model is used to describe the overall process of signals from input, processing to output of the equipment in different working modes.

[0081] In one embodiment, the three-dimensional geometric model is constructed as a multi-level model according to the actual assembly structure of the equipment, the behavioral model divides the operation process of the equipment into several working state nodes and establishes state transition relationships, and the signal model constructs multiple signal flow paths according to different working modes to describe the transmission relationship of signals between different processing units.

[0082] Step S3: Establish the mapping relationship between the behavioral model and the corresponding components in the three-dimensional geometric model;

[0083] Establish the correlation between the signal model and the behavior model;

[0084] In a specific implementation, each working state node in the behavior model is associated with a set of structural components in the three-dimensional geometric model to indicate the structural components that participate in the work in that working state; at the same time, each working state node is also associated with the signal processing mode or signal flow in the signal model to indicate the signal processing method used in that working state.

[0085] In one embodiment, when the behavior model is in a certain working state, the set of structural components that need to participate in the teaching is determined by a pre-established mapping relationship, and the signal processing flow that needs to be enabled in the signal model is determined simultaneously, so that the structural display and the signal processing logic are consistent in the same behavior state.

[0086] Step S4: During the teaching process, receive instructions for the target device, drive the behavior model to change state according to the instructions, the state change is used to characterize the change in the operating state of the target device, and synchronously trigger the corresponding state update of the three-dimensional geometric model and signal model.

[0087] In a specific implementation, the instruction can be a user operation instruction, a teaching control instruction, or a mode switching instruction, used to trigger the device to enter different working states; after the behavior model state changes, the system uses the state change as a unified trigger condition to synchronously drive the three-dimensional geometric model and signal model to update their states.

[0088] In one embodiment, when a user issues a state switching command during the teaching process, the behavior model switches from the current state to the target state. At the same time, the system updates the display and motion state of the corresponding structural components in the three-dimensional geometric model and updates the corresponding signal processing flow in the signal model, so that the running state of each model is consistent with the current behavior state.

[0089] Step S5: Based on the updated signal model, determine the signal flow path of the target device in the current working state, and map the signal flow path to the corresponding component or structural position in the three-dimensional geometric model.

[0090] In a specific implementation, multiple signal flow paths are pre-built in the signal model, and different signal flow paths correspond to different working modes or signal processing methods. After the behavior model state is updated, the signal flow path to be adopted is determined according to the current running state of the signal model, and a spatial correspondence is established between the signal flow path and the structural components in the three-dimensional geometric model.

[0091] In one embodiment, when the device enters a specific working state, the system determines the signal flow path that matches the state in the signal model, and maps the signal transmission process between processing units to the corresponding structural component positions in the three-dimensional geometric model, so as to intuitively reflect the correspondence between the signal processing process and the device structure during the teaching process.

[0092] Step S6: Based on the mapping relationship between the signal flow path and the three-dimensional geometric model, conduct collaborative teaching output on the structural state, working principle and signal processing process of the target device.

[0093] In a specific implementation, the collaborative teaching output includes a comprehensive presentation of changes in the device's structural form, explanations of its working principles, and signal processing procedures, enabling the learner to understand the device's structural composition, working logic, and signal processing mechanisms simultaneously within the same teaching scenario.

[0094] In one embodiment, the system synchronously presents the state changes of structural components and the signal processing at the corresponding structural positions during the teaching process. Through the coordinated display of structure and signals, the teaching object can intuitively understand the overall operating mechanism of the device in the current working state.

[0095] In some embodiments, establishing the mapping relationship between corresponding components in the behavior model and the three-dimensional geometric model, and establishing the association relationship between the signal model and the behavior model, includes:

[0096] Define each work stage or work state in the behavior model as a behavior state node;

[0097] Configure at least one corresponding set of structural component identifiers for each behavior state node. The set of structural component identifiers is used to indicate the three-dimensional geometric model components that participate in the work in that behavior state.

[0098] When the behavior model changes state, the three-dimensional geometric model components that need to be activated, displayed, or used for teaching are determined based on the set of structural component identifiers corresponding to the current behavior state node.

[0099] Configure a corresponding signal processing mode or signal flow identifier for each behavior state node;

[0100] When the behavior model undergoes a state transition, based on the signal processing mode or signal flow identifier corresponding to the current behavior state node, the signal flow path or signal processing unit that needs to be activated in the signal model is determined, and the association between the signal model and the behavior model is established.

[0101] In some embodiments, when establishing associations between behavioral state nodes in the behavioral model and the three-dimensional geometric model and signal model, the generation of the structural component identifier set and the signal processing element set includes at least one of the following methods:

[0102] Based on manual configuration, according to the design data of the target device or teaching needs, pre-configure the corresponding set of structural component identifiers for each behavioral state node in the behavioral model, as well as the signal processing mode or signal flow identifier corresponding to the behavioral state node.

[0103] Based on the automatic parsing method, the structural component identifiers associated with the current behavior state node are parsed from the component hierarchy or assembly relationship of the three-dimensional geometric model, and the corresponding set of structural component identifiers is generated. Simultaneously, the signal interface relationship or signal connection relationship corresponding to the structural component identifier is parsed to determine the signal processing elements associated with the behavior state node.

[0104] Based on the rule generation method, according to the preset component participation rules and signal processing rules, and according to the working mode, working stage or functional type corresponding to the behavior state node, the structural component identifiers that meet the rule conditions are selected from the component set of the three-dimensional geometric model to generate the corresponding structural component identifier set; and the signal processing unit or signal flow path that matches the structural component identifier set is selected from the signal model.

[0105] In some embodiments, the generation of both the structural component identifier set and the signal processing element set is based on an automatic parsing method. When the behavior model undergoes a state transition, the behavior state nodes are parsed and inferred based on the inference model. Combining the structural component identifier set and the signal processing element set, the motion actions of each structural component corresponding to the current behavior state are determined, specifically including:

[0106] The behavioral state nodes that undergo state transitions in the behavioral model are input into the inference model. The behavioral state nodes are then parsed to obtain the behavioral semantic information that represents the behavioral state.

[0107] Based on behavioral semantic information, the action type and action constraint information corresponding to the behavioral state are obtained through reasoning model, and the signal processing mode or signal flow type corresponding to the behavioral state are obtained through synchronous reasoning.

[0108] For each structural component in the structural component identifier set, the motion action corresponding to each structural component in the current behavior state is determined by combining the component hierarchy or assembly relationship of each structural component in the three-dimensional geometric model.

[0109] Based on the signal processing mode or signal flow type, determine the signal processing unit or signal flow path that needs to be activated in the current behavior state from the set of signal processing elements, and establish the relationship between the signal model and the behavior model.

[0110] Output motion descriptions or motion parameters corresponding to each structural component to drive the corresponding structural component in the three-dimensional geometric model to undergo motion changes consistent with the behavior state, and synchronously drive the signal model to perform signal processing teaching according to the determined signal flow path.

[0111] In some embodiments, the inference model is a trained model, and the action association between the behavior model and the three-dimensional geometric model, as well as the signal association between the behavior model and the signal model, are established through the inference model during the behavior state node parsing and inference process, specifically including:

[0112] During the model training phase, a training dataset containing behavioral state description samples and corresponding semantic annotations is obtained. The semantic annotations include at least behavioral semantic annotations and signal semantic annotations. The behavioral semantic annotations include at least action type, action object type and action constraint information. The signal semantic annotations include at least signal processing mode or signal flow type.

[0113] Based on the training dataset, the inference model is trained to establish the correspondence between the behavioral state description and the behavioral semantic annotation and signal semantic annotation, thus obtaining the trained inference model.

[0114] When the behavior model undergoes a state transition, the state description corresponding to the behavior state node is input into the trained inference model;

[0115] During the running phase, the trained inference model receives a state description. By extracting semantic elements from the state description, it identifies the action type, action object type, and action constraint information corresponding to the behavior state, and simultaneously identifies the signal processing mode or signal flow type corresponding to the behavior state.

[0116] The extracted behavioral semantic elements are combined and standardized to obtain structural action semantic information used to represent the behavioral state. The structural action semantic information is used to indicate the motion of structural components in the three-dimensional geometric model.

[0117] The extracted signal semantic elements are combined and standardized to obtain signal semantic information that represents the behavioral state. The signal semantic information is used to indicate the signal processing unit or signal flow path that needs to be activated in the signal model. The action association relationship between the behavior model and the three-dimensional geometric model, as well as the signal association relationship between the behavior model and the signal model, are established respectively.

[0118] In some embodiments, based on the signal semantic information output by the inference model, a signal flow path or signal processing unit corresponding to the current behavioral state is selected and activated in the signal model to achieve the coordinated operation of the signal model and the behavioral model, including:

[0119] In the signal model, multiple signal flow paths or combinations of multiple signal processing units are pre-constructed, and corresponding flow identifiers or mode identifiers are configured for each signal flow path or signal processing unit.

[0120] After the behavior model undergoes a state transition, signal semantic information is acquired, and a signal flow identifier or pattern identifier that matches the current behavior state is determined based on the signal semantic information.

[0121] Based on signal flow identifiers or pattern identifiers, select the corresponding signal flow path or signal processing unit from multiple signal flow paths or combinations of multiple signal processing units in the signal model;

[0122] Enable the selected signal flow path or signal processing unit to enable the signal model to perform signal generation, transmission or processing according to the determined signal flow path, and achieve signal processing teaching consistent with the current behavior state.

[0123] In some embodiments, when a behavior model undergoes a state change, the behavior state node is used as a unified trigger source to perform synchronous update control on the 3D geometric model and the signal model, so as to achieve consistent operation of multiple models in the current behavior state, specifically including:

[0124] When a behavioral model undergoes a state change, a corresponding state change event is generated, and the state change event is used as the trigger condition for multi-model synchronous updates.

[0125] Based on state change events, the motion update of structural components corresponding to the current behavior state node in the 3D geometric model is synchronously triggered, and the activation or switching of signal flow paths or signal processing units corresponding to the current behavior state in the trigger signal model is also triggered.

[0126] Please see Figure 2 As shown, in some embodiments, this application provides a digital twin-driven multi-model synchronous teaching system for implementing a digital twin-driven multi-model synchronous teaching method. The system includes:

[0127] The modeling module is used to acquire modeling information of the target device. The modeling information includes structural information, workflow information and signal processing information. Based on the structural information, a three-dimensional geometric model is constructed to represent the device's external structure and component hierarchy. Based on the workflow information, a behavioral model is constructed to represent the sequence of state changes and state transition relationships of the device in different working stages. Based on the signal processing information, a signal model is constructed to represent the signal generation, transmission and processing processes of the device in different working modes.

[0128] The model association module is used to establish the mapping relationship between the behavior model and the corresponding components in the 3D geometric model, and to establish the association relationship between the signal model and the behavior model;

[0129] The element parsing module is used to automatically generate a set of structural component identifiers and a set of signal processing elements when establishing a connection between behavioral state nodes in the behavioral model and the 3D geometric model and signal model.

[0130] The reasoning module is used to parse and reason about the behavior state nodes when the behavior model changes state, and output structural action semantic information and signal semantic information to represent the current behavior state.

[0131] The structure-driven module is used to determine the motion action of each structural component in the current behavior state based on the semantic information of structural actions, combined with the set of structural component identifiers and the component hierarchy or assembly relationship in the 3D geometric model, and drive the corresponding structural components in the 3D geometric model to update their motion.

[0132] The signal driving module is used to select and enable the signal flow path or signal processing unit corresponding to the current behavior state in the signal model based on the signal semantic information, so that the signal model can perform signal generation, transmission or processing according to the determined signal flow path.

[0133] The synchronization control module is used to synchronously trigger the structural update of the 3D geometric model and the signal flow switching of the signal model when the state of the behavior model changes, using the behavior state node as a unified trigger source, so as to perform consistent control of the running state of multiple models.

[0134] The teaching output module is used to collaboratively teach and output the structural state, working principle, and signal processing of the target device based on the synchronous update results of the three-dimensional geometric model and the signal model.

[0135] In some embodiments, this application provides a terminal, including:

[0136] Memory for storing multi-model synchronous teaching programs driven by digital twins;

[0137] A processor is configured to implement the steps of the digital twin-driven multi-model synchronous teaching method when executing the digital twin-driven multi-model synchronous teaching system.

[0138] In some embodiments, this application provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the digital twin-driven multi-model synchronous teaching method.

[0139] The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit the scope of one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this specification should be included within the protection scope of one or more embodiments of this specification.

Claims

1. A digital twin-driven multi-model synchronous teaching method, characterized in that, Includes the following steps: Acquire modeling information for the target device, including structural information, workflow information, and signal processing information; A three-dimensional geometric model is constructed based on structural information to characterize the external structure and hierarchical relationships of the equipment components; A behavioral model is constructed based on workflow information to characterize the operating status of the target equipment and the sequence of state changes and state transition relationships at different working stages. Based on signal processing information, a signal model is constructed to characterize the signal generation, transmission and processing processes of the device under different operating modes; Establish a mapping relationship between the behavioral model and the corresponding components in the 3D geometric model; Establish the correlation between the signal model and the behavior model; Establishing the mapping relationship between corresponding components in the behavioral model and the 3D geometric model, and establishing the association relationship between the signal model and the behavioral model, includes: Define each work stage or work state in the behavior model as a behavior state node; Configure at least one corresponding set of structural component identifiers for each behavior state node. The set of structural component identifiers is used to indicate the three-dimensional geometric model components that participate in the work in that behavior state. When the behavior model changes state, the three-dimensional geometric model components that need to be activated, displayed, or used for teaching are determined based on the set of structural component identifiers corresponding to the current behavior state node. Configure a corresponding signal processing mode or signal flow identifier for each behavior state node; When the behavior model undergoes a state transition, based on the signal processing mode or signal flow identifier corresponding to the current behavior state node, determine the signal flow path or signal processing unit that needs to be activated in the signal model, and establish the association between the signal model and the behavior model. During the teaching process, instructions are received for the target device, and the behavior model is driven to change state according to the instructions. The state change is used to characterize the change in the operating state of the target device, and the corresponding state update of the three-dimensional geometric model and signal model is triggered synchronously. Based on the updated signal model, the signal flow path of the target device in the current working state is determined, and the signal flow path is mapped to the corresponding component or structural position in the three-dimensional geometric model. Based on the mapping relationship between signal flow path and three-dimensional geometric model, the structural state, working principle and signal processing of target equipment are collaboratively taught and output; Both the structural component identifier set and the signal processing element set are generated using an automatic parsing method. When the behavior model undergoes a state transition, the behavior state nodes are parsed and inferred based on the inference model. Combining the structural component identifier set and the signal processing element set, the motion actions of each structural component corresponding to the current behavior state are determined, specifically including: The behavioral state nodes that undergo state transitions in the behavioral model are input into the inference model. The behavioral state nodes are then parsed to obtain the behavioral semantic information that represents the behavioral state. Based on behavioral semantic information, the action type and action constraint information corresponding to the behavioral state are obtained through reasoning model, and the signal processing mode or signal flow type corresponding to the behavioral state are obtained through synchronous reasoning. For each structural component in the structural component identifier set, the motion action corresponding to each structural component in the current behavior state is determined by combining the component hierarchy or assembly relationship of each structural component in the three-dimensional geometric model. Based on the signal processing mode or signal flow type, determine the signal processing unit or signal flow path that needs to be activated in the current behavior state from the set of signal processing elements, and establish the relationship between the signal model and the behavior model. Output motion descriptions or motion parameters corresponding to each structural component to drive the corresponding structural component in the three-dimensional geometric model to undergo motion changes consistent with the behavior state, and synchronously drive the signal model to perform signal processing teaching according to the determined signal flow path.

2. The digital twin-driven multi-model synchronous teaching method according to claim 1, characterized in that, When establishing associations between behavioral state nodes in the behavioral model and the 3D geometric model and signal model, the generation of the structural component identifier set and the signal processing element set includes at least one of the following methods: Based on manual configuration, according to the design data of the target device or teaching needs, pre-configure the corresponding set of structural component identifiers for each behavioral state node in the behavioral model, as well as the signal processing mode or signal flow identifier corresponding to the behavioral state node. Based on the automatic parsing method, the structural component identifiers associated with the current behavior state node are parsed from the component hierarchy or assembly relationship of the three-dimensional geometric model, and the corresponding set of structural component identifiers is generated. Simultaneously, the signal interface relationship or signal connection relationship corresponding to the structural component identifier is parsed to determine the signal processing elements associated with the behavior state node. Based on the rule generation method, according to the preset component participation rules and signal processing rules, and according to the working mode, working stage or functional type corresponding to the behavior state node, the structural component identifiers that meet the rule conditions are selected from the component set of the three-dimensional geometric model to generate the corresponding structural component identifier set; and the signal processing unit or signal flow path that matches the structural component identifier set is selected from the signal model.

3. The digital twin-driven multi-model synchronous teaching method according to claim 2, characterized in that, The inference model is a trained model. The action relationships between the behavior model and the 3D geometric model, as well as the signal relationships between the behavior model and the signal model, are established through the inference model during the behavior state node parsing and inference process. Specifically, this includes: During the model training phase, a training dataset containing behavioral state description samples and corresponding semantic annotations is obtained. The semantic annotations include at least behavioral semantic annotations and signal semantic annotations. The behavioral semantic annotations include at least action type, action object type and action constraint information. The signal semantic annotations include at least signal processing mode or signal flow type. Based on the training dataset, the inference model is trained to establish the correspondence between the behavioral state description and the behavioral semantic annotation and signal semantic annotation, thus obtaining the trained inference model. When the behavior model undergoes a state transition, the state description corresponding to the behavior state node is input into the trained inference model; During the running phase, the trained inference model receives a state description. By extracting semantic elements from the state description, it identifies the action type, action object type, and action constraint information corresponding to the behavior state, and simultaneously identifies the signal processing mode or signal flow type corresponding to the behavior state. The extracted behavioral semantic elements are combined and standardized to obtain structural action semantic information used to represent the behavioral state. The structural action semantic information is used to indicate the motion of structural components in the three-dimensional geometric model. The extracted signal semantic elements are combined and standardized to obtain signal semantic information that represents the behavioral state. The signal semantic information is used to indicate the signal processing unit or signal flow path that needs to be activated in the signal model. The action association relationship between the behavior model and the three-dimensional geometric model, as well as the signal association relationship between the behavior model and the signal model, are established respectively.

4. The digital twin-driven multi-model synchronous teaching method according to claim 3, characterized in that, Based on the signal semantic information output by the inference model, the signal flow path or signal processing unit corresponding to the current behavioral state is selected and activated in the signal model to achieve the coordinated operation of the signal model and the behavioral model, including: In the signal model, multiple signal flow paths or combinations of multiple signal processing units are pre-constructed, and corresponding flow identifiers or mode identifiers are configured for each signal flow path or signal processing unit. After the behavior model undergoes a state transition, signal semantic information is acquired, and a signal flow identifier or pattern identifier that matches the current behavior state is determined based on the signal semantic information. Based on signal flow identifiers or pattern identifiers, select the corresponding signal flow path or signal processing unit from multiple signal flow paths or combinations of multiple signal processing units in the signal model; Enable the selected signal flow path or signal processing unit to enable the signal model to perform signal generation, transmission or processing according to the determined signal flow path, and achieve signal processing teaching consistent with the current behavior state.

5. The digital twin-driven multi-model synchronous teaching method according to any one of claims 1-4, characterized in that, When a behavioral model undergoes a state change, the behavioral state node serves as a unified trigger source to perform synchronous update control on the 3D geometric model and the signal model, thereby achieving consistent operation of multiple models under the current behavioral state. Specifically, this includes: When a behavioral model undergoes a state change, a corresponding state change event is generated, and the state change event is used as the trigger condition for multi-model synchronous updates. Based on state change events, the motion update of structural components corresponding to the current behavior state node in the 3D geometric model is synchronously triggered, and the activation or switching of signal flow paths or signal processing units corresponding to the current behavior state in the trigger signal model is also triggered.

6. A digital twin-driven multi-model synchronous teaching system, used to implement the digital twin-driven multi-model synchronous teaching method as described in claim 1, characterized in that, The system includes: The modeling module is used to acquire modeling information of the target device. The modeling information includes structural information, workflow information and signal processing information. Based on the structural information, a three-dimensional geometric model is constructed to represent the device's external structure and component hierarchy. Based on the workflow information, a behavioral model is constructed to represent the sequence of state changes and state transition relationships of the device in different working stages. Based on the signal processing information, a signal model is constructed to represent the signal generation, transmission and processing processes of the device in different working modes. The model association module is used to establish the mapping relationship between the behavior model and the corresponding components in the 3D geometric model, and to establish the association relationship between the signal model and the behavior model; The element parsing module is used to automatically generate a set of structural component identifiers and a set of signal processing elements when establishing a connection between behavioral state nodes in the behavioral model and the 3D geometric model and signal model. The reasoning module is used to parse and reason about the behavior state nodes when the behavior model changes state, and output structural action semantic information and signal semantic information to represent the current behavior state. The structure-driven module is used to determine the motion action of each structural component in the current behavior state based on the semantic information of structural actions, combined with the set of structural component identifiers and the component hierarchy or assembly relationship in the 3D geometric model, and drive the corresponding structural components in the 3D geometric model to update their motion. The signal driving module is used to select and enable the signal flow path or signal processing unit corresponding to the current behavior state in the signal model based on the signal semantic information, so that the signal model can perform signal generation, transmission or processing according to the determined signal flow path. The synchronization control module is used to synchronously trigger the structural update of the 3D geometric model and the signal flow switching of the signal model when the state of the behavior model changes, using the behavior state node as a unified trigger source, so as to perform consistent control of the running state of multiple models. The teaching output module is used to collaboratively teach and output the structural state, working principle, and signal processing of the target device based on the synchronous update results of the three-dimensional geometric model and the signal model.

7. A terminal, characterized in that, include: Memory for storing multi-model synchronous teaching programs driven by digital twins; A processor is configured to implement the steps of the digital twin-driven multi-model synchronous teaching method as described in claim 1 when executing the digital twin-driven multi-model synchronous teaching system.

8. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the digital twin-driven multi-model synchronous teaching method as described in claim 1.

Images