A virtual equity operation visual monitoring system based on digital twinning

Abstract

The application discloses a virtual right benefit operation visual monitoring system based on digital twinning, collects full life cycle data through a virtual right benefit digital twinning modeling module, constructs right benefit twins which are real-time mapped with physical operation states, effectively breaks the island problem caused by data fragmentation in traditional systems, and realizes accurate replication of physical world right benefit states in virtual space; secondly, the right benefit operation situation awareness module analyzes the twins in multiple dimensions, generates flow heat maps and risk topology maps, the module makes invisible risk transmission paths explicit, and solves the risk perception lag problem; finally, the visual monitoring display module spatiotemporally aligns and fuses the heat maps, topology maps and level labels to generate a unified situation view, which enables operation personnel to intuitively master flow heat, health zoning and risk traceability paths on a map, and significantly improves the traceability efficiency of abnormal events and the accuracy of operation decisions.

Description

Technical Field

[0001] This invention relates to the field of virtual rights operation monitoring technology, and in particular to a virtual rights operation visualization monitoring system based on digital twins. Background Technology

[0002] With the rapid development of the digital economy, virtual rights (such as points, vouchers, digital collectibles, membership rights, etc.) have become the core carriers for enterprise user operation and commercial monetization. In the existing operation system, virtual rights are usually transferred and managed by a centralized business system. However, with the expansion of business scale and the increasing complexity of rights, the traditional operation model has gradually exposed the following technical defects: (1) Data silos and lack of mapping: The current operation system often separates the issuance, transfer and cancellation of virtual rights into different subsystems, lacking a unified data view. It is difficult for operators to perceive the real transfer path and residence status of rights between different strategy nodes in real time, resulting in the inability to accurately assess the health of rights and only relying on lagging report data for decision-making; (2) Single visualization means and lack of global situation: The existing monitoring screens are mostly lists or simple line charts, lacking an intuitive display of the heat of rights transfer and risk topology. Operators cannot see the transfer trend, health status and potential risk transmission relationship of rights on one chart at the same time, resulting in low efficiency of source investigation and difficulty in realizing the transformation from passive response to active perception. Summary of the Invention

[0003] In view of this, the present invention proposes a virtual rights operation visualization monitoring system based on digital twins, which can effectively solve the defects of existing technologies such as data silos and mapping deficiencies, as well as the lack of a global situation due to the single visualization method.

[0004] The technical solution of this invention is implemented as follows:

[0005] A visualization monitoring system for virtual rights operation based on digital twins, comprising:

[0006] The virtual rights digital twin modeling module is used to collect data on the entire lifecycle of virtual rights and to construct a rights twin that maps the real-time operational status of physical rights based on the data on the entire lifecycle of virtual rights.

[0007] The equity operation status awareness module is used to perform multi-dimensional status analysis on the equity twin and generate equity flow heat map and risk topology map.

[0008] The visualization monitoring and display module is used to display the operational status of the equity twin and, based on the equity flow heatmap and risk topology map, to display causal alarms for abnormal equity events of the equity twin.

[0009] As a further optional solution to the aforementioned virtual rights operation visualization monitoring system based on digital twins, the virtual rights digital twin modeling module includes:

[0010] The data acquisition unit is used to access multi-source heterogeneous data throughout the entire lifecycle of virtual rights from generation, circulation, verification to recycling through a multi-protocol adapter, and to complete data cleaning and time-series normalization based on a timestamp alignment mechanism;

[0011] The rights mapping unit is used to extract entity relationships from the cleaned data using a graph neural network, construct a multimodal association graph including rights attribute nodes, user behavior nodes and operation strategy nodes, and instantiate the multimodal association graph into a rights twin that is synchronized with the physical rights operation status in real time.

[0012] The state anchoring unit is used to continuously detect the mapping deviation between the equity twin and the physical operation status based on the sliding window consistency verification algorithm. When the deviation exceeds the preset threshold, it triggers adaptive correction of the model parameters.

[0013] As a further optional solution to the aforementioned virtual rights operation visualization monitoring system based on digital twins, the rights mapping unit includes:

[0014] The graph topology construction subunit is used to extract entity relationships from cleaned multi-source heterogeneous data using graph neural networks. It abstracts rights attributes, user behavior and operation strategies into heterogeneous nodes, and calculates the semantic correlation between nodes based on the attention mechanism to construct a multimodal association graph.

[0015] The rights entity instantiation subunit is used to map each entity node in the multimodal association graph to its corresponding physical rights operation status, generate a three-dimensional state descriptor including rights attribute vector, behavior feature vector and strategy influence vector, and fuse the three-dimensional state descriptor into a rights twin that is synchronized with the physical rights operation status in real time.

[0016] As a further optional solution to the aforementioned virtual rights operation visualization monitoring system based on digital twins, the rights operation situation awareness module includes:

[0017] The rights and interests circulation heat map analysis unit is used to collect the circulation frequency and residence time of virtual rights and interests in the rights and interests twin in real time among various operational strategy nodes, and generate a rights and interests circulation heat map based on the spatiotemporal density algorithm.

[0018] The rights and interests health assessment unit is used to quantitatively score the operational health status of each virtual right and interest in the rights and interests twin based on a preset multi-dimensional indicator system, and to classify the rights and interests into three levels: normal, sub-healthy and risky based on the scoring results.

[0019] The equity association propagation analysis unit is used to identify implicit association links between equity entities based on the segmentation results, and to calculate the propagation probability and influence radius of risk in the equity network based on the implicit association links, thereby generating a risk topology map.

[0020] As a further optional solution to the aforementioned virtual rights operation visualization monitoring system based on digital twins, the rights transfer heat analysis unit includes:

[0021] The data aggregation subunit is used to collect the frequency and duration of virtual rights in the rights twin in real time among various operation strategy nodes, and aggregate the frequency and duration of the transfers according to the time window and spatial node dimensions to generate a transfer density matrix.

[0022] The thermal rendering subunit is used to calculate the equity aggregation density of each operation strategy node within a preset time period based on the flow density matrix using a spatiotemporal density algorithm, and to perform hierarchical mapping of the aggregation density using thermal gradients to generate an equity flow heatmap.

[0023] As a further optional solution to the aforementioned virtual rights operation visualization monitoring system based on digital twins, the rights association propagation analysis unit includes:

[0024] The implicit link mining subunit is used to receive the equity level classification results, cluster risk-state and sub-health-state equity entities based on the equity level classification results, and use graph embedding algorithm to mine implicit link links between normal-state equity entities to construct an implicit relationship network of equity.

[0025] The propagation probability calculation subunit is used to calculate the propagation probability of a risk event on each associated link based on the implicit relationship network of rights and interests, using a random walk algorithm, and to calculate the risk impact radius by combining the duration of rights and interests residence and the frequency of transfer.

[0026] The risk graph generation subunit is used to map the propagation probability and risk impact radius to the corresponding nodes and edges of the implicit relationship network of rights and interests, thereby generating a risk topology graph, where the node size represents the risk impact radius and the edge thickness represents the propagation probability.

[0027] As a further optional solution to the aforementioned virtual rights operation visualization monitoring system based on digital twins, the visualization monitoring display module includes:

[0028] The situation fusion submodule is used to align the equity flow heatmap with the risk topology map in time and space to generate a unified situation view, and to map the equity level classification results output by the equity health assessment unit to the unified situation view to divide the normal state monitoring area, the sub-healthy state early warning area and the risk state alarm area.

[0029] The root cause alarm display submodule is used to display the risk propagation path in the sub-healthy state warning zone and risk state alarm zone in the unified situation view based on root cause alarm information, using dynamic optical flow along the fused correlation link, and highlighting the abnormal root cause node with flashing marks.

[0030] A method for visual monitoring of virtual rights operation based on digital twins, specifically including:

[0031] Collect data on the entire lifecycle of virtual rights and interests, and construct a rights twin that maps the real-time operational status of physical rights and interests based on the data.

[0032] Multi-dimensional state analysis of the equity twin is performed to generate an equity transfer heat map and a risk topology map.

[0033] The system displays the operational status of the equity twin and provides causal alerts for abnormal equity events based on equity transfer heatmaps and risk topology maps.

[0034] A computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for visual monitoring of virtual rights operation based on digital twins.

[0035] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for visual monitoring of virtual rights operation based on digital twins.

[0036] The beneficial effects of this invention are as follows: Firstly, by using a virtual rights digital twin modeling module, data from the entire lifecycle of virtual rights is collected, constructing a rights twin that maps in real-time to the operational status of physical rights. This not only solves the data silo problem caused by data fragmentation in different subsystems in traditional systems, but also achieves accurate replication of the physical world's rights status in virtual space through digital twin technology, ensuring the integrity and real-time nature of operational data. Secondly, through a visualization monitoring and display module, rights flow heatmaps, risk topology maps, and rights level labels are spatiotemporally aligned and integrated to generate a unified situational view. Operators can then view this unified situational view... The system provides a direct view of the circulation of rights and interests, health zones, and risk tracing paths, enabling a shift from passive response to proactive awareness. This significantly improves the efficiency of tracing abnormal rights and interests events and the accuracy of operational decisions. Furthermore, through the rights and interests operation status awareness module, the system performs multi-dimensional status analysis on the rights and interests twins, generating a rights and interests circulation heatmap and a risk topology map. This process not only quantifies the health status of rights and interests but, more importantly, identifies the implicit links between rights and interests entities. Compared to traditional methods that can only display alarms at a single node, this solution can make the invisible risk transmission paths explicit, effectively solving the problem of delayed risk perception. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0038] Figure 1 This is a schematic diagram illustrating the composition of a virtual rights operation visualization monitoring system based on digital twins according to the present invention.

[0039] Figure 2 This is a flowchart illustrating a method for visual monitoring of virtual rights operation based on digital twins, according to the present invention.

[0040] Figure 3 This is a schematic diagram of the composition of a computing device according to the present invention. Detailed Implementation

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. 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.

[0042] refer to Figures 1 to 3A visualization monitoring system for virtual rights operation based on digital twins includes a virtual rights digital twin modeling module, a rights operation situation awareness module, and a visualization monitoring and display module, wherein:

[0043] A virtual rights digital twin modeling module is used to collect full lifecycle data of virtual rights and construct a rights twin that maps in real time to the operational status of physical rights based on the full lifecycle data of virtual rights; in some embodiments, the virtual rights digital twin modeling module includes:

[0044] The data acquisition unit is used to access multi-source heterogeneous data throughout the entire lifecycle of virtual rights from generation, circulation, verification to recycling through a multi-protocol adapter, and to complete data cleaning and time-series normalization based on a timestamp alignment mechanism;

[0045] The rights mapping unit is used to extract entity relationships from the cleaned data using a graph neural network, construct a multimodal association graph including rights attribute nodes, user behavior nodes and operation strategy nodes, and instantiate the multimodal association graph into a rights twin that is synchronized with the physical rights operation status in real time.

[0046] The state anchoring unit is used to continuously detect the mapping deviation between the equity twin and the physical operation status based on the sliding window consistency verification algorithm. When the deviation exceeds the preset threshold, it triggers adaptive correction of the model parameters.

[0047] Specifically, firstly, the data acquisition unit accesses multi-source heterogeneous data throughout the entire lifecycle of points, from generation, circulation, redemption to recycling, through multi-protocol adapters deployed at the API gateway and database layers. For example, it collects user login logs, points acquisition records, points redemption orders, and backend risk control rule logs. Subsequently, based on a timestamp alignment mechanism, the aforementioned heterogeneous data is cleaned and time-series normalized to eliminate data disorder caused by network latency or system clock deviations, forming a standardized rights and interests circulation log sequence.

[0048] Secondly, the rights mapping unit uses graph neural networks to extract entity relationships from the cleaned data. The system uses rights attributes (such as point value and validity period), user behaviors (such as acquisition, consumption, and transfer), and operational strategies (such as double points activities and expired clearing rules) as different types of nodes to construct a multimodal association graph. Through the embedding algorithm of graph neural networks, the graph is instantiated into a rights twin that is synchronized with the physical rights operation status in real time, ensuring that the virtual model can accurately reflect the complex rights transfer logic in the real world.

[0049] Finally, the state anchoring unit continuously detects the mapping deviation between the rights twin and the physical rights operation status based on the sliding window consistency verification algorithm. The system sets the sliding window size to 5 minutes and calculates the difference between the virtual model status and the physical database status every minute. When the detected deviation exceeds the preset threshold (e.g., the data loss rate exceeds 0.1%), the model parameter adaptive correction mechanism is immediately triggered to dynamically adjust the mapping weights, ensuring that the digital twin always maintains high fidelity and achieves real-time synchronization with the physical world.

[0050] In this way, efficient access and cleaning of multi-source heterogeneous data throughout the entire lifecycle of virtual rights is achieved. Through multi-protocol adapters and timestamp alignment mechanisms, the status quo of data silos in traditional systems is completely broken, ensuring data integrity and temporal accuracy. Secondly, by using graph neural networks to construct multimodal association graphs, it can not only accurately depict the complex implicit relationships between rights attributes, user behavior and operational strategies, but also transform unstructured business logic into a computable graph structure, greatly improving the expressive power of the rights twin. In addition, by introducing sliding window consistency verification and adaptive correction mechanisms, the system can monitor and correct the mapping deviation between the virtual model and the physical entity in real time, effectively preventing model distortion caused by data delays or anomalies, and ensuring the stability and real-time performance of the digital twin under long-term operation.

[0051] In some embodiments, the power mapping unit includes:

[0052] The graph topology construction subunit is used to extract entity relationships from cleaned multi-source heterogeneous data using graph neural networks. It abstracts rights attributes, user behavior and operation strategies into heterogeneous nodes, and calculates the semantic correlation between nodes based on the attention mechanism to construct a multimodal association graph.

[0053] The rights entity instantiation subunit is used to map each entity node in the multimodal association graph to its corresponding physical rights operation status, generate a three-dimensional state descriptor including rights attribute vector, behavior feature vector and strategy influence vector, and fuse the three-dimensional state descriptor into a rights twin that is synchronized with the physical rights operation status in real time.

[0054] Specifically, the graph topology construction subunit uses graph neural networks to extract deep entity relationships from standardized rights and interests transfer logs. The system abstracts rights and interests attributes (such as points value and validity period), user behaviors (such as acquisition, consumption, and transfer), and operational strategies (such as double points activities and expired clearing rules) into heterogeneous nodes. Subsequently, the semantic correlation between nodes is calculated based on an attention mechanism. For example, the system identifies a strong semantic correlation between the "double points activity" node and the "user acquisition behavior" node, thereby constructing a correlation graph containing multimodal information to accurately depict the complex logic behind rights and interests transfer.

[0055] The rights instantiation subunit maps each entity node in the multimodal association graph to its corresponding physical rights operation status. The system generates a three-dimensional state descriptor for each node, including rights attribute vectors, behavioral feature vectors, and strategy influence vectors. For example, for a certain points redemption behavior, the system generates a three-dimensional vector containing redemption amount attributes, user operation characteristics, and activity strategy influence. Finally, these three-dimensional state descriptors are merged to generate a rights twin that is synchronized with the physical rights operation status in real time, ensuring that the virtual model not only contains structural information but also specific business status values.

[0056] Thus, by constructing sub-units through graph topology, the system can automatically identify and quantify the implicit relationships between rights attributes, user behavior, and operational strategies, solving the problem of rigid relationship definitions in traditional modeling and enabling the rights twin to adapt more flexibly to complex business scenarios. Secondly, by using an attention mechanism to weighted calculate semantic relevance, the system can dynamically capture the importance of different nodes in specific scenarios, effectively filtering noisy data and improving the quality of the relational graph construction, providing a more accurate topological foundation for subsequent risk propagation analysis. In addition, by using the three-dimensional state descriptors generated by the rights instantiation sub-units, the system transforms unstructured business logic into computable high-dimensional vectors, achieving full synchronization of the rights twin from structure mapping to state values, greatly enhancing the digital twin's fidelity to the physical world's operational state and its real-time perception capability.

[0057] An equity operation situation awareness module is used to perform multi-dimensional state analysis on the equity twin, generating an equity flow heatmap and a risk topology map; in some embodiments, the equity operation situation awareness module includes:

[0058] The rights and interests circulation heat map analysis unit is used to collect the circulation frequency and residence time of virtual rights and interests in the rights and interests twin in real time among various operational strategy nodes, and generate a rights and interests circulation heat map based on the spatiotemporal density algorithm.

[0059] The rights and interests health assessment unit is used to quantitatively score the operational health status of each virtual right and interest in the rights and interests twin based on a preset multi-dimensional indicator system, and to classify the rights and interests into three levels: normal, sub-healthy and risky based on the scoring results.

[0060] The equity association propagation analysis unit is used to identify implicit association links between equity entities based on the segmentation results, and to calculate the propagation probability and influence radius of risk in the equity network based on the implicit association links, thereby generating a risk topology map.

[0061] Specifically, the rights and interests circulation heat analysis unit collects data in real time on the circulation frequency and residence time of virtual rights and interests in the rights and interests twin across various operational strategy nodes. For example, if the system detects that the residence time of a certain type of points at the "double points activity" node has increased significantly and the circulation frequency has fluctuated abnormally, the system maps these dynamic data to a visualization coordinate system based on the spatiotemporal density algorithm to generate a rights and interests circulation heat map, which intuitively displays the circulation heat and congestion of rights and interests across different strategy nodes.

[0062] The rights and interests health assessment unit quantifies and scores each virtual right of the rights and interests twin based on a preset multi-dimensional indicator system (such as circulation speed, abnormality rate, user satisfaction, etc.). The system divides the rights and interests into three levels: normal, sub-healthy and risky, according to the scoring results. For example, if the abnormal redemption rate of a certain right and interest exceeds the threshold, the system will automatically mark it as risky so that the operations staff can pay close attention to it.

[0063] Based on the above division results, the rights and interests association propagation analysis unit identifies implicit association links between rights and interests entities. The system uses a random walk algorithm to calculate the propagation probability of risk events on each association link, and combines the rights and interests residence time and circulation frequency to calculate the risk impact radius. For example, when a certain risky rights and interests are detected, the system can deduce the possibility of the risk spreading to other rights and interests through association links, thereby generating a risk topology map and clearly showing the potential propagation path of the risk.

[0064] Thus, through the rights and interests circulation heat map analysis unit, the system transforms abstract rights and interests circulation data into intuitive heat maps, enabling operators to identify bottlenecks and hotspots in rights and interests circulation at a glance, solving the pain point of traditional monitoring's difficulty in quantifying circulation activity. Secondly, the rights and interests health assessment unit achieves refined management of rights and interests operation status through quantitative scoring and grading mechanisms, transforming vague operational conditions into clear grade labels. In addition, the rights and interests association and propagation analysis unit connects isolated risk points into a network by mining implicit association links and calculating propagation probabilities, effectively solving the problem of invisible risk transmission paths, enabling the system to provide early warnings of the spread of risks, and greatly improving the initiative and accuracy of risk prevention and control.

[0065] In some embodiments, the equity transfer thermal analysis unit includes:

[0066] The data aggregation subunit is used to collect the frequency and duration of virtual rights in the rights twin in real time among various operation strategy nodes, and aggregate the frequency and duration of the transfers according to the time window and spatial node dimensions to generate a transfer density matrix.

[0067] The thermal rendering subunit is used to calculate the equity aggregation density of each operation strategy node within a preset time period based on the flow density matrix using a spatiotemporal density algorithm, and to perform hierarchical mapping of the aggregation density using thermal gradients to generate an equity flow heatmap.

[0068] Specifically, the data aggregation subunit collects in real time the frequency and duration of virtual rights in the rights twin across various operational strategy nodes. For example, the system detects that during the "double points activity" node, the frequency of virtual rights transfers surges in a short period, and the duration of transfers is significantly extended. The system aggregates this data by time window (e.g., per minute) and spatial node dimension (e.g., activity node, redemption node, expiration node) to generate a transfer density matrix.

[0069] The thermal rendering subunit calculates the equity aggregation density of each operational strategy node within a preset time period based on the flow density matrix and using a spatiotemporal density algorithm. The specific calculation steps are as follows:

[0070] Data standardization: Normalize the frequency of data transfer and the duration of data stay to the 0-1 range to eliminate the influence of units;

[0071] Kernel density estimation: The Gaussian kernel function is used to estimate the spatiotemporal coordinates of each node. The calculation formula is as follows: ,in For kernel function, For the spatiotemporal coordinates of events involving the transfer of rights and interests;

[0072] Gradient classification: Based on the calculated cluster density value, the nodes are divided into three density levels: high, medium, and low, and mapped to three thermal colors: red, yellow, and green, respectively.

[0073] Finally, the system generates a heat map of equity flow, which intuitively displays the flow and congestion of equity between different strategy nodes.

[0074] Thus, through the data aggregation subunit, the system transforms discrete flow events into a structured density matrix, solving the problems of data fragmentation and difficulty in quantification in traditional monitoring. Secondly, by using a spatiotemporal density algorithm for kernel density estimation, the system can smoothly display the aggregation trend of rights and interests in the spatiotemporal dimension, effectively filtering out the interference of single-point abnormal data, so that the heat map can truly reflect the macro trend of rights and interests flow. In addition, through the hierarchical mapping of the heat rendering subunit, the system transforms the complex density calculation results into intuitive color gradients, enabling operators to quickly identify hot spots and bottleneck nodes in rights and interests flow, greatly improving the ability to perceive the status quo of rights and interests and decision-making efficiency.

[0075] In some embodiments, the rights-related propagation analysis unit includes:

[0076] The implicit link mining subunit is used to receive the equity level classification results, cluster risk-state and sub-health-state equity entities based on the equity level classification results, and use graph embedding algorithm to mine implicit link links between normal-state equity entities to construct an implicit relationship network of equity.

[0077] The propagation probability calculation subunit is used to calculate the propagation probability of a risk event on each associated link based on the implicit relationship network of rights and interests, using a random walk algorithm, and to calculate the risk impact radius by combining the duration of rights and interests residence and the frequency of transfer.

[0078] The risk graph generation subunit is used to map the propagation probability and risk impact radius to the corresponding nodes and edges of the implicit relationship network of rights and interests, thereby generating a risk topology graph, where the node size represents the risk impact radius and the edge thickness represents the propagation probability.

[0079] Specifically, the implicit link mining subunit receives the equity level classification results, first performs cluster analysis on risky and sub-healthy equity entities, and then uses graph embedding algorithms (such as Node2Vec) to deeply mine the implicit links between normal equity entities, constructing an equity implicit relationship network that includes all equity entities and their potential relationships. The constructed equity implicit relationship network is then transformed into a mathematical adjacency matrix. In this matrix, if there is an association (edge) between two equity entities, the value at the corresponding position is 1 (or weight value), otherwise it is 0.

[0080] The propagation probability calculation subunit is based on the implicit relationship network of interests and uses a random walk algorithm to calculate the propagation probability of a risk event on each related link. The specific calculation steps are as follows:

[0081] Constructing the transition matrix: Based on the adjacency matrix of the implicit interest relationship network. Calculate the normalized transition probability matrix ,in , indicating from node travel to node The probability of;

[0082] Perform a random walk: Set the number of steps to walk. (e.g., 10 steps) Starting from the risk source node, simulate a large number of random walks (e.g., 10,000 times) and count the frequency of each edge being traversed;

[0083] Calculate the propagation probability: for a certain edge Probability of propagation It equals the number of times the edge is traversed in all paths divided by the total number of paths.

[0084] Calculating the radius of influence: The risk impact radius is calculated by weighting the duration of equity residence at the node and the frequency of equity transfer. ;

[0085] The risk graph generation subunit maps the calculated propagation probability and risk impact radius to the corresponding nodes and edges of the implicit relationship network of rights and interests. The system sets the node size to be proportional to the risk impact radius and the edge thickness to be proportional to the propagation probability, and finally generates a risk topology graph that intuitively shows the range and path of the potential spread of risk.

[0086] Thus, the implicit link mining subunit successfully identified implicit relationships between normal interests that are difficult to discover using traditional methods by utilizing graph embedding algorithms, constructing a complete interest relationship network and solving the problem of invisible risk transmission paths. Secondly, by simulating the risk propagation process through a random walk algorithm, the system can scientifically quantify the propagation probability of each link and calculate the impact radius by combining dwell time, transforming abstract risk relationships into specific numerical indicators, which greatly improves the accuracy of risk assessment. In addition, the risk graph generation subunit transforms complex propagation probabilities and impact radii into intuitive topological structures through visual mapping of node size and edge thickness, enabling operators to identify high-risk propagation paths and core impact nodes at a glance.

[0087] A visualization monitoring and display module is used to display the operational status of the equity twin and, based on the equity flow heatmap and risk topology map, to provide causal alerts for abnormal equity events of the equity twin; in some embodiments, the visualization monitoring and display module includes:

[0088] The situation fusion submodule is used to align the equity flow heatmap with the risk topology map in time and space to generate a unified situation view, and to map the equity level classification results output by the equity health assessment unit to the unified situation view to divide the normal state monitoring area, the sub-healthy state early warning area and the risk state alarm area.

[0089] The root cause alarm display submodule is used to display the risk propagation path in the sub-healthy state warning zone and risk state alarm zone in the unified situation view based on root cause alarm information, using dynamic optical flow along the fused correlation link, and highlighting the abnormal root cause node with flashing marks.

[0090] Specifically, the situation fusion submodule first aligns the equity flow heatmap with the risk topology map in time and space. Using the equity flow heatmap as the base map, the system accurately overlays the nodes and connections in the risk topology map onto the corresponding operational strategy nodes in the heatmap, generating a unified situation view that includes both heat and risk information. Subsequently, the system reads the equity level classification results output by the equity health assessment unit and maps the labels of normal, sub-healthy, and risky states to the corresponding areas in the view, thereby visually clearly delineating the normal state monitoring area, the sub-healthy state early warning area, and the risky state alarm area.

[0091] When the cause-finding alarm display submodule detects an anomaly in the sub-healthy state warning zone or risk state alarm zone in the unified situation view, it immediately triggers an alarm display. Based on the cause-finding alarm information, the system generates dynamic optical flow on the associated links of the risk topology map to simulate the propagation path of risk spreading from the source outward. At the same time, the system locates the root cause node (such as a specific operational strategy node) that caused the abnormal event and highlights and flashes it to guide the operations personnel to quickly pinpoint the source of the problem.

[0092] Thus, through the situational fusion submodule, the system successfully resolved the spatiotemporal inconsistency between heatmaps and topology maps, displaying the flow of rights and risks on the same map, enabling a comprehensive view and greatly enhancing operators' overall perception of complex situations. Secondly, by using the rights and interests level classification results for regional mapping, the system transforms abstract health scores into intuitive red, yellow, and green zones, allowing operators to quickly identify alarm areas requiring key attention, shifting from passively searching for data to proactively monitoring the situation. Furthermore, through the dynamic optical flow and node flashing of the causal alarm display submodule, the system makes invisible risk propagation paths and hidden root cause nodes explicit, effectively shortening the time for fault diagnosis and risk handling, and significantly improving the accuracy and response speed of operational decisions.

[0093] A method for visual monitoring of virtual rights operation based on digital twins, specifically including:

[0094] Collect data on the entire lifecycle of virtual rights and interests, and construct a rights twin that maps the real-time operational status of physical rights and interests based on the data.

[0095] Multi-dimensional state analysis of the equity twin is performed to generate an equity transfer heat map and a risk topology map.

[0096] The system displays the operational status of the equity twin and provides causal alerts for abnormal equity events based on equity transfer heatmaps and risk topology maps.

[0097] A computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for visual monitoring of virtual rights operation based on digital twins.

[0098] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for visual monitoring of virtual rights operation based on digital twins.

[0099] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A visualization monitoring system for virtual rights operation based on digital twins, characterized in that, include: The virtual rights digital twin modeling module is used to collect data on the entire lifecycle of virtual rights and to construct a rights twin that maps the real-time operational status of physical rights based on the data. The equity operation status awareness module is used to perform multi-dimensional status analysis on the equity twin and generate equity flow heat map and risk topology map. The visualization monitoring and display module is used to display the operational status of the equity twin and, based on the equity flow heatmap and risk topology map, to display causal alarms for abnormal equity events of the equity twin.

2. The virtual rights operation visualization monitoring system based on digital twins according to claim 1, characterized in that, The virtual rights digital twin modeling module includes: The data acquisition unit is used to access multi-source heterogeneous data throughout the entire lifecycle of virtual rights from generation, circulation, verification to recycling through a multi-protocol adapter, and to complete data cleaning and time-series normalization based on a timestamp alignment mechanism. The rights mapping unit is used to extract entity relationships from the cleaned data using a graph neural network, construct a multimodal association graph including rights attribute nodes, user behavior nodes and operation strategy nodes, and instantiate the multimodal association graph into a rights twin that is synchronized with the physical rights operation status in real time. The state anchoring unit is used to continuously detect the mapping deviation between the equity twin and the physical operation status based on the sliding window consistency verification algorithm. When the deviation exceeds the preset threshold, it triggers adaptive correction of the model parameters.

3. The virtual rights operation visualization monitoring system based on digital twins according to claim 2, characterized in that, The weight mapping unit includes: The graph topology construction subunit is used to extract entity relationships from cleaned multi-source heterogeneous data using graph neural networks. It abstracts rights attributes, user behavior and operation strategies into heterogeneous nodes, and calculates the semantic correlation between nodes based on the attention mechanism to construct a multimodal association graph. The rights entity instantiation subunit is used to map each entity node in the multimodal association graph to its corresponding physical rights operation status, generate a three-dimensional state descriptor including rights attribute vector, behavior feature vector and strategy influence vector, and fuse the three-dimensional state descriptor into a rights twin that is synchronized with the physical rights operation status in real time.

4. The virtual rights operation visualization monitoring system based on digital twins according to claim 1, characterized in that, The rights and interests operation status awareness module includes: The rights and interests circulation heat map analysis unit is used to collect the circulation frequency and residence time of virtual rights and interests in the rights and interests twin in real time among various operation strategy nodes, and generate rights and interests circulation heat map based on spatiotemporal density algorithm; The rights and interests health assessment unit is used to quantitatively score the operational health status of each virtual right and interest in the rights and interests twin based on a preset multi-dimensional indicator system, and to classify the rights and interests into three levels: normal, sub-healthy and risky based on the scoring results. The equity association propagation analysis unit is used to identify implicit association links between equity entities based on the segmentation results, and to calculate the propagation probability and influence radius of risk in the equity network based on the implicit association links, thereby generating a risk topology map.

5. The virtual rights operation visualization monitoring system based on digital twins according to claim 4, characterized in that, The equity transfer thermal analysis unit includes: The data aggregation subunit is used to collect the frequency and duration of virtual rights in the rights twin in real time among various operation strategy nodes, and aggregate the frequency and duration of the transfer and the duration of the transfer according to the time window and spatial node dimensions to generate a transfer density matrix. The thermal rendering subunit is used to calculate the equity aggregation density of each operation strategy node within a preset time period based on the flow density matrix using a spatiotemporal density algorithm, and to perform hierarchical mapping of the aggregation density using thermal gradients to generate an equity flow heatmap.

6. The virtual rights operation visualization monitoring system based on digital twins according to claim 5, characterized in that, The rights-related propagation analysis unit includes: The implicit link mining subunit is used to receive the equity level classification results, cluster risk-state and sub-health-state equity entities based on the equity level classification results, and use graph embedding algorithm to mine implicit link links between normal-state equity entities to construct an implicit relationship network of equity. The propagation probability calculation subunit is used to calculate the propagation probability of a risk event on each associated link based on the implicit relationship network of rights and interests, using a random walk algorithm, and to calculate the risk impact radius by combining the duration of rights and interests residence and the frequency of transfer. The risk graph generation subunit is used to map the propagation probability and risk impact radius to the corresponding nodes and edges of the implicit relationship network of rights and interests, thereby generating a risk topology graph, where the node size represents the risk impact radius and the edge thickness represents the propagation probability.

7. The virtual rights operation visualization monitoring system based on digital twins according to claim 1, characterized in that, The visualization monitoring display module includes: The situation fusion submodule is used to align the equity flow heatmap with the risk topology map in time and space to generate a unified situation view, and to map the equity level classification results output by the equity health assessment unit to the unified situation view to divide the normal state monitoring area, the sub-healthy state early warning area and the risk state alarm area. The root cause alarm display submodule is used to display the risk propagation path in the sub-healthy state warning zone and risk state alarm zone in the unified situation view based on root cause alarm information, using dynamic optical flow along the fused correlation link, and highlighting the abnormal root cause node with flashing marks.

8. A method for visual monitoring of virtual rights operation based on digital twins, characterized in that, Specifically, it includes: Collect data on the entire lifecycle of virtual rights and interests, and construct a rights twin that maps the real-time operational status of physical rights and interests based on the data. Multi-dimensional state analysis of the equity twin is performed to generate an equity transfer heat map and a risk topology map. The system displays the operational status of the equity twin and provides causal alerts for abnormal equity events based on equity transfer heatmaps and risk topology maps.

9. A computing device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the virtual rights operation visualization monitoring method based on digital twins as described in claim 8.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the virtual rights operation visualization monitoring method based on digital twins as described in claim 8.

Images