Visual interaction method, device and equipment based on state probability transition model

Abstract

The invention discloses a visual interaction method, device and equipment based on a state probability transition model, and relates to the technical field of man-machine interaction, and the method comprises the steps: collecting multi-source data, extracting a state feature vector, and fusing the multi-source data; constructing a state transition model based on a state transition graph G = (V, E, P), and dynamically calculating a state transition probability matrix; wherein V is a state set, and the nodes represent different states; e is an edge set, and edges represent possible transfer paths between states; p is an edge weight set, represents a transition probability and can be dynamically updated; a state visualization graph is generated based on the state transition graph G, and dynamic visualization display is rendered through a graphic engine; receiving an interaction operation, triggering the state transition model to update parameters in response to the interaction operation, and recalculating; and responding to different target states and / or strategy parameters of the interaction operation, generating and comparing a plurality of strategy paths, and visually displaying a strategy deduction process. According to the invention, the precision, interaction capability and interpretability of the system are improved.

Description

Technical Field

[0001] This invention relates to the field of human-computer interaction technology, and in particular to a visual interaction method, device, equipment and medium based on a state probability transition model. Background Technology

[0002] In dynamic decision-making scenarios, traditional manual decision-making models suffer from slow response times and low efficiency, while purely automated systems struggle to adapt to highly dynamic and ever-changing state assessments and responses. Human-machine hybrid interactive decision-making, by combining human situational understanding with the computational advantages of machines, is gradually becoming a key paradigm for improving the reliability and adaptability of decision-making.

[0003] In related technologies, human-computer hybrid interaction systems have the following limitations: 1. Using static state diagrams or preset strategy paths results in low accuracy in predicting real-time state evolution. 2. Existing visualization methods (static diagrams, tables, etc.) cannot render the state evolution path in real time, and the dynamic process is not expressed; the system mostly adopts a one-way information display mode, lacking a human-computer feedback loop; 3. The evolutionary logic is not sufficiently visualized, making it difficult for users to understand the underlying rationale of the model's recommendation strategy and resulting in insufficient interpretability of the decisions. Summary of the Invention

[0004] This invention provides a visualization interaction method, device, equipment, and medium based on a state probability transition model, which solves the problems of insufficient prediction accuracy, weak interaction loop, and insufficient decision interpretability in human-computer hybrid interaction systems.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, a visualization and interaction method based on a state probability transition model is provided, including: Collect multi-source data, extract state feature vectors from the multi-source data, and fuse the multi-source data; A state transition model is constructed based on the state transition graph G = (V, E, P), and the state transition probability matrix is ​​dynamically calculated. Here, V is the set of states, and nodes represent different states; E is the set of edges, and edges represent possible transition paths between states; P is the set of edge weights, representing the transition probability, which can be dynamically updated. A state visualization graph is generated based on the state transition graph G, and dynamically visualized using a graphics engine; the displayed content includes: state nodes, transition paths, and state levels. Receive interactive operations, and in response to the interactive operations, trigger the state transition model to update parameters and recalculate; In response to different target states and / or policy parameters included in the interactive operation, multiple policy paths are generated and compared, and the policy deduction process is visualized.

[0006] Secondly, a visualization and interactive device based on a state probability transition model is provided, comprising: The data acquisition and preprocessing module is used to acquire multi-source data, extract state feature vectors from multi-source data, and fuse multi-source data. The state transition modeling module is used to construct a state transition model based on the state transition graph G = (V, E, P) and dynamically calculate the state transition probability matrix; where V is the set of states, and nodes represent different states; E is the set of edges, and edges represent possible transition paths between states; P is the set of edge weights, representing the transition probability, which can be dynamically updated. The visualization graph generation and rendering module is used to generate a state visualization graph based on the state transition graph G, and to render the dynamic visualization display through a graphics engine; the displayed content includes: state nodes, transition paths and state levels. The user interaction control module is used to receive interaction operations and, in response to the interaction operations, trigger the state transition model to update parameters and recalculate them. The decision support and strategy simulation module is used to generate and compare multiple strategy paths in response to different target states and / or strategy parameters contained in the interactive operation, and to visualize the strategy deduction process.

[0007] In a third aspect, an electronic device is provided, the electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the visualization interaction method based on the state probability transition model as described in the first aspect.

[0008] Fourthly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the visualization interaction method based on the state probability transition model as described in the first aspect.

[0009] The visualization and interaction method based on the state probability transition model of the present invention has the following advantages: This application constructs a state transition graph, which intuitively displays the evolutionary logic between states in a graph structure. Combined with dynamic edge weight visualization and semantic node highlighting mechanisms, it significantly improves the user's efficiency in understanding the global state. Simultaneously, it supports users in simulating paths, editing strategies, and receiving real-time feedback through interactive methods, enhancing human-computer collaborative decision-making capabilities. By introducing probabilistic modeling, dynamic graph display, and real-time human-computer interaction mechanisms, it significantly improves the accuracy of state modeling, the interpretability of information presentation, and the system's interactivity. The main advantages include: Accurate modeling: Characterizing complex state changes through state transition probability maps; Highly visualized: Clearly express state information using graph nodes, paths, colors, and other elements; High interactivity: Supports user input, simulated intervention, and feedback loop; Highly interpretable: The model's predictive logic is clearly visible, enhancing user trust; High decision-making efficiency: Provides real-time strategy simulation and multi-path comparison analysis tools.

[0010] The device, electronic equipment, and readable storage medium corresponding to the visualization interaction method based on the state probability transition model of this invention can achieve the same technical effect, and will not be described in detail here to avoid repetition. Attached Figure Description

[0011] Figure 1 A schematic flowchart illustrating a visualization and interaction method based on a state probability transition model provided in an embodiment of this application; Figure 2 A schematic flowchart illustrating data acquisition and preprocessing provided in this application embodiment; Figure 3 A schematic flowchart illustrating a state diagram modeling principle provided in an embodiment of this application; Figure 4 A visual schematic flowchart provided for embodiments of this application; Figure 5 A schematic diagram of an interaction logic provided for an embodiment of this application; Figure 6 A schematic diagram illustrating the principle of a strategy simulation provided in this application embodiment; Figure 7 A schematic diagram of the structure of a visualization interactive device based on a state probability transition model provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions in the embodiments of this application are clearly described. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art are within the scope of protection of this application.

[0013] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0014] The steps described in the specification and the flowcharts in the accompanying drawings of this invention are not necessarily strictly executed according to the step numbers; the execution order of the method steps can be changed. Furthermore, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be broken down into multiple steps.

[0015] The following detailed description, in conjunction with the accompanying drawings and preferred embodiments, describes the visualization interaction method, apparatus, device, and medium based on the state probability transition model provided in this application.

[0016] Human-machine hybrid interactive decision-making emphasizes the complementary advantages of human experience and intelligent algorithms. By leveraging human intuition, risk awareness, and contextual understanding, it guides or corrects machine judgments under conditions of incomplete information. At the same time, relying on the computational power and pattern recognition advantages of algorithms, it provides humans with decision-making suggestions, state predictions, and visualization support, thereby improving the overall decision-making quality and response efficiency.

[0017] Current human-computer hybrid interaction systems are typically based on the following key technologies: State awareness and modeling techniques: By fusing multi-source data, accurate descriptions and models of the current environmental state are constructed, providing semantic support for subsequent analysis. Common methods include knowledge graphs, Bayesian networks, and Markov decision processes (MDPs).

[0018] Probabilistic reasoning and state transition modeling: In complex policy interaction environments, systems need to predict and evaluate possible future state evolutions. Based on state probabilistic transition models, the dynamic transformation patterns between states can be quantified, providing support for policy selection.

[0019] Visualized interactive interface technology: To enhance the efficiency of human-computer collaboration, it is necessary to use a visual interface to display the state evolution path, probability prediction results and strategy recommendations in real time, so that users can quickly understand and adjust their decision-making direction based on graphical information.

[0020] User-participatory feedback mechanism: Supports human users to intervene in the system's reasoning process through an interactive interface, such as correcting transition probabilities, supplementing semantic information, or adjusting strategy priorities, thereby achieving dynamic collaboration and consensus generation between humans and machines.

[0021] However, existing human-computer interaction methods are mostly limited to static information display, lacking in-depth modeling of dynamic strategy interaction processes and state transition mechanisms, and thus failing to effectively reflect the collaborative mechanisms between humans and machines in the "evolutionary state space." Specifically: 1. Because existing state modeling methods mostly use static state diagrams or preset policy paths, lacking dynamic probability transition mechanisms, their ability to predict state evolution in complex policy interaction environments is insufficient, making it difficult to support real-time decision-making. Disadvantage ①: Lack of probabilistic modeling methods for state evolution, resulting in low prediction accuracy.

[0022] 2. Because the visualization methods for state information are mostly static graphs, tables, or rule-driven interfaces, they fail to incorporate the subjective adjustment behavior of humans in judging the state, resulting in poor interactivity and low decision-making transparency. Disadvantage ②: Human-computer interaction lacks a feedback loop, making it difficult to support user intervention and guidance in the model's reasoning process.

[0023] 3. Due to the lack of visual representation of state evolution paths and decision-making basis, users find it difficult to understand the internal logic of the model's output during the decision-making process, resulting in low credibility of human-machine collaboration. Disadvantage ③: Poor interpretability affects user trust and operational efficiency.

[0024] 4. Because some systems do not consider the uncertainty and probability of state changes, and only display the static optimal path or historical experience, the system's adaptability to changing scenarios is weak. Disadvantage ④: It does not have the ability to robustly handle complex dynamic situations.

[0025] While existing models have established weighted state nodes and transition relationships, they lack effective visualization methods. Users cannot intuitively grasp the overall picture of policy interaction states, the meaning of key nodes, and possible evolution paths, hindering real-time monitoring, teaching demonstrations, or policy evaluation. The lack of real-time visualization support for dynamic evolution processes results in opaque predictions. In actual policy interactions, states change dynamically, requiring users to monitor their current position, reachable states, and probabilistic paths in real time. Existing methods fail to dynamically highlight states in the graph, visualize path predictions, or interactively display future evolution trends, lacking user-friendly interface. Users cannot interactively analyze or edit state graphs to improve decision-making flexibility. Existing systems are mostly one-way displays; users cannot perform in-depth analysis, parameter adjustment, or policy simulation through interactive operations (such as clicking, dragging, filtering, and editing). They do not support policy hypothesis verification and "what-if" analysis, lacking a human-computer collaborative intelligent policy interaction experience. To address the technical problems of low state prediction accuracy, weak interaction mechanisms, and unexplainable decision-making processes in existing technologies, this application proposes an innovative method that integrates state probability transition models with visualization interaction methods to achieve a more efficient and interpretable human-machine hybrid decision support system.

[0026] The application scenarios of this application include complex and dynamic environments such as intelligent transportation, emergency response, and financial risk control. For these high-risk and high-uncertainty scenarios, the core of this application lies in designing a system architecture that integrates "state transition modeling + graphical visualization + real-time interactive feedback + decision simulation" functions. Through dynamic diagrams and human-computer collaborative operation, it enhances state perception and decision support capabilities in complex strategic interactive environments.

[0027] This application is used for decision support in strategic interaction and competitive scenarios. The following explanation uses its application in intelligent transportation and game-based competitive scenarios as examples.

[0028] Please see Figure 1-6 This application provides a visualization and interaction method based on a state probability transition model, such as... Figure 1-2 As shown, it includes: Step S1: Collect multi-source data, extract the state feature vectors of the multi-source data, and fuse the multi-source data.

[0029] As attached Figure 2 As shown, this step involves data acquisition and preprocessing. The corresponding data acquisition and preprocessing module serves as the system's front-end input interface, receiving raw data from the environmental perception system (such as sensors, task platforms, and external databases) and performing feature extraction, dimensionality reduction, and standardization. This module employs a multi-source heterogeneous data fusion strategy (such as Bayesian fusion or weighted average algorithms) to uniformly represent state factors, providing clean and reliable data support for subsequent modeling.

[0030] For example, in a game-based competitive scenario, real-time game status data can be accessed, including the type, location, status, and resource status of individuals on both the red and blue sides.

[0031] For example, in intelligent transportation scenarios, multi-source data can be collected by accessing traffic flow sensors (such as camera AI recognition data), road network GIS databases, and emergency event reporting systems. This includes real-time vehicle speed and occupancy data streams, congestion index vectors output by traffic state estimators, accident point coordinates, and so on.

[0032] Step S2: Construct a state transition model based on the state transition graph G = (V, E, P) and dynamically calculate the state transition probability matrix; where V is the set of states, and nodes represent different states; E is the set of edges, and edges represent possible transition paths between states; P is the set of edge weights, representing the transition probability, which can be dynamically updated.

[0033] The core of this step is to construct a "state transition graph" based on a Markov chain or conditional probabilistic graphical model. For example, in intelligent transportation scenarios, a Markov chain model or conditional probabilistic graphical model is constructed with traffic nodes (intersections) as states and road segment connectivity relationships as edges, dynamically calculating the turning traffic flow transition probability matrix. Similarly, in game-based competitive scenarios, a Markov model or conditional probabilistic graphical model is constructed with the overall state of the game's red and blue players, resources, etc., as nodes, and the transition relationships between different states as edges, dynamically calculating the transition probability matrix between different situations.

[0034] The graph structure supports sparse representation and dynamic edge addition and deletion. State transition probabilities are calculated through historical data statistics or neural network prediction models. To enhance prediction flexibility, a learnable policy weight adjustment mechanism can be introduced to dynamically correct edge weights based on contextual information.

[0035] Figure 3 The diagram shown illustrates the principle of state diagram modeling. The modeling module can be divided into three stages: initial graph construction, dynamic updating, and abnormal state marking. The system also supports abnormal state identification functions, such as state abrupt changes and frequency anomalies, to assist in the prediction of high-risk states.

[0036] Step S3: Generate a state visualization graph based on the state transition graph G, and dynamically display it using a graphics engine; the displayed content includes: state nodes, transition paths, and state levels.

[0037] This step constructs a state visualization graph based on the aforementioned graph G, and uses a graphics engine (such as D3.js, ECharts, or OpenGL) to dynamically display state nodes, transition paths, state levels, and other content on the user interface.

[0038] This step S3 specifically includes: Step S31: Bind the state node to its meaning by encoding it using color, shape and / or label.

[0039] This step is the graph node semantic mapping mechanism: binding state nodes with their meanings (task type, level, risk value) and encoding them using colors, shapes, labels, etc. For example, node colors encode congestion levels (red: congested, green: unobstructed). Alternatively, node colors can represent the degree of threat the current state poses to the red team: red: severe threat, orange: moderate threat, blue: safe.

[0040] Step S32: Edges with a transition probability higher than a set threshold are represented by thicker or brighter lines.

[0041] This step is the path weight dynamic mapping mechanism: edges with higher transition probabilities are represented by thicker or brighter lines to enhance visual guidance. For example, edge width is dynamically mapped to traffic transition probabilities. Similarly, edges with higher adversarial state transition probabilities are represented by thicker or brighter lines.

[0042] Step S33: Highlight active paths or key nodes in real time based on the latest data changes.

[0043] This step is the state tracking mechanism. For example, highlighting congested paths in real time.

[0044] Step S34: Optionally, different auxiliary views can be superimposed on the drawing.

[0045] This step involves a multi-dimensional overlay mechanism. For example, it supports overlaying auxiliary views such as risk heatmaps and time evolution trajectories on the map. Congestion propagation animations are rendered on the road network base map, with arrows indicating the dominant direction of traffic flow. When a user disables a road segment, the associated edges are automatically covered with a semi-transparent mask, and alternative detour routes are displayed.

[0046] In practice, the rendering engine visualization process is as follows: Figure 4 As shown, the system includes steps such as situation mapping, situation calculation, and key information display. The system refreshes the canvas periodically through the rendering engine and binds it to data update events to achieve real-time refresh of the state diagram and response to sudden state changes.

[0047] Step S4: Receive an interactive operation, and in response to the interactive operation, trigger the state transition model to update parameters and recalculate.

[0048] The interactive operations in this step include actions by users, producers, or testers, such as: clicking / hovering nodes to view detailed information; dragging graph structures to rearrange the view structure; drag-and-drop path building functionality, allowing users to simulate paths and view predicted consequences; parameter adjustment panels: such as adjusting state weights, disabling certain paths, etc.; and semantically based flexible interaction, which can support real-time text and voice interaction.

[0049] This step, known as the "interventional path prediction" mechanism, allows users to manually modify the state sequence based on model predictions and feed it back to the prediction module, achieving a symbiotic collaboration between the model and the user. The interaction logic is as follows: Figure 5 As shown, each user interaction triggers a "feedback loop," where the system recalculates the state prediction and policy results, and presents a new evolution path in the diagram.

[0050] For example, it supports dragging and dropping to adjust traffic light timing parameters, manually closing road segment nodes, and triggering model recalculation. It can also change node threat levels and edge connection probabilities.

[0051] Step S5: In response to different target states and / or policy parameters contained in the interactive operation, generate and compare multiple policy paths, and visualize the policy deduction process.

[0052] This step embeds a strategy evolution simulation mechanism based on the graph model. Users can generate and compare the feasibility, risk, and cost of multiple strategy paths by selecting different target states or strategy parameters, and display the strategy deduction process through a "visual sandbox." Specifically, it includes: Multi-path comparison analysis (sorted by cost function, success rate, and risk level), decision suggestion prompts (highlighting recommended paths and reasons), strategy conflict detection (determining path logic conflicts or resource conflicts), and backtracking and version management (supporting undoing and historical comparison).

[0053] Strategy simulation process as follows Figure 6 As shown, each strategy path is encapsulated as a path object, and the system supports displaying multiple solutions simultaneously and automatically labeling their advantages and disadvantages.

[0054] For example, in intelligent transportation scenarios, multiple traffic diversion plans are generated, and predicted travel time and congestion reduction rates are compared. Simultaneously, the overall travel time is minimized while the unobstructed flow of critical rescue channels is maximized. When a traffic diversion plan causes overload in adjacent areas, conflicting road sections are automatically highlighted and an alarm is issued. For instance, in a resource competition scenario, the system can generate attack paths such as "frontal assault," "flank encirclement," and "luring the enemy in," predicting indicators such as target achievement rate, unit loss rate, and key point control time. The system automatically selects the path with the highest achievement rate and lowest cost and highlights it.

[0055] This application constructs a dynamic state modeling mechanism that supports multi-source data-driven approaches. The data acquisition layer supports access to multi-source data, including structured data (logs, sensors) and unstructured data (text, video extraction), which are then abstracted and transformed and uniformly mapped to the state graph model, improving the model's generalization and adaptability.

[0056] A probabilistic state transition graph structure oriented towards state modeling was constructed. For the first time, probabilistic graphical models (such as Markov chains and state transition matrices) were introduced into state perception and decision-making systems, forming a dynamically updatable graph structure with semantic expressive capabilities. Nodes represent system states, edges represent transition relationships between states, and edge weights map transition probabilities or risk values, supporting dynamic growth and adjustment. This improves the predictive ability for complex state evolution in dynamic policy interaction environments by constructing a state transition probability model to model and quantify state changes under the influence of multiple factors.

[0057] A visual mapping machine for point semantics and edge weights was constructed. Through visual design features such as color, shape, edge thickness, and layer overlay, semantic information such as the importance, priority, risk level, and evolution trend of states is intuitively mapped onto the graph. Multi-dimensional graphical effects such as node highlighting, path coloring, and risk heatmap coverage are supported.

[0058] It provides an interactive interface for strategy simulation and path editing. It offers graph-based simulation and deduction capabilities, constructing a visual interactive interface that dynamically presents states, transition paths, and predicted probabilities graphically, enabling users to intuitively understand and interact with the system model. Users can interactively generate or adjust state evolution paths by dragging paths, modifying probabilities, and setting target states. The system automatically calculates the shortest cost / minimum risk / maximum reward for each path, assisting users in formulating or comparing multiple strategy options.

[0059] A real-time feedback and visualization update mechanism was constructed. A human-machine hybrid collaboration mechanism was introduced, allowing users to adjust state variables or intervention strategy selection based on visualized information, thereby optimizing the system's prediction and recommendation results. The system has real-time graph update capabilities: each user interaction (such as node clicks or path changes) triggers background inference, model updates, and automatic refresh of the visualization graph, achieving closed-loop human-machine control. It supports time-series simulation and replay of the state evolution process. This enhances the interpretability and credibility of the decision-making process, strengthening users' ability to participate in the entire process of perception, analysis, and decision-making.

[0060] Furthermore, this application provides a modular architecture design and cross-platform deployability. The system adopts a front-end and back-end decoupled architecture, with each module capable of independent deployment, exhibiting excellent scalability and platform compatibility, and is suitable for various application scenarios such as command and decision-making, industrial operation and maintenance, and network security.

[0061] Compared to existing technologies, traditional systems struggle to simultaneously represent multiple states, multiple paths, and their transition probabilities due to the uncertainty and multi-path nature of state evolution, leading to high understanding costs and delayed policy formulation. The state transition graph constructed in this application can intuitively display the evolutionary logic between states in a graph structure. Combined with dynamic edge weight visualization and semantic node highlighting mechanisms, it significantly improves the user's efficiency in understanding the global state. Simultaneously, the system supports users in simulating paths, editing policies, and receiving real-time feedback through interactive methods, enhancing human-computer collaborative decision-making capabilities. Therefore, compared to existing technologies, this invention has significant advantages in usability, response efficiency, accuracy of state understanding, and policy deduction capabilities. By introducing probabilistic modeling, dynamic graph display, and real-time human-computer interaction mechanisms, it significantly improves the accuracy of state modeling, the interpretability of information presentation, and the system's interactivity. The main advantages include: Accurate modeling: Characterizing complex state changes through state transition probability maps; Highly visualized: Clearly express state information using graph nodes, paths, colors, and other elements; High interactivity: Supports user input, simulated intervention, and feedback loop; Highly interpretable: The model's predictive logic is clearly visible, enhancing user trust; High decision-making efficiency: Provides real-time strategy simulation and multi-path comparison analysis tools.

[0062] This invention is applicable to highly dynamic and highly uncertain fields, such as human-computer collaborative scenarios like command and dispatch, state analysis, and risk warning. It enables the modeling and display of multi-state evolution paths under complex and uncertain scenarios, enhancing the robustness and adaptability of the system. By integrating state probability modeling, human-computer interaction design, and dynamic visualization, it provides a low-latency, highly interpretable, and highly interactive technical solution for decision support in highly dynamic environments, and has broad practical value.

[0063] See Figure 7 Corresponding to the above-described visualization interaction method embodiment based on the state probability transition model, this application embodiment provides a visualization interaction device based on the state probability transition model, including: The data acquisition and preprocessing module 1001 is used to acquire multi-source data, extract state feature vectors from multi-source data, and fuse multi-source data. The state transition modeling module 1002 is used to construct a state transition model based on the state transition graph G = (V, E, P) and dynamically calculate the state transition probability matrix; where V is the set of states, and nodes represent different states; E is the set of edges, and edges represent possible transition paths between states; P is the set of edge weights, representing the transition probability, which can be dynamically updated. The visualization graph generation and rendering module 1003 is used to generate a state visualization graph based on the state transition graph G, and to render a dynamic visualization display through a graphics engine; the display content includes: state nodes, transition paths and state levels. User interaction control module 1004 is used to receive interaction operations and, in response to the interaction operations, trigger the state transition model to update parameters and recalculate them. The decision support and strategy simulation module 1005 is used to generate and compare multiple strategy paths in response to different target states and / or strategy parameters contained in the interactive operation, and to visualize the strategy deduction process.

[0064] Furthermore, the visualization graph generation and rendering module 1002 is specifically used for: Bind state nodes to their meanings and encode them using colors, shapes, and / or labels; Edges with a transition probability higher than a set threshold are represented by thicker or brighter lines; Highlight active paths or key nodes in real time based on the latest data changes; Different auxiliary views can be optionally overlaid on the drawing.

[0065] Furthermore, the decision support and strategy simulation module 1005 is specifically used for: Multi-path comparison analysis, decision suggestion prompts, strategy conflict detection, and backtracking and version management.

[0066] Furthermore, the device is used for intelligent transportation decision support.

[0067] The above-described visualization interaction device based on the state probability transition model implements the steps and processes of the above-described visualization interaction method based on the state probability transition model, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0068] See Figure 8 Corresponding to the above-described visualization interaction method embodiment based on the state probability transition model, this application embodiment provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps and processes of the above-described visualization interaction method embodiment based on the state probability transition model, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0069] The memory 1009 can be used to store software programs and various data. The memory 1009 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback function, image playback function, etc.). Furthermore, the memory 1009 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1009 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0070] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor 1010.

[0071] Corresponding to the above-described visualization interaction method embodiment based on the state probability transition model, this application embodiment also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the steps and processes of the above-described visualization interaction method embodiment based on the state probability transition model, and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0072] The processor is the processor in the electronic device described in the above embodiments of this application. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0073] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0074] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0075] It is understood that the embodiments of this application have been described above in conjunction with the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. As those skilled in the art will know, various changes or equivalent substitutions can be made to these features and embodiments without departing from the spirit and scope of the invention. Furthermore, those skilled in the art, under the guidance or instruction of this application, can modify these features and embodiments to adapt to specific situations and materials without departing from the spirit and scope of the invention. Therefore, this invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the protection scope of this invention.

Claims

1. A visualization and interaction method based on a state probability transition model, characterized in that, include: Collect multi-source data, extract state feature vectors from the multi-source data, and fuse the multi-source data; A state transition model is constructed based on the state transition graph G = (V, E, P), and the state transition probability matrix is ​​dynamically calculated. Here, V is the set of states, and nodes represent different states; E is the set of edges, and edges represent possible transition paths between states; P is the set of edge weights, representing the transition probability, which can be dynamically updated. A state visualization graph is generated based on the state transition graph G, and dynamically visualized using a graphics engine; the displayed content includes: state nodes, transition paths, and state levels. Receive interactive operations, and in response to the interactive operations, trigger the state transition model to update parameters and recalculate; In response to different target states and / or policy parameters included in the interactive operation, multiple policy paths are generated and compared, and the policy deduction process is visualized.

2. The visualization interaction method based on the state probability transition model according to claim 1, characterized in that, The process of generating a state visualization graph based on the state transition graph G and rendering it dynamically using a graphics engine includes: Bind state nodes to their meanings and encode them using colors, shapes, and / or labels; Edges with a transition probability higher than a set threshold are represented by thicker or brighter lines; Highlight active paths or key nodes in real time based on the latest data changes; Different auxiliary views can be optionally overlaid on the drawing.

3. The visualization interaction method based on the state probability transition model according to claim 1, characterized in that, The process of responding to different target states and / or policy parameters included in the interactive operation, generating and comparing multiple policy paths, and visually displaying the policy deduction process includes: Multi-path comparison analysis, decision suggestion prompts, strategy conflict detection, and backtracking and version management.

4. The visualization interaction method based on the state probability transition model according to claim 1, characterized in that, The method is used for intelligent transportation decision support.

5. A visualization and interactive device based on a state probability transition model, characterized in that, include: The data acquisition and preprocessing module is used to acquire multi-source data, extract state feature vectors from multi-source data, and fuse multi-source data. The state transition modeling module is used to construct a state transition model based on the state transition graph G = (V, E, P) and dynamically calculate the state transition probability matrix; where V is the set of states, and nodes represent different states; E is the set of edges, and edges represent possible transition paths between states; P is the set of edge weights, representing the transition probability, which can be dynamically updated. The visualization graph generation and rendering module is used to generate a state visualization graph based on the state transition graph G, and to render the dynamic visualization display through a graphics engine; the displayed content includes: state nodes, transition paths and state levels. The user interaction control module is used to receive interaction operations and, in response to the interaction operations, trigger the state transition model to update parameters and recalculate them. The decision support and strategy simulation module is used to generate and compare multiple strategy paths in response to different target states and / or strategy parameters contained in the interactive operation, and to visualize the strategy deduction process.

6. The visualization and interactive device based on the state probability transition model according to claim 1, characterized in that, The visualization generation and rendering module is specifically used for: Bind state nodes to their meanings and encode them using colors, shapes, and / or labels; Edges with a transition probability higher than a set threshold are represented by thicker or brighter lines; Highlight active paths or key nodes in real time based on the latest data changes; Different auxiliary views can be optionally overlaid on the drawing.

7. The visualization and interactive device based on the state probability transition model according to claim 1, characterized in that, The decision support and strategy simulation module is specifically used for: Multi-path comparison analysis, decision suggestion prompts, strategy conflict detection, and backtracking and version management.

8. The visualization and interactive device based on the state probability transition model according to claim 1, characterized in that, The device is used for intelligent transportation decision support.

9. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the visualization interaction method based on the state probability transition model as described in any one of claims 1 to 4.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the visualization interaction method based on a state probability transition model as described in any one of claims 1 to 4.

Images