Method and device for operating an intelligent platform

Abstract

The application discloses a kind of intelligent platform control method and system, collection operation instruction input signal, and the input signal is processed by multimodal perception unit, generates trigger signal to complete the switching from manual intervention mode to autonomous operation mode, the multimodal perception unit includes voice recognition module, gesture tracking module and touch detection module;According to the preset operation framework diagram, each functional node in intelligent platform is sequentially executed dynamic monitoring, and the real-time state information of each functional node is recorded;Extract the state parameters of the currently running functional node, and correlate analysis is carried out with the state parameters of other functional nodes, to build node relationship map;Based on the node relationship map, the functional node corresponding to the abnormal state parameter is automatically corrected, and its operating parameter is adjusted to normal range.Through dynamic monitoring to functional node and record real-time state, user can accurately perceive platform running state, effectively reduce the risk of misoperation.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and in particular to a method and device for controlling an intelligent platform. Background Technology

[0002] With the continuous advancement of science and technology, intelligent platforms have been widely applied in various fields such as industrial control, smart homes, and aerospace. During the operation of an intelligent platform, it is usually necessary to observe and monitor the operating parameters of each functional module in real time to ensure the stable operation of the system.

[0003] However, existing intelligent platform control technologies still have many shortcomings in practical applications, mainly in the following aspects: First, in terms of interaction methods, existing control modes typically rely on a single input device (such as a keyboard, mouse, or touchscreen) to complete command input. This method is not only cumbersome to operate, but also prone to operator fatigue and low efficiency over long periods of time. Furthermore, in complex environments (such as strong noise interference or drastic changes in lighting), the adaptability and robustness of a single input device are poor, making it difficult to guarantee the accuracy and timeliness of command input.

[0004] Secondly, in terms of status monitoring and feedback, existing technologies often lack real-time, dynamic monitoring and feedback mechanisms for the operational status of each functional node of the system. Operators find it difficult to accurately perceive the operation results or the real-time operating status of the platform, which increases the risk of misoperation and makes it impossible to promptly detect and handle potential problems within the system.

[0005] Third, in terms of anomaly handling and system fault tolerance, existing technologies typically employ manual identification of abnormal parameters or alarm mechanisms based on simple thresholds, lacking in-depth analysis of the relationships between functional nodes. When an anomaly occurs in a node, existing systems struggle to automatically adapt or correct themselves based on the relationships between nodes, resulting in insufficient self-healing capabilities and operational stability. Summary of the Invention

[0006] The purpose of this application is to provide a method and device for controlling an intelligent platform. In view of the lack of a real-time dynamic monitoring and feedback mechanism, this invention enables users to accurately perceive the platform's operating status by performing dynamic monitoring on functional nodes and recording their real-time status, effectively reducing the risk of misoperation and enabling timely detection of potential problems within the system.

[0007] The technical solution provided in this application is as follows: This invention provides a method for controlling an intelligent platform, comprising: S1. Collect operation command input signals, and process the input signals through a multimodal perception unit to generate trigger signals to complete the switch from manual intervention mode to autonomous operation mode. The multimodal perception unit includes a voice recognition module, a gesture tracking module, and a touch detection module. S2. Perform dynamic monitoring on each functional node in the intelligent platform in sequence according to the preset operation framework diagram, and record the real-time status information of each functional node. S3. Extract the status parameters of the currently running functional nodes and perform correlation analysis with the status parameters of other functional nodes to construct a node relationship graph; S4. Based on the node relationship graph, automatically correct the functional nodes corresponding to the abnormal state parameters and adjust their operating parameters to the normal range.

[0008] In a preferred embodiment, acquiring operation command input signals and processing the input signals through a multimodal sensing unit to generate trigger signals to complete the switch from manual intervention mode to autonomous operation mode further includes: The audio signal is acquired through a speech recognition module and converted into text commands. The gesture tracking module captures the user's hand movement trajectory and converts the trajectory into coordinate data; The touch detection module detects the user's actions on the touchscreen and converts the actions into touch signals; The data fusion algorithm integrates text commands, coordinate data, and touch signals into a unified operation command.

[0009] In a preferred embodiment, the process of dynamically monitoring each functional node in the intelligent platform according to a preset operational framework diagram and recording the real-time status information of each functional node further includes: The physical parameters of the functional nodes are collected through a sensor network. These physical parameters include temperature changes, voltage fluctuations, load conditions, and communication delays. The collected physical parameters are stored in a local cache and marked with a timestamp.

[0010] In a preferred embodiment, extracting the state parameters of the currently running functional node and performing correlation analysis with the state parameters of other functional nodes to construct a node relationship graph further includes: Remove outliers and noisy data using data cleaning algorithms; The functional nodes are grouped using the K-means clustering algorithm: The real-time status information of all functional nodes is obtained from the dynamic monitoring module. The real-time status information includes at least physical parameters such as temperature change, voltage fluctuation, load status and communication delay. The number of clusters K is determined according to system requirements, and K functional nodes are randomly selected from all functional nodes as initial cluster centers. Calculate the Euclidean distance from each functional node to the cluster center, and assign the functional node to the nearest cluster; Calculate the mean of the state parameters of all functional nodes in each cluster, and use the mean as the new cluster center to update the cluster center; The allocation and update steps are executed iteratively until the cluster center no longer changes significantly or the preset number of iterations is reached, and functional nodes with similar operating characteristics are grouped into the same category. Calculate the correlation coefficients between functional nodes and draw a node relationship graph based on the correlation coefficients.

[0011] In a preferred embodiment, automatically correcting the functional nodes corresponding to abnormal state parameters based on the node relationship graph and adjusting their operating parameters to the normal range further includes: By querying the node relationship graph, the association between abnormal functional nodes and other normal functional nodes can be determined; The possible causes of the anomaly are analyzed based on the correlation relationship, including the failure of a dependent node or improper parameter settings; Based on the analysis results, specific corrective measures should be formulated. These measures should include at least adjusting the parameters of the abnormal nodes, restarting the relevant services or modules, and increasing resource allocation. Implement corrective measures and monitor the effectiveness of the correction through a feedback mechanism. If the correction fails, adjust the correction strategy and re-execute it.

[0012] In a preferred embodiment, the method further includes: S5. If the abnormal status parameters cannot be restored to the normal range after multiple corrections, the node relationship graph will be reconfigured to generate a new operation framework graph to ensure the normal operation of the current functional nodes. At the same time, the functional nodes corresponding to the abnormal status parameters will be isolated or replaced. The generation of the new runtime framework diagram specifically includes: Analyze the current system's structure and the dependencies between functional nodes to identify key nodes and paths that cause anomalies; Based on the analysis results, a new functional node distribution and connection relationship are designed, including adding redundant nodes, changing data transmission paths, or optimizing resource allocation. The feasibility and stability of the newly generated runtime framework were verified using simulation technology. Deploy the validated new runtime framework into the actual system and update the system's default runtime framework diagram.

[0013] Based on the same concept, the present invention also provides a control device for an intelligent platform, comprising: The data acquisition module is used to acquire operation command input signals and process the input signals through a multimodal perception unit to generate trigger signals to complete the switch from manual intervention mode to autonomous operation mode. The multimodal perception unit includes a voice recognition module, a gesture tracking module, and a touch detection module. The dynamic monitoring module is used to perform dynamic monitoring on each functional node in the intelligent platform in sequence according to the preset operation framework diagram, and record the real-time status information of each functional node. The relationship analysis module is used to extract the status parameters of the currently running functional nodes and perform correlation analysis with the status parameters of other functional nodes to construct a node relationship graph. The parameter correction module is used to automatically correct the functional nodes corresponding to abnormal state parameters based on the node relationship graph, and adjust their operating parameters to the normal range.

[0014] In a preferred embodiment, it also includes The graph reconstruction module is used to reconfigure the node relationship graph and generate a new operating framework graph if the abnormal state parameters cannot be restored to the normal range after multiple corrections. This ensures the normal operation of the current functional nodes and isolates or replaces the functional nodes corresponding to the abnormal state parameters.

[0015] Based on the same concept, the present invention also provides an electronic device, comprising: The memory is used to store the processing program; A processor, which, when executing the processing program, implements the control method of the intelligent platform as described in any of the preceding claims.

[0016] Based on the same concept, the present invention also provides a readable storage medium storing a processing program, which, when executed by a processor, implements the control method of the intelligent platform as described in any of the preceding claims.

[0017] Compared with the prior art, this application has the following advantages: This invention enables users to accurately perceive the platform's operational status by dynamically monitoring and recording the real-time status of functional nodes, effectively reducing the risk of misoperation and promptly identifying potential internal system problems. Addressing the lack of node correlation analysis and adaptive adjustment capabilities in anomaly handling, this invention constructs a node relationship graph to automatically correct abnormal nodes, achieving adaptive adjustment and repair based on node correlation, effectively improving the system's self-healing ability and operational stability. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the intelligent platform control method provided in an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram illustrating the working principle of the multimodal sensing unit in an embodiment of the present invention.

[0020] Figure 3 This is a schematic diagram illustrating the construction and parameter correction logic of the node relationship graph in an embodiment of the present invention.

[0021] Figure 4 This is a structural block diagram of the intelligent platform control device provided in an embodiment of the present invention. Detailed Implementation

[0022] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0023] It should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0024] Example See Figure 1 The technical solution of this embodiment is a method for controlling an intelligent platform, including: S1. Collect operation command input signals, and process the input signals through a multimodal perception unit to generate trigger signals to complete the switch from manual intervention mode to autonomous operation mode. The multimodal perception unit includes a voice recognition module, a gesture tracking module, and a touch detection module. S2. Perform dynamic monitoring on each functional node in the intelligent platform in sequence according to the preset operation framework diagram, and record the real-time status information of each functional node. S3. Extract the status parameters of the currently running functional nodes and perform correlation analysis with the status parameters of other functional nodes to construct a node relationship graph; S4. Based on the node relationship graph, automatically correct the functional nodes corresponding to the abnormal state parameters and adjust their operating parameters to the normal range.

[0025] To address the lack of real-time dynamic monitoring and feedback mechanisms, this invention dynamically monitors and records the real-time status of functional nodes, enabling users to accurately perceive the platform's operational status, effectively reducing the risk of misoperation, and promptly identifying potential internal system problems. Secondly, addressing the limitations of existing technologies such as single interaction methods, low operational efficiency, and poor environmental adaptability, this invention utilizes a multimodal sensing unit combined with voice, gestures, and touch control for signal acquisition and processing, achieving diverse mode switching. This solves the problem of operational fatigue caused by a single input device, significantly improving interactive flexibility and robustness in complex environments. Finally, addressing the lack of node correlation analysis and adaptive adjustment capabilities in anomaly handling, this invention constructs a node relationship graph to automatically correct abnormal nodes, achieving adaptive adjustment and repair based on node correlation, effectively improving the system's self-healing ability and operational stability.

[0026] See Figure 2 In a preferred embodiment, acquiring operation command input signals and processing the input signals through a multimodal sensing unit to generate trigger signals to complete the switch from manual intervention mode to autonomous operation mode further includes: The audio signal is acquired through a speech recognition module and converted into text commands. The gesture tracking module captures the user's hand movement trajectory and converts the trajectory into coordinate data; The touch detection module detects the user's actions on the touchscreen and converts the actions into touch signals; The data fusion algorithm integrates text commands, coordinate data, and touch signals into a unified operation command.

[0027] Specifically, in this embodiment, users can input operation commands in multiple ways. The voice recognition module collects audio signals through a microphone array, and converts them into text commands after filtering and feature extraction; the gesture tracking module uses a camera to capture the user's hand movement trajectory and converts it into coordinate data through image processing algorithms; the touch detection module detects user clicks, swipes, and other operations on the touchscreen using capacitive or resistive sensors and converts them into touch signals. Subsequently, the system integrates text commands, coordinate data, and touch signals into a unified operation command through a data fusion algorithm, generating a trigger signal to complete the mode switching.

[0028] By acquiring and processing input signals for operation commands through a multimodal sensing unit, the problems of low operational efficiency and fatigue caused by traditional single-input devices are solved. The multimodal sensing unit combines speech recognition, gesture tracking, and touch detection, and integrates input signals using data fusion algorithms, improving the flexibility and adaptability of interaction. At the same time, this multimodal interaction method exhibits higher robustness in complex environments (such as noise interference and changes in lighting), ensuring that operation commands accurately reflect user intentions and significantly improving the overall interactive performance of the intelligent platform.

[0029] In a preferred embodiment, the process of dynamically monitoring each functional node in the intelligent platform according to a preset operational framework diagram and recording the real-time status information of each functional node further includes: The physical parameters of the functional nodes are collected through a sensor network. These physical parameters include temperature changes, voltage fluctuations, load conditions, and communication delays. The collected physical parameters are stored in a local cache and marked with a timestamp.

[0030] Specifically, the system has a pre-defined operational framework diagram that outlines the logical connections between all functional nodes in the intelligent platform. The dynamic monitoring module connects to each functional node via a sensor network (such as temperature and current sensors) to collect real-time physical parameters. These parameters include, but are not limited to, node temperature changes, voltage fluctuations, load conditions, and communication latency. The collected physical parameters are stored in a local cache and marked with precise timestamps so that the historical operational trajectory of the nodes can be reconstructed during subsequent analysis.

[0031] By performing dynamic monitoring on each functional node sequentially according to the preset operational framework diagram, the operational status of the intelligent platform can be comprehensively and in real time. By recording real-time status information with timestamps, not only is a detailed data foundation provided for subsequent anomaly analysis, but the risk of misoperation due to lack of real-time feedback can also be avoided, ensuring the synchronization between monitoring results and user input commands.

[0032] In a preferred embodiment, extracting the state parameters of the currently running functional node and performing correlation analysis with the state parameters of other functional nodes to construct a node relationship graph further includes: Remove outliers and noisy data using data cleaning algorithms; The functional nodes are grouped using the K-means clustering algorithm: The real-time status information of all functional nodes is obtained from the dynamic monitoring module. The real-time status information includes at least physical parameters such as temperature change, voltage fluctuation, load status and communication delay. The number of clusters K is determined according to system requirements, and K functional nodes are randomly selected from all functional nodes as initial cluster centers. Calculate the Euclidean distance from each functional node to the cluster center, and assign the functional node to the nearest cluster; Calculate the mean of the state parameters of all functional nodes in each cluster, and use the mean as the new cluster center to update the cluster center; The allocation and update steps are executed iteratively until the cluster center no longer changes significantly or the preset number of iterations is reached, and functional nodes with similar operating characteristics are grouped into the same category. Calculate the correlation coefficients between functional nodes and draw a node relationship graph based on the correlation coefficients.

[0033] The process of constructing the node relationship graph is as follows: First, outliers and noisy data are removed from the collected data using a data cleaning algorithm to ensure data quality. Next, the K-means clustering algorithm is used to group the functional nodes: real-time status information (including temperature changes, voltage fluctuations, load conditions, and communication delays) of all functional nodes is obtained from the dynamic monitoring module; the number of clusters K is determined according to system requirements, and K functional nodes are randomly selected as initial cluster centers; the Euclidean distance from each functional node to each cluster center is calculated, and the node is assigned to the nearest cluster; the mean of the state parameters of all functional nodes within each cluster is calculated as the new cluster center to update the cluster center; the above assignment and update steps are iteratively executed until the cluster centers no longer change significantly or the preset number of iterations is reached, thereby grouping functional nodes with similar operating characteristics into the same category. Finally, the correlation coefficient between functional nodes is calculated, and the node relationship graph is drawn based on the correlation coefficient. The edge weights in the graph represent the strength of influence between nodes.

[0034] By cleaning data and using the K-means clustering algorithm, functional nodes with similar operational characteristics can be scientifically grouped, improving the systematic nature of system management. Based on the clustering results, correlation coefficients are calculated and node relationship graphs are drawn, which not only demonstrates the direct connections between functional nodes but also quantifies the degree of influence between nodes through weight labeling. This provides intuitive and accurate data support for subsequent anomaly localization and correction strategy formulation, enhancing the intelligence level of system analysis.

[0035] In some embodiments, the K-means clustering algorithm is used to group functional nodes. This algorithm is a commonly used unsupervised learning algorithm that is suitable for dividing data points into K clusters with similar characteristics, and then grouping them.

[0036] The following are the specific grouping steps: Data preparation: Obtain real-time status information of all functional nodes from the dynamic monitoring module. This information includes, but is not limited to, physical parameters such as temperature changes, voltage fluctuations, load conditions, and communication delays.

[0037] 1. Determine the number of clusters K: First, the operating parameters of all functional nodes (such as CPU utilization, memory usage, network latency, etc.) are collected and analyzed.

[0038] 2. Choose the K value: The K value represents the number of clusters into which the functional nodes are to be divided. The choice of K value is determined based on the specific requirements of the system and the characteristics of the functional nodes.

[0039] 3. Perform K-means clustering: Initialize cluster centers: Randomly select K functional nodes as initial cluster centers.

[0040] Data point allocation: Calculate the distance from each functional node to each cluster center (usually using Euclidean distance) and allocate it to the nearest cluster.

[0041] Update cluster center: Recalculate the mean of all functional nodes in each cluster and use it as the new cluster center.

[0042] Iterative optimization: Repeat the steps of allocating data points and updating cluster centers until the cluster centers no longer change significantly or the preset number of iterations is reached.

[0043] 4. Grouping Application: Based on the grouping results, functional nodes with similar operating characteristics are grouped into the same category.

[0044] Calculate the correlation coefficients between functional nodes and draw a node relationship graph based on the correlation coefficients.

[0045] In a preferred embodiment, automatically correcting the functional nodes corresponding to abnormal state parameters based on the node relationship graph and adjusting their operating parameters to the normal range further includes: By querying the node relationship graph, the association between abnormal functional nodes and other normal functional nodes can be determined; The possible causes of the anomaly are analyzed based on the correlation relationship, including the failure of a dependent node or improper parameter settings; Based on the analysis results, specific corrective measures should be formulated. These measures should include at least adjusting the parameters of the abnormal nodes, restarting the relevant services or modules, and increasing resource allocation. Implement corrective measures and monitor the effectiveness of the correction through a feedback mechanism. If the correction fails, adjust the correction strategy and re-execute it.

[0046] Specifically, when an abnormal status parameter of a functional node is detected, the system first queries the node relationship graph to determine the association between the abnormal functional node and other normal functional nodes. Based on these associations, the system analyzes possible causes of the anomaly, such as a failure of a dependent node or improper parameter settings. Based on the analysis results, specific corrective measures are formulated, which at least include adjusting the parameters of the abnormal node, restarting related services or modules, and increasing resource allocation. After implementing corrective measures, the system monitors the effectiveness of the correction through a feedback mechanism. If the correction fails, the correction strategy is adjusted and re-executed until the node status returns to normal.

[0047] Association analysis based on node relationship graphs can quickly and accurately pinpoint the root cause of anomalies (such as dependent node failures), avoiding the risks of blind adjustments. The formulated corrective measures encompass various methods, including parameter adjustments, service restarts, and resource allocation, and are combined with a feedback mechanism to form a closed-loop control, effectively improving the system's stability and reliability, and ensuring that the intelligent platform can quickly recover from local anomalies.

[0048] See Figure 1 In a preferred embodiment, the method further includes: S5. If the abnormal status parameters cannot be restored to the normal range after multiple corrections, the node relationship graph will be reconfigured to generate a new operation framework graph to ensure the normal operation of the current functional nodes. At the same time, the functional nodes corresponding to the abnormal status parameters will be isolated or replaced. The generation of the new runtime framework diagram specifically includes: Analyze the current system's structure and the dependencies between functional nodes to identify key nodes and paths that cause anomalies; Based on the analysis results, a new functional node distribution and connection relationship are designed, including adding redundant nodes, changing data transmission paths, or optimizing resource allocation. The feasibility and stability of the newly generated runtime framework were verified using simulation technology. Deploy the validated new runtime framework into the actual system and update the system's default runtime framework diagram.

[0049] Specifically, in this embodiment, the process of generating a new runtime framework diagram includes: First, analyzing the structure and dependencies between functional nodes of the current system to identify key nodes and paths that cause anomalies; then, designing new functional node distributions and connections based on the analysis results, including adding redundant nodes, changing data transmission paths, or optimizing resource allocation; next, using simulation technology to verify the feasibility and stability of the newly generated runtime framework to ensure it can operate normally under various conditions; finally, deploying the verified new runtime framework to the actual system, updating the system's preset runtime framework diagram, and isolating or replacing abnormal nodes.

[0050] When the system faces persistent anomalies that cannot be recovered from through conventional corrections, adaptive reconfiguration at the system architecture level is achieved by reconfiguring the node relationship graph and generating a new operational framework diagram. Simulation technology is introduced to verify the feasibility of the new framework, avoiding secondary failures caused by blind deployment. This process ensures the system's fault tolerance and continuous operation capability in the face of severe failures, further enhancing the system's environmental adaptability and robustness.

[0051] Based on the same concept, the present invention also provides a control device for an intelligent platform, comprising: The data acquisition module is used to acquire operation command input signals and process the input signals through a multimodal perception unit to generate trigger signals to complete the switch from manual intervention mode to autonomous operation mode. The multimodal perception unit includes a voice recognition module, a gesture tracking module, and a touch detection module. The dynamic monitoring module is used to perform dynamic monitoring on each functional node in the intelligent platform in sequence according to the preset operation framework diagram, and record the real-time status information of each functional node. The relationship analysis module is used to extract the status parameters of the currently running functional nodes and perform correlation analysis with the status parameters of other functional nodes to construct a node relationship graph. The parameter correction module is used to automatically correct the functional nodes corresponding to abnormal state parameters based on the node relationship graph, and adjust their operating parameters to the normal range.

[0052] In a preferred embodiment, it also includes The graph reconstruction module is used to reconfigure the node relationship graph and generate a new operating framework graph if the abnormal state parameters cannot be restored to the normal range after multiple corrections. This ensures the normal operation of the current functional nodes and isolates or replaces the functional nodes corresponding to the abnormal state parameters.

[0053] Based on the same concept, the present invention also provides an electronic device, comprising: The memory is used to store the processing program; A processor, which, when executing the processing program, implements the control method of the intelligent platform as described in any of the preceding claims.

[0054] Based on the same concept, the present invention also provides a readable storage medium storing a processing program, which, when executed by a processor, implements the control method of the intelligent platform as described in any of the preceding claims.

[0055] The embodiments of this application have been described in detail above with reference to the accompanying drawings, but this application is not limited to the above embodiments. Even if various changes are made to this application, if these changes fall within the scope of the claims of this application and their equivalents, they shall still fall within the protection scope of this application.

Claims

1. A method for controlling an intelligent platform, characterized in that, include: S1. Collect operation command input signals, and process the input signals through a multimodal perception unit to generate trigger signals to complete the switch from manual intervention mode to autonomous operation mode. The multimodal perception unit includes a voice recognition module, a gesture tracking module, and a touch detection module. S2. Perform dynamic monitoring on each functional node in the intelligent platform in sequence according to the preset operation framework diagram, and record the real-time status information of each functional node. S3. Extract the status parameters of the currently running functional nodes and perform correlation analysis with the status parameters of other functional nodes to construct a node relationship graph; S4. Based on the node relationship graph, automatically correct the functional nodes corresponding to the abnormal state parameters and adjust their operating parameters to the normal range.

2. The control method of the intelligent platform as described in claim 1, characterized in that, The process of acquiring operation command input signals and processing them through a multimodal sensing unit to generate trigger signals to switch from manual intervention mode to autonomous operation mode further includes: The audio signal is acquired through a speech recognition module and converted into text commands. The gesture tracking module captures the user's hand movement trajectory and converts the trajectory into coordinate data; The touch detection module detects the user's actions on the touchscreen and converts the actions into touch signals; The data fusion algorithm integrates text commands, coordinate data, and touch signals into a unified operation command.

3. The control method of the intelligent platform as described in claim 1, characterized in that, According to the preset operational framework diagram, dynamic monitoring is performed sequentially on each functional node in the intelligent platform, and the real-time status information of each functional node is recorded, further including: The physical parameters of the functional nodes are collected through a sensor network. These physical parameters include temperature changes, voltage fluctuations, load conditions, and communication delays. The collected physical parameters are stored in a local cache and marked with a timestamp.

4. The control method of the intelligent platform as described in claim 1, characterized in that, Extracting the status parameters of the currently running functional nodes and performing correlation analysis with the status parameters of other functional nodes to construct a node relationship graph further includes: Remove outliers and noisy data using data cleaning algorithms; The functional nodes are grouped using the K-means clustering algorithm: The real-time status information of all functional nodes is obtained from the dynamic monitoring module. The real-time status information includes at least physical parameters such as temperature change, voltage fluctuation, load status and communication delay. The number of clusters K is determined according to system requirements, and K functional nodes are randomly selected from all functional nodes as initial cluster centers. Calculate the Euclidean distance from each functional node to the cluster center, and assign the functional node to the nearest cluster; Calculate the mean of the state parameters of all functional nodes in each cluster, and use the mean as the new cluster center to update the cluster center; The allocation and update steps are executed iteratively until the cluster center no longer changes significantly or the preset number of iterations is reached, and functional nodes with similar operating characteristics are grouped into the same category. Calculate the correlation coefficients between functional nodes and draw a node relationship graph based on the correlation coefficients.

5. The control method of the intelligent platform as described in claim 1, characterized in that, Automatic correction of functional nodes corresponding to abnormal state parameters based on the node relationship graph, adjusting their operating parameters to the normal range, further includes: By querying the node relationship graph, the association between abnormal functional nodes and other normal functional nodes can be determined; The possible causes of the anomaly are analyzed based on the correlation relationship, including the failure of a dependent node or improper parameter settings; Based on the analysis results, specific corrective measures should be formulated. These measures should include at least adjusting the parameters of the abnormal nodes, restarting the relevant services or modules, and increasing resource allocation. Implement corrective measures and monitor the effectiveness of the correction through a feedback mechanism. If the correction fails, adjust the correction strategy and re-execute it.

6. The control method of the intelligent platform as described in claim 1, characterized in that, The method further includes: S5. If the abnormal status parameters cannot be restored to the normal range after multiple corrections, the node relationship graph will be reconfigured to generate a new operation framework graph to ensure the normal operation of the current functional nodes. At the same time, the functional nodes corresponding to the abnormal status parameters will be isolated or replaced. The generation of the new runtime framework diagram specifically includes: Analyze the current system's structure and the dependencies between functional nodes to identify key nodes and paths that cause anomalies; Based on the analysis results, a new functional node distribution and connection relationship are designed, including adding redundant nodes, changing data transmission paths, or optimizing resource allocation. The feasibility and stability of the newly generated runtime framework were verified using simulation technology. Deploy the validated new runtime framework into the actual system and update the system's default runtime framework diagram.

7. A control device for an intelligent platform, characterized in that, include: The data acquisition module is used to acquire operation command input signals and process the input signals through a multimodal perception unit to generate trigger signals to complete the switch from manual intervention mode to autonomous operation mode. The multimodal perception unit includes a voice recognition module, a gesture tracking module, and a touch detection module. The dynamic monitoring module is used to perform dynamic monitoring on each functional node in the intelligent platform in sequence according to the preset operation framework diagram, and record the real-time status information of each functional node. The relationship analysis module is used to extract the status parameters of the currently running functional nodes and perform correlation analysis with the status parameters of other functional nodes to construct a node relationship graph. The parameter correction module is used to automatically correct the functional nodes corresponding to abnormal state parameters based on the node relationship graph, and adjust their operating parameters to the normal range.

8. The control device for the intelligent platform as described in claim 7, characterized in that, Also includes The graph reconstruction module is used to reconfigure the node relationship graph and generate a new operating framework graph if the abnormal state parameters cannot be restored to the normal range after multiple corrections. This ensures the normal operation of the current functional nodes and isolates or replaces the functional nodes corresponding to the abnormal state parameters.

9. An electronic device, characterized in that, include: The memory is used to store the processing program; A processor that, when executing the processing program, implements the control method of the intelligent platform as described in any one of claims 1 to 6.

10. A readable storage medium, characterized in that, The readable storage medium stores a processing program, which, when executed by a processor, implements the control method of the intelligent platform as described in any one of claims 1 to 6.

Images