Multi-platform compatibility optimization method and system for carrying equipment controller

Abstract

The invention relates to the technical field of carrying equipment. The multi-platform compatibility optimization method and system for the carrying equipment controller are provided, and the method comprises the following steps: carrying out dynamic monitoring and topology analysis processing on a network node connection relationship of a carrying equipment cluster, and generating a dynamic network topological graph and a link state data set; performing training processing on the mapping relation between the network state and the protocol parameter, and generating a protocol parameter dynamic adjustment strategy and a protocol decision table; performing real-time switching processing on the cross-platform communication protocol stack to generate a control instruction data stream compatible with multiple platforms; performing dynamic updating processing on a reward function of the reinforcement learning model, triggering protocol parameter optimization to be executed again, and generating an iterative optimization protocol parameter dynamic adjustment strategy; the problems that topology awareness and dynamic response depended on by static routing are missing, protocol switching and compression ratio self-adaptive adjustment of network parameter solidification are invalid, and cross-platform instruction conflicts and transmission efficiency degradation of heterogeneous protocol adaptation are caused are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of handling equipment, and particularly to a method and system for optimizing the multi-platform compatibility of a handling equipment controller. Background Art

[0002] With the rapid development of industrial automation and intelligent logistics, handling equipment clusters (such as AGV fleets and unmanned forklifts) undertake core material handling tasks in scenarios such as warehousing logistics, flexible manufacturing, and port transportation. Real-time communication protocol adaptation in a dynamic network environment is a key technology to ensure the collaborative operation of multiple devices, directly affecting the reliability of instruction transmission and the system response efficiency.

[0003] However, traditional dynamic networking communication technologies have the following problems in protocol dynamic adaptation: Static routing dependence leads to the lack of real-time topology awareness, and it is unable to dynamically respond to link state changes caused by node movement; Network parameter solidification results in the inability to switch protocols and adjust compression ratios, lacking an adaptive mechanism driven by bandwidth and packet loss rate; Rigid adaptation of heterogeneous protocol stacks hinders the dynamic loading of hardware characteristics, leading to cross-platform instruction stream conflicts and deteriorated transmission efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a method and system for optimizing the multi-platform compatibility of a handling equipment controller for the above technical problems, so as to solve the problems of the lack of topology awareness and dynamic response caused by static routing dependence, the failure of protocol switching and adaptive adjustment of compression ratios due to network parameter solidification, and the cross-platform instruction conflicts and deteriorated transmission efficiency caused by rigid adaptation of heterogeneous protocols.

[0005] In a first aspect, the present application provides a method for optimizing the multi-platform compatibility of a handling equipment controller, and the method includes:

[0006] Based on the real-time status data of network nodes collected by distributed probes, dynamically monitor and perform topology analysis on the network node connection relationships of the handling equipment cluster to generate a dynamic network topology map and a link state data set;

[0007] Based on the dynamic network topology map and the link state data set, train the mapping relationship between the network state and protocol parameters through a reinforcement learning model to generate a protocol parameter dynamic adjustment strategy and a protocol decision table;

[0008] According to the protocol parameter dynamic adjustment strategy, perform real-time switching on the cross-platform communication protocol stack, and dynamically load a protocol adaptation layer based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms;

[0009] Based on the control instruction data stream compatible with multiple platforms, verify and process the protocol switching delay and data integrity in the simulation environment, trigger the primary and backup channel switching through the redundant link backup mechanism, generate the link health report and the control instruction data stream for stable transmission, and control the handling equipment to perform operations based on the control instruction data stream for stable transmission;

[0010] Based on the link health report and the protocol switching log, perform dynamic update processing on the reward function of the reinforcement learning model, optimize the parameter weights of the protocol decision table, and trigger the re-execution of protocol parameter optimization to generate an iterative optimization strategy for dynamic adjustment of protocol parameters.

[0011] Furthermore, based on the dynamic network topology graph and the link state data set, train the mapping relationship between the network state and the protocol parameters through the reinforcement learning model to generate a strategy for dynamic adjustment of protocol parameters and a protocol decision table, including:

[0012] Based on the dynamic network topology graph, extract the communication load fluctuation characteristics and link stability indicators of network nodes to generate a network state feature vector;

[0013] According to the historical protocol parameter configuration records in the link state data set, construct a reinforcement learning action space including protocol parameter types, weight ranges, and associated constraint conditions;

[0014] Based on the network state feature vector and the reinforcement learning action space, perform multiple rounds of iterative training on the mapping relationship between the network state and the protocol parameters through the policy gradient algorithm to generate a strategy for dynamic adjustment of protocol parameters;

[0015] Perform discretization encoding on the parameter configuration rules in the strategy for dynamic adjustment of protocol parameters to generate a protocol decision table, which includes the mapping relationship between protocol types, parameter thresholds, and link states.

[0016] Furthermore, based on the network state feature vector and the reinforcement learning action space, perform multiple rounds of iterative training on the mapping relationship between the network state and the protocol parameters through the policy gradient algorithm to generate a strategy for dynamic adjustment of protocol parameters, including:

[0017] Based on the communication load fluctuation characteristics and link stability indicators in the network state feature vector, perform priority sorting on the protocol parameter types in the reinforcement learning action space to generate an action priority weight table;

[0018] According to the action priority weight table and the real-time communication delay threshold of the link state data set, construct a reinforcement learning training environment including protocol parameter constraint conditions and a dynamic reward function;

[0019] In the reinforcement learning training environment, the exploration-exploitation balance training process is carried out on the mapping relationship between network states and protocol parameters through the policy gradient algorithm to generate an initial dynamic adjustment policy;

[0020] Based on the historical execution success rate and link health metrics of the initial dynamic adjustment policy, the initial dynamic adjustment policy is screened for effectiveness through a policy evaluation function to generate an optimized protocol parameter dynamic adjustment policy.

[0021] Furthermore, according to the protocol parameter dynamic adjustment policy, real-time switching processing is performed on the cross-platform communication protocol stack, and the protocol adaptation layer is dynamically loaded based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms, including:

[0022] Based on the protocol priority rules in the protocol parameter dynamic adjustment policy, weight sorting is performed on the candidate protocols of the cross-platform communication protocol stack to generate a protocol priority table;

[0023] According to the protocol priority table and the current network load status, parallel caching and conflict detection processing are performed on the instruction streams of the primary and backup protocol stacks through a dual-protocol stack buffer queue to generate conflict-free protocol switching instructions;

[0024] Based on the hardware instruction set architecture and peripheral interface types of the target platform, feature parsing is performed on the driver module of the protocol adaptation layer to generate hardware compatibility configuration parameters;

[0025] According to the hardware compatibility configuration parameters, the protocol adaptation layer matching the target platform is dynamically loaded, and instruction set conversion processing is performed on the conflict-free protocol switching instructions to generate an intermediate standardized instruction stream;

[0026] Based on the data frame verification results of the intermediate standardized instruction stream, redundant bit filling and protocol header correction processing are performed to generate a control instruction data stream compatible with multiple platforms.

[0027] Furthermore, according to the protocol priority table and the current network load status, parallel caching and conflict detection processing are performed on the instruction streams of the primary and backup protocol stacks through a dual-protocol stack buffer queue to generate conflict-free protocol switching instructions, including:

[0028] Based on the protocol weight values in the protocol priority table and the current network load status, priority verification is performed on the instruction streams of the primary and backup protocol stacks to generate a dynamically adjusted protocol execution priority sequence;

[0029] Parallel caching and timestamp alignment processing are performed on the instruction streams of the primary and backup protocol stacks through a dual-protocol stack buffer queue to generate a synchronized buffer instruction queue;

[0030] Match the conflict characteristics of the data frame format and instruction parameters in the synchronous buffer instruction queue according to the preset protocol conflict rule library, and generate a conflict detection result set;

[0031] Based on the conflict detection result set and the dynamically adjusted protocol execution priority sequence, perform protocol field replacement or priority override processing on the conflict instruction stream to generate a conflict-free protocol switching instruction.

[0032] Further, based on the control instruction data stream compatible with multiple platforms, verify the protocol switching delay and data integrity in the simulation environment, and trigger the primary and backup channel switching through the redundant link backup mechanism to generate a link health report and a stable transmission control instruction data stream, including:

[0033] Build a simulation verification environment containing multi-dimensional network state simulation parameters based on the protocol type of the control instruction data stream compatible with multiple platforms and the hardware characteristics of the target platform;

[0034] In the simulation verification environment, perform dynamic threshold detection processing on the response delay fluctuation and data frame integrity of the protocol switching instruction to generate a protocol switching performance evaluation result;

[0035] Based on the delay overrun and data loss events in the protocol switching performance evaluation result, dynamically adjust the switching priority of the primary and backup channels through the redundant link backup mechanism to generate an optimized link switching strategy;

[0036] According to the optimized link switching strategy, perform timing alignment and redundant check bit filling processing on the control instruction streams of the primary and backup links through the dual-channel synchronous verification mechanism to generate a conflict-free redundant instruction stream;

[0037] Build a link health quantification model based on the transmission success rate and channel load balancing metrics of the conflict-free redundant instruction stream, and generate a link health report and a stable transmission control instruction data stream.

[0038] Further, based on the link health report and the protocol switching log, perform dynamic update processing on the reward function of the reinforcement learning model, optimize the parameter weights of the protocol decision table, and trigger the re-execution of the protocol parameter optimization to generate an iteratively optimized protocol parameter dynamic adjustment strategy, including:

[0039] Build a multi-dimensional link health evaluation matrix based on the transmission success rate, delay fluctuation, and load balancing metrics in the link health report to generate a dynamic reward function update coefficient set;

[0040] According to the historical parameter configuration records and switching success rate in the protocol switching log, perform incremental update processing on the parameter weights of the protocol decision table, and retain the valid parameter weights that meet the preset health threshold to generate a candidate parameter weight set;

[0041] Update the coefficient set based on the dynamic reward function, and perform gradient backpropagation adjustment on the immediate reward calculation rule of the reinforcement learning model to generate a reinforcement learning model adapted to the current link state;

[0042] Through the reinforcement learning model adapted to the current link state, perform multiple rounds of Monte Carlo policy evaluation on the candidate parameter weight set to screen out the optimized parameter weights that meet the balance conditions of stability and efficiency;

[0043] According to the optimized parameter weights and the failure event types in the protocol switching log, trigger the re-execution instruction for protocol parameter optimization to generate an iteratively optimized dynamic adjustment strategy for protocol parameters.

[0044] In a second aspect, the present application also provides a multi-platform compatibility optimization system for a handling device controller, and the system includes:

[0045] A dynamic topology monitoring module, configured to perform dynamic monitoring and topology analysis on the network node connection relationship of the handling device cluster based on the real-time state data of network nodes collected by distributed probes, and generate a dynamic network topology map and a link state data set;

[0046] A reinforcement learning training module, configured to perform training on the mapping relationship between the network state and protocol parameters through a reinforcement learning model based on the dynamic network topology map and the link state data set, and generate a dynamic adjustment strategy for protocol parameters and a protocol decision table;

[0047] A protocol switching adaptation module, configured to perform real-time switching on the cross-platform communication protocol stack according to the dynamic adjustment strategy of protocol parameters, and dynamically load a protocol adaptation layer based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms;

[0048] A simulation verification redundancy switching module, configured to verify the protocol switching delay and data integrity in a simulation environment based on the control instruction data stream compatible with multiple platforms, trigger the main and backup channel switching through a redundant link backup mechanism, generate a link health report and a control instruction data stream for stable transmission, and control the handling device to perform operations based on the control instruction data stream for stable transmission;

[0049] A dynamic optimization iteration module, configured to perform dynamic update processing on the reward function of the reinforcement learning model based on the link health report and the protocol switching log, optimize the parameter weights of the protocol decision table, and trigger the re-execution of protocol parameter optimization to generate an iteratively optimized dynamic adjustment strategy for protocol parameters.

[0050] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of any of the methods in the first aspect of the present application are implemented.

[0051] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the methods in the first aspect of the present application are implemented.

[0052] The technical solution provided by the present application includes the following technical effects: By providing a method and system for optimizing the multi-platform compatibility of a handling equipment controller, including: based on the real-time status data of network nodes collected by distributed probes, dynamically monitoring and topologically analyzing the connection relationships of network nodes in a handling equipment cluster to generate a dynamic network topology map and a link status data set; based on the dynamic network topology map and the link status data set, training the mapping relationship between the network status and protocol parameters through a reinforcement learning model to generate a protocol parameter dynamic adjustment strategy and a protocol decision table; according to the protocol parameter dynamic adjustment strategy, performing real-time switching processing on the cross-platform communication protocol stack, and dynamically loading a protocol adaptation layer based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms; based on the control instruction data stream compatible with multiple platforms, verifying the protocol switching delay and data integrity in a simulation environment, and triggering the main and standby channel switching through a redundant link backup mechanism to generate a link health report and a control instruction data stream for stable transmission, and controlling the handling equipment to perform operations based on the control instruction data stream for stable transmission; based on the link health report and the protocol switching log, dynamically updating the reward function of the reinforcement learning model, optimizing the parameter weights of the protocol decision table, and triggering the re-execution of protocol parameter optimization to generate an iteratively optimized protocol parameter dynamic adjustment strategy to solve the problems of missing topological awareness and dynamic response of static routing dependence, failure of protocol switching and adaptive adjustment of compression ratio due to solidified network parameters, and cross-platform instruction conflicts and deteriorated transmission efficiency caused by rigid heterogeneous protocol adaptation. Description of the Drawings

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 It is a flowchart of the method for optimizing the multi-platform compatibility of a handling equipment controller in an embodiment of the present invention;

[0055] Figure 2Flowchart for training the mapping relationship between network status and protocol parameters through a reinforcement learning model based on a dynamic network topology graph and a link state data set in an embodiment of the present invention to generate a protocol parameter dynamic adjustment strategy and a protocol decision table;

[0056] Figure 3 Structural diagram of a multi-platform compatibility optimization system for a handling equipment controller in an embodiment of the present invention. Detailed implementation manners

[0057] In order to make the above objects, features, and advantages of the present application more obvious and understandable, the following describes the specific real-time manners of the present application in detail with reference to the accompanying drawings. Many specific details are set forth in the following description to fully understand the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the application. Therefore, the present application is not limited by the specific embodiments disclosed below.

[0058] As Figure 1 shown, the present application provides a multi-platform compatibility optimization method for a handling equipment controller, and the method includes:

[0059] S101: Based on the real-time status data of network nodes collected by distributed probes, dynamically monitor and perform topology analysis on the network node connection relationships of the handling equipment cluster to generate a dynamic network topology graph and a link state data set.

[0060] Specifically, deploy distributed probes on each network node of the handling equipment cluster. The above probes can collect relevant status data of network nodes in real time, such as information such as the IP address, port number, communication load, throughput, and latency of the nodes, as well as the connection relationships between nodes. Collect and integrate the above-mentioned collected real-time status data of network nodes to form a data set including network node information and mutual relationships. Through data processing and analysis algorithms, perform preliminary processing on the data set to remove noise and abnormal data to improve the accuracy of subsequent analysis. Based on the processed data, use network topology analysis technology to dynamically monitor the network node connection relationships of the handling equipment cluster. Sense the changes in the network topology structure in real time, including the addition and withdrawal of nodes, the establishment or interruption of connection links, etc., and at the same time analyze the dynamic change trend of network connections to predict possible network bottlenecks or fault points.

[0061] Based on dynamic monitoring, further perform topological analysis on the connection relationships of network nodes. Using relevant algorithms such as graph theory, abstract the network nodes and their connection relationships into a graph model, representing the devices in the network with nodes and the connection links between devices with edges, and endowing the edges with corresponding attributes such as bandwidth and delay. Through the construction and analysis of the graph model, reveal the structural characteristics of the network and the relationship patterns between nodes, and identify key nodes and important links. According to the results of the topological analysis, generate a dynamic network topology graph. The topology graph intuitively displays information such as the distribution of network nodes, connection relationships, and link states in the handling equipment cluster, providing a visual basis for network management and optimization. At the same time, based on the collected network node status data and the link attribute information obtained during the topological analysis process, organize and generate a link status data set. This data set includes detailed status information of each link, which can be used for subsequent network performance evaluation and protocol parameter adjustment, etc., providing basic data support for cross-platform compatibility optimization.

[0062] S102: Based on the dynamic network topology graph and the link status data set, use a reinforcement learning model to train and process the mapping relationship between network status and protocol parameters, and generate a protocol parameter dynamic adjustment strategy and a protocol decision table.

[0063] Specifically, extract key information such as the communication load fluctuation characteristics and link stability of network nodes from the dynamic network topology graph, generate a vector including multi-dimensional network status characteristics to represent the current operating conditions of the network. Based on the historical protocol parameter configuration records accumulated in the link status data set, construct a reinforcement learning action space, clarify the types of protocol parameters, weight ranges, and the association constraint conditions between different parameters, providing an operation range and rules for subsequent parameter adjustment. Combine the generated network status characteristic vector with the constructed reinforcement learning action space, use the policy gradient algorithm to build a training framework for the mapping relationship between network status and protocol parameters, and according to the preset reward mechanism, through multiple rounds of iterative training, continuously optimize and adjust the strategy to generate an effective protocol parameter dynamic adjustment strategy. Perform discretization encoding on the parameter configuration rules in the obtained protocol parameter dynamic adjustment strategy, and generate a clear and easy-to-query and execute protocol decision table according to the corresponding relationship between protocol types, parameter thresholds, and link states, providing a basis for the rapid adjustment and selection of protocol parameters in the actual communication process.

[0064] S103: According to the protocol parameter dynamic adjustment strategy, perform real-time switching on the cross-platform communication protocol stack, and dynamically load the protocol adaptation layer based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms.

[0065] Specifically, according to the protocol priority rules in the protocol parameter dynamic adjustment strategy, the candidate protocols of the cross-platform communication protocol stack are sorted by weight to generate a protocol priority table, so as to determine the protocols to be preferentially selected in different situations, and adapt to the network conditions and task requirements. According to the protocol priority table and the current network load status, the instruction streams of the primary and backup protocol stacks are parallel cached and conflict detected through the dual protocol stack buffer queue to generate conflict-free protocol switching instructions. In the buffer queue, operations such as priority verification and timestamp alignment are performed on the instruction streams of the primary and backup protocol stacks, and according to the preset protocol conflict rule library, conflict feature matching processing is performed on the data frame format and instruction parameters to ensure that there are no conflicts in the instruction stream during the protocol switching process, and to ensure the accuracy and integrity of data transmission. Based on the hardware instruction set architecture and peripheral interface type of the target platform, feature parsing processing is performed on the driver module of the protocol adaptation layer to generate hardware compatibility configuration parameters. This step aims to enable the protocol adaptation layer to fully adapt to the hardware characteristics of the target platform, ensure the stable operation of the protocol on different hardware platforms, and give full play to the performance advantages of the hardware.

[0066] According to the hardware compatibility configuration parameters, the protocol adaptation layer matching the target platform is dynamically loaded, and the instruction set conversion processing is performed on the conflict-free protocol switching instructions to generate an intermediate standardized instruction stream. Through the dynamic loading mechanism, according to the actual situation of the target platform, the corresponding protocol adaptation layer can be flexibly selected and loaded, improving the flexibility and scalability of the system. Based on the data frame verification result of the intermediate standardized instruction stream, through redundant bit filling and protocol header correction processing, a control instruction data stream compatible with multiple platforms is generated. Verifying the data frame can ensure the integrity of the data, while redundant bit filling and protocol header correction can improve the reliability and compatibility of data transmission, enabling the control instruction data stream to be seamlessly transmitted and executed between different platforms.

[0067] S104: Based on the control instruction data stream compatible with multiple platforms, verify the protocol switching delay and data integrity in the simulation environment, and trigger the primary and backup channel switching through the redundant link backup mechanism to generate a link health report and a control instruction data stream for stable transmission, and control the handling device to perform operations based on the control instruction data stream for stable transmission.

[0068] Specifically, based on the protocol type of the control instruction data stream compatible with multiple platforms and the hardware characteristics of the target platform, a simulation verification environment containing multi-dimensional network state simulation parameters is constructed, such as simulating different network bandwidths, latencies, packet loss rates, etc. In the simulation verification environment, dynamic threshold detection processing is performed on the response latency fluctuation and data frame integrity of the protocol switching instruction to generate a protocol switching performance evaluation result, and it is judged whether the latency and data loss are within an acceptable range. Based on the latency overrun and data loss events in the protocol switching performance evaluation result, the switching priority of the primary and backup channels is dynamically adjusted through the redundant link backup mechanism to generate an optimized link switching strategy to improve the reliability and stability of the link.

[0069] According to the optimized link switching strategy, the control instruction streams of the primary and backup links are subjected to timing alignment and redundant check bit filling processing through the dual-channel synchronous verification mechanism to generate a conflict-free redundant instruction stream, ensuring the integrity and consistency of the control instructions during the link switching process. Based on the transmission success rate and channel load balancing index of the conflict-free redundant instruction stream, a link health quantification model is constructed to generate a link health report and a control instruction data stream for stable transmission. The link health report can intuitively reflect the performance and status of the link, providing a basis for subsequent network optimization and maintenance. Based on the control instruction data stream for stable transmission, the handling equipment is controlled to perform operations, ensuring that the handling equipment can complete the material handling task more efficiently and accurately in a reliable network environment.

[0070] S105: Based on the link health report and protocol switching log, perform dynamic update processing on the reward function of the reinforcement learning model, optimize the parameter weights of the protocol decision table, and trigger the re-execution of protocol parameter optimization to generate an iteratively optimized dynamic adjustment strategy for protocol parameters.

[0071] Specifically, based on the transmission success rate, latency fluctuation, and load balancing index in the link health report, a multi-dimensional link health evaluation matrix is constructed to generate a set of dynamic reward function update coefficients. This step quantifies the actual performance of the link into multiple dimensions of indicators, providing a basis for the subsequent update of the reward function. According to the historical parameter configuration records and switching success rate in the protocol switching log, incremental update processing is performed on the parameter weights of the protocol decision table, retaining the effective parameter weights that meet the preset health threshold to generate a set of candidate parameter weights. By analyzing the historical data, the parameter weights that perform well in actual applications are screened out, providing a reference for subsequent optimization. Based on the set of dynamic reward function update coefficients, gradient backpropagation adjustment processing is performed on the immediate reward calculation rule of the reinforcement learning model to generate a reinforcement learning model adapted to the current link state. This step enables the reinforcement learning model to dynamically adjust its reward calculation method according to the actual state of the current link, thereby better guiding the optimization of protocol parameters.

[0072] Through a reinforcement learning model that adapts to the current link state, perform multiple rounds of Monte Carlo policy evaluation on the set of candidate parameter weights to screen out the optimized parameter weights that meet the balance conditions of stability and efficiency. Use the Monte Carlo policy evaluation method to repeatedly evaluate and screen the candidate parameter weights to ensure that the selected optimized parameter weights can achieve a balance between stability and efficiency. According to the optimized parameter weights and the failure event types in the protocol switching log, trigger the re-execution instruction for protocol parameter optimization to generate an iterative optimized dynamic adjustment strategy for protocol parameters. According to the obtained optimization results, restart the protocol parameter optimization process to generate a more optimized dynamic adjustment strategy for protocol parameters, continuously improving the performance and reliability of the system.

[0073] An embodiment of the present application provides a method for optimizing the multi-platform compatibility of a handling device controller, including: based on the real-time state data of network nodes collected by distributed probes, perform dynamic monitoring and topology analysis on the network node connection relationships of the handling device cluster to generate a dynamic network topology map and a link state data set; based on the dynamic network topology map and the link state data set, train the mapping relationship between the network state and protocol parameters through a reinforcement learning model to generate a dynamic adjustment strategy for protocol parameters and a protocol decision table; according to the dynamic adjustment strategy for protocol parameters, perform real-time switching on the cross-platform communication protocol stack, and dynamically load the protocol adaptation layer based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms; based on the control instruction data stream compatible with multiple platforms, verify the protocol switching delay and data integrity in the simulation environment, and trigger the main and standby channel switching through the redundant link backup mechanism to generate a link health report and a stable transmission control instruction data stream, and control the handling device to perform operations based on the stable transmission control instruction data stream; based on the link health report and the protocol switching log, dynamically update the reward function of the reinforcement learning model, optimize the parameter weights of the protocol decision table, and trigger the re-execution of protocol parameter optimization to generate an iterative optimized dynamic adjustment strategy for protocol parameters to solve the problems of missing topological awareness and dynamic response of static routing dependence, failure of protocol switching and adaptive adjustment of compression ratio of network parameter solidification, and cross-platform instruction conflict and transmission efficiency degradation of heterogeneous protocol adaptation rigidity.

[0074] As Figure 2 shown, based on the dynamic network topology map and the link state data set, training the mapping relationship between the network state and protocol parameters through a reinforcement learning model to generate a dynamic adjustment strategy for protocol parameters and a protocol decision table includes:

[0075] S201: Based on the dynamic network topology map, extract the communication load fluctuation characteristics and link stability indicators of network nodes to generate a network state feature vector.

[0076] S202: Construct a reinforcement learning action space containing protocol parameter types, weight ranges, and associated constraint conditions based on the historical protocol parameter configuration records in the link state dataset;

[0077] S203: Based on the network state feature vector and the reinforcement learning action space, perform multiple rounds of iterative training on the mapping relationship between the network state and protocol parameters through the policy gradient algorithm to generate a dynamic adjustment policy for protocol parameters;

[0078] S204: Perform discretized encoding processing on the parameter configuration rules in the dynamic adjustment policy for protocol parameters to generate a protocol decision table, which includes the mapping relationship between protocol types, parameter thresholds, and link states.

[0079] Specifically, extract key information such as the communication load fluctuation characteristics of network nodes and link stability indicators from the dynamic network topology graph, perform integration and quantization processing on them, and generate a network state feature vector that can reflect the network state. Then, based on the historical protocol parameter configuration records accumulated in the link state dataset, deeply analyze the types, weight ranges of protocol parameters, and the associated constraint conditions between different parameters, and construct a reinforcement learning action space to provide a clear operation range and constraint rules for subsequent mapping relationship training.

[0080] After that, combine the generated network state feature vector with the constructed reinforcement learning action space, and use the policy gradient algorithm to perform multiple rounds of iterative training on the mapping relationship between the network state and protocol parameters. During the training process, by continuously adjusting and optimizing the policy, the model can learn the optimal protocol parameter configuration under different network state characteristics and generate an effective dynamic adjustment policy for protocol parameters. Then, perform discretized encoding processing on the parameter configuration rules in the obtained dynamic adjustment policy for protocol parameters, and generate a clear protocol decision table that is convenient for querying and execution according to the mapping relationship between protocol types, parameter thresholds, and link states, providing a basis for the rapid adjustment and selection of protocol parameters in the actual communication process.

[0081] Furthermore, based on the network state feature vector and the reinforcement learning action space, perform multiple rounds of iterative training on the mapping relationship between the network state and protocol parameters through the policy gradient algorithm to generate a dynamic adjustment policy for protocol parameters, including:

[0082] Based on the communication load fluctuation characteristics and link stability indicators in the network state feature vector, perform priority sorting on the protocol parameter types in the reinforcement learning action space to generate an action priority weight table;

[0083] According to the action priority weight table and the real-time communication delay threshold of the link state dataset, construct a reinforcement learning training environment including protocol parameter constraint conditions and a dynamic reward function;

[0084] In the reinforcement learning training environment, the exploration-exploitation balance training process is carried out on the mapping relationship between network states and protocol parameters through the policy gradient algorithm to generate an initial dynamic adjustment policy.

[0085] Based on the historical execution success rate and link health metrics of the initial dynamic adjustment policy, the initial dynamic adjustment policy is screened for effectiveness through a policy evaluation function to generate an optimized protocol parameter dynamic adjustment policy.

[0086] Specifically, key elements such as the communication load fluctuation characteristics and link stability metrics in the network state feature vector are analyzed in depth. Combining the above network state information, a priority ranking process is carried out on the types of protocol parameters in the reinforcement learning action space to generate an action priority weight table. This process aims to determine the protocols to be preferentially selected in different situations to adapt to network conditions and task requirements. Subsequently, based on the generated action priority weight table and the real-time communication delay threshold in the link state dataset, a reinforcement learning training environment containing protocol parameter constraint conditions and a dynamic reward function is constructed. In this environment, the adjustment of protocol parameters will be subject to corresponding constraints, and the dynamic reward function will give corresponding rewards according to the matching degree between network states and protocol parameters to guide the model to learn the optimal mapping relationship.

[0087] In the constructed reinforcement learning training environment, the exploration-exploitation balance training process is carried out on the mapping relationship between network states and protocol parameters using the policy gradient algorithm. During the training process, the algorithm will continuously explore new protocol parameter configurations and make full use of existing knowledge to find the best protocol parameter combinations in different network states to generate an initial dynamic adjustment policy. Subsequently, based on key performance metrics such as the historical execution success rate of the initial dynamic adjustment policy and link health metrics, the initial dynamic adjustment policy is screened for effectiveness through a policy evaluation function. This process will eliminate poorly performing policy configurations and retain parameter configurations that exhibit good performance in actual applications, thus generating an optimized protocol parameter dynamic adjustment policy to provide strong decision-making support for the real-time switching and adaptation of cross-platform communication protocol stacks.

[0088] Furthermore, according to the protocol parameter dynamic adjustment policy, real-time switching of the cross-platform communication protocol stack is carried out, and the protocol adaptation layer is dynamically loaded based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms, including:

[0089] Based on the protocol priority rules in the protocol parameter dynamic adjustment policy, a weight ranking process is carried out on the candidate protocols of the cross-platform communication protocol stack to generate a protocol priority table;

[0090] According to the protocol priority table and the current network load status, parallel caching and conflict detection processing are performed on the instruction streams of the primary and standby protocol stacks through the dual-protocol stack buffer queue to generate conflict-free protocol switching instructions;

[0091] Based on the hardware instruction set architecture and peripheral interface types of the target platform, feature parsing processing is performed on the driver modules of the protocol adaptation layer to generate hardware compatibility configuration parameters;

[0092] According to the hardware compatibility configuration parameters, the protocol adaptation layer matching the target platform is dynamically loaded, and instruction set conversion processing is performed on the conflict-free protocol switching instructions to generate an intermediate standardized instruction stream;

[0093] Based on the data frame verification results of the intermediate standardized instruction stream, a control instruction data stream compatible with multiple platforms is generated through redundant bit filling and protocol header correction processing.

[0094] Specifically, according to the protocol priority rules in the protocol parameter dynamic adjustment strategy, the candidate protocols of the cross-platform communication protocol stack are weighted and sorted to generate a protocol priority table. This step aims to determine the preferred protocol type in different scenarios, so as to better fit the current network environment and task requirements. According to the protocol priority table and the current network load status, parallel caching and conflict detection processing are performed on the instruction streams of the primary and standby protocol stacks through the dual-protocol stack buffer queue to generate conflict-free protocol switching instructions. In the buffer queue, operations such as priority verification and timestamp alignment are performed on the instruction streams of the primary and standby protocol stacks, and conflict feature matching processing is performed on the data frame format and instruction parameters according to the preset protocol conflict rule library to ensure that there are no conflicts in the instruction stream during the protocol switching process, and to ensure the accuracy and integrity of data transmission.

[0095] Based on the hardware instruction set architecture and peripheral interface types of the target platform, feature parsing processing is performed on the driver modules of the protocol adaptation layer to generate hardware compatibility configuration parameters. According to the above parameters, the protocol adaptation layer matching the target platform is dynamically loaded, and instruction set conversion processing is performed on the conflict-free protocol switching instructions to generate an intermediate standardized instruction stream. This ensures the stable operation of the protocol on different hardware platforms and gives full play to the performance advantages of the hardware. Based on the data frame verification results of the intermediate standardized instruction stream, a control instruction data stream compatible with multiple platforms is generated through redundant bit filling and protocol header correction processing. Verifying the data frame can ensure the integrity of the data, while redundant bit filling and protocol header correction can improve the reliability and compatibility of data transmission, enabling the control instruction data stream to be seamlessly transmitted and executed between different platforms.

[0096] Furthermore, according to the protocol priority table and the current network load status, parallel caching and conflict detection processing are performed on the instruction streams of the primary and standby protocol stacks through the dual-protocol stack buffer queue to generate conflict-free protocol switching instructions, including:

[0097] Based on the protocol weight values in the protocol priority table and the current network load status, perform priority verification processing on the instruction streams of the primary and standby protocol stacks to generate a dynamically adjusted protocol execution priority sequence;

[0098] Perform parallel caching and timestamp alignment processing on the instruction streams of the primary and standby protocol stacks through a dual-protocol stack buffer queue to generate a synchronized buffer instruction queue;

[0099] According to the preset protocol conflict rule library, perform conflict feature matching processing on the data frame formats and instruction parameters in the synchronized buffer instruction queue to generate a conflict detection result set;

[0100] Based on the conflict detection result set and the dynamically adjusted protocol execution priority sequence, perform protocol field replacement or priority override processing on the conflict instruction stream to generate a conflict-free protocol switching instruction.

[0101] Specifically, based on the protocol weight values in the protocol priority table and the current network load status, perform priority verification processing on the instruction streams of the primary and standby protocol stacks to generate a dynamically adjusted protocol execution priority sequence. This step ensures that under the current network conditions, the most suitable protocol is preferentially selected for data transmission to improve network efficiency and reliability. Perform parallel caching and timestamp alignment processing on the instruction streams of the primary and standby protocol stacks through a dual-protocol stack buffer queue to generate a synchronized buffer instruction queue. In the buffer queue, perform priority verification and timestamp alignment on the instruction streams of the primary and standby protocol stacks to ensure that the instruction streams remain synchronized during the processing, providing a basis for subsequent conflict detection.

[0102] According to the preset protocol conflict rule library, perform conflict feature matching processing on the data frame formats and instruction parameters in the synchronized buffer instruction queue to generate a conflict detection result set. This step identifies the data frame formats and instruction parameters in the instruction stream that may cause conflicts by matching the preset conflict rules, providing a basis for subsequent conflict resolution. Based on the conflict detection result set and the dynamically adjusted protocol execution priority sequence, perform protocol field replacement or priority override processing on the conflict instruction stream to generate a conflict-free protocol switching instruction. By replacing the conflicting protocol fields or adjusting the priorities of the instructions, ensure that there are no conflicts in the instruction stream during the protocol switching process, guaranteeing the integrity and accuracy of data transmission.

[0103] Furthermore, based on the control instruction data stream compatible with multiple platforms, verify and process the protocol switching delay and data integrity in the simulation environment, and trigger the primary and backup channel switching through the redundant link backup mechanism, generating a link health report and a stable transmission control instruction data stream, including: constructing a simulation verification environment containing multi-dimensional network state simulation parameters based on the protocol type of the control instruction data stream compatible with multiple platforms and the hardware characteristics of the target platform; in the simulation verification environment, perform dynamic threshold detection on the response delay fluctuation of the protocol switching instruction and the data frame integrity, generating a protocol switching performance evaluation result; based on the delay overrun and data loss events in the protocol switching performance evaluation result, dynamically adjust the switching priority of the primary and backup channels through the redundant link backup mechanism, generating an optimized link switching strategy; according to the optimized link switching strategy, perform timing alignment and redundant check bit filling on the control instruction streams of the primary and backup links through the dual-channel synchronization verification mechanism, generating a conflict-free redundant instruction stream; based on the transmission success rate and channel load balancing index of the conflict-free redundant instruction stream, construct a link health quantification model, generating a link health report and a stable transmission control instruction data stream.

[0104] Specifically, construct a simulation verification environment containing multi-dimensional network state simulation parameters based on the protocol type of the control instruction data stream compatible with multiple platforms and the hardware characteristics of the target platform. Combine factors such as network topology structure, communication protocol characteristics, and hardware performance indicators to generate simulation parameters such as network delay, packet loss rate, and bandwidth fluctuation, comprehensively restoring the possible network scenarios. At the same time, consider the hardware characteristics of the target platform, such as processor performance, memory capacity, and storage speed, to configure the simulation environment.

[0105] In the simulation verification environment, perform dynamic threshold detection on the response delay fluctuation of the protocol switching instruction and the data frame integrity, generating a protocol switching performance evaluation result. Real-time monitor the response delay fluctuation during the protocol switching process, and ensure that no packets are lost or damaged during the protocol switching process through data frame integrity detection technologies such as checksum and hash value comparison. Compare the delay fluctuation and data loss situation during the protocol switching process with the preset threshold, generating a protocol switching performance evaluation result. The content includes key indicators such as the number of delay overruns and data loss rate, providing an important basis for link optimization.

[0106] Based on the latency overrun and data loss events in the protocol switching performance evaluation results, the switching priorities of the primary and backup channels are dynamically adjusted through the redundant link backup mechanism to generate an optimized link switching strategy. According to the protocol switching performance evaluation results, the bottlenecks and potential fault points in the network are identified, and combined with the redundant link backup mechanism, the switching priorities of the primary and backup channels are dynamically adjusted. When a network failure or performance degradation occurs, the data transmission can be quickly and smoothly switched to the backup link to ensure the continuity and reliability of data transmission. The adjusted link switching strategy is comprehensively evaluated to ensure its effectiveness and stability in various network scenarios, and an optimized link switching strategy is generated.

[0107] According to the optimized link switching strategy, the timing alignment and redundant check bit filling processes are performed on the control instruction streams of the primary and backup links through the dual-channel synchronous verification mechanism to generate a conflict-free redundant instruction stream. During the data transmission process, the status of the primary and backup links is monitored in real time to ensure the synchronous transmission of the control instruction streams between the primary and backup links. The redundant check bit filling process is performed on the control instruction streams to enhance the reliability and anti-interference ability of the data. Conflict detection and resolution are performed on the synchronized primary and backup link control instruction streams to ensure that there are no conflicts or data loss during the link switching process, and a conflict-free redundant instruction stream is generated.

[0108] Based on the transmission success rate of the conflict-free redundant instruction stream and the channel load balancing index, a link health quantification model is constructed to generate a link health report and a control instruction data stream for stable transmission. A link health quantification model is established to quantitatively evaluate the health status of the link. According to the link health quantification model, the operating status of the link is monitored and analyzed in real time to generate a link health report. The content includes the health score of the link, fault warning information, etc. The conflict-free redundant instruction stream is optimized into a control instruction data stream for stable transmission to ensure its stability and reliability in various network environments.

[0109] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown in the direction of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0110] In one embodiment, as Figure 3As shown in the figure, the present application also provides a multi-platform compatibility optimization system 300 for a handling equipment controller. The system 300 includes:

[0111] A dynamic topology monitoring module 301, which is used to dynamically monitor and perform topology analysis on the network node connection relationship of the handling equipment cluster based on the real-time status data of network nodes collected by distributed probes, and generate a dynamic network topology map and a link status data set;

[0112] A reinforcement learning training module 302, which is used to train the mapping relationship between the network state and protocol parameters through a reinforcement learning model based on the dynamic network topology map and the link status data set, and generate a protocol parameter dynamic adjustment strategy and a protocol decision table;

[0113] A protocol switching adaptation module 303, which is used to perform real-time switching on the cross-platform communication protocol stack according to the protocol parameter dynamic adjustment strategy, and dynamically load a protocol adaptation layer based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms;

[0114] A simulation verification redundancy switching module 304, which is used to verify the protocol switching delay and data integrity in a simulation environment based on the control instruction data stream compatible with multiple platforms, trigger the main and standby channel switching through a redundant link backup mechanism, generate a link health report and a control instruction data stream for stable transmission, and control the handling equipment to execute operations based on the control instruction data stream for stable transmission;

[0115] A dynamic optimization iteration module 305, which is used to dynamically update the reward function of the reinforcement learning model based on the link health report and the protocol switching log, optimize the parameter weights of the protocol decision table, trigger the re-execution of protocol parameter optimization, and generate an iteratively optimized protocol parameter dynamic adjustment strategy.

[0116] Specifically, the dynamic topology monitoring module 301 uses distributed probes to collect the real-time status data of network nodes. The above data includes key information such as the connection relationship, communication load, and link stability of network nodes. Through the dynamic monitoring and topology analysis of the above data, a dynamic network topology map and a link status data set are generated. The reinforcement learning training module 302 trains the mapping relationship between the network state and protocol parameters through a reinforcement learning model. Extract the communication load fluctuation characteristics and link stability indicators of network nodes to generate a network state feature vector. According to the historical protocol parameter configuration records in the link status data set, construct a reinforcement learning action space including protocol parameter types, weight ranges, and associated constraint conditions. Use the policy gradient algorithm to perform multiple rounds of iterative training on the mapping relationship between the network state and protocol parameters to generate a protocol parameter dynamic adjustment strategy. And perform discretization encoding on the parameter configuration rules in the protocol parameter dynamic adjustment strategy to generate a protocol decision table.

[0117] The protocol switching adaptation module 303 dynamically adjusts the policy according to the protocol parameters and performs real-time switching processing on the cross-platform communication protocol stack. Based on the protocol priority rules, it performs weight sorting on the candidate protocols of the cross-platform communication protocol stack to generate a protocol priority table. According to the protocol priority table and the current network load status, it performs parallel caching and conflict detection processing on the instruction streams of the primary and backup protocol stacks through the dual-protocol stack buffer queue to generate conflict-free protocol switching instructions. At the same time, based on the hardware instruction set architecture and peripheral interface type of the target platform, it performs feature parsing on the driver module of the protocol adaptation layer to generate hardware compatibility configuration parameters. According to the hardware compatibility configuration parameters, it dynamically loads the protocol adaptation layer matching the target platform and performs instruction set conversion processing on the conflict-free protocol switching instructions to generate an intermediate standardized instruction stream. Then, based on the data frame verification result of the intermediate standardized instruction stream, it performs redundant bit filling and protocol header correction processing to generate a control instruction data stream compatible with multiple platforms.

[0118] The simulation verification redundancy switching module 304 verifies the protocol switching latency and data integrity in the simulation environment. It constructs a simulation verification environment containing multi-dimensional network state simulation parameters, and performs dynamic threshold detection on the response latency fluctuation and data frame integrity of the protocol switching instructions in it to generate a protocol switching performance evaluation result. Based on the latency overrun and data loss events in the protocol switching performance evaluation result, it dynamically adjusts the switching priority of the primary and backup channels through the redundant link backup mechanism to generate an optimized link switching strategy. According to the optimized link switching strategy, it performs timing alignment and redundant check bit filling on the control instruction streams of the primary and backup links through the dual-channel synchronization verification mechanism to generate a conflict-free redundant instruction stream. Based on the transmission success rate and channel load balancing metrics of the conflict-free redundant instruction stream, it constructs a link health quantification model to generate a link health report and a control instruction data stream for stable transmission, and controls the handling device to perform operations based on the control instruction data stream for stable transmission.

[0119] The dynamic optimization iteration module 305 performs dynamic update processing on the reward function of the reinforcement learning model. A multi-dimensional link health evaluation matrix is constructed, and a set of dynamic reward function update coefficients is generated. According to the historical parameter configuration records and switching success rates in the protocol switching log, incremental update processing is performed on the parameter weights of the protocol decision table, and the valid parameter weights that meet the preset health threshold are retained to generate a set of candidate parameter weights. Based on the set of dynamic reward function update coefficients, gradient backpropagation adjustment processing is performed on the immediate reward calculation rule of the reinforcement learning model to generate a reinforcement learning model adapted to the current link state. Through the reinforcement learning model adapted to the current link state, multi-round Monte Carlo policy evaluation processing is performed on the set of candidate parameter weights to screen out the optimized parameter weights that meet the conditions of stability and efficiency balance. According to the optimized parameter weights and the types of failure events in the protocol switching log, a protocol parameter optimization re-execution instruction is triggered to generate a dynamically adjusted strategy for iterative optimization of protocol parameters.

[0120] In one embodiment, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0121] In one embodiment, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0122] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0123] The above embodiments only represent several implementation manners of the embodiments of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the application embodiments. It should be noted that for those of ordinary skill in the art, without departing from the concept of the embodiments of the present application, several deformations and improvements can still be made, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A method for optimizing the compatibility of a handling equipment controller on multiple platforms, characterized in that: The method comprises: Based on the real-time status data of network nodes collected by distributed probes, the connection relationship of network nodes in the handling equipment cluster is dynamically monitored and topologically analyzed to generate a dynamic network topology diagram and link status data set; Based on the dynamic network topology diagram and link status data set, the mapping relationship between network status and protocol parameters is trained through a reinforcement learning model to generate a protocol parameter dynamic adjustment strategy and a protocol decision table; According to the protocol parameter dynamic adjustment strategy, the cross-platform communication protocol stack is switched in real time, and the protocol adaptation layer is dynamically loaded based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms; Based on the control instruction data stream compatible with multiple platforms, the protocol switching delay and data integrity are verified in a simulation environment, and the primary and standby channel switching is triggered through a redundant link backup mechanism, a link health report and a stably transmitted control instruction data stream are generated, and the handling equipment is controlled to perform operations based on the stably transmitted control instruction data stream; Based on the link health report and the protocol switching log, the reward function of the reinforcement learning model is dynamically updated, the parameter weights of the protocol decision table are optimized, and the protocol parameter optimization is triggered to be re-executed to generate an iteratively optimized protocol parameter dynamic adjustment strategy.

2. The method for optimizing the multi-platform compatibility of a handling equipment controller according to claim 1, characterized in that: Based on the dynamic network topology map and link state data set, the mapping relationship between network state and protocol parameters is trained and processed by a reinforcement learning model to generate a protocol parameter dynamic adjustment strategy and a protocol decision table, including: Based on the dynamic network topology graph, extract the communication load fluctuation characteristics and link stability indicators of the network nodes to generate a network status feature vector; Constructing a reinforcement learning action space including protocol parameter types, weight ranges, and associated constraints based on the historical protocol parameter configuration records in the link state data set; Based on the network state feature vector and the reinforcement learning action space, a mapping relationship between the network state and the protocol parameters is subjected to multiple rounds of iterative training processing by a policy gradient algorithm to generate the protocol parameter dynamic adjustment strategy; Discretization coding is performed on parameter configuration rules in the protocol parameter dynamic adjustment strategy to generate the protocol decision table, which includes a mapping relationship between protocol type, parameter threshold and link status.

3. The method for optimizing the multi-platform compatibility of a handling equipment controller according to claim 2, characterized in that: The method of performing multiple rounds of iterative training on the mapping relationship between the network state and the protocol parameters through a policy gradient algorithm based on the network state feature vector and the reinforcement learning action space to generate the protocol parameter dynamic adjustment strategy includes: Based on the communication load fluctuation characteristics and link stability indicators in the network state feature vector, the protocol parameter types of the reinforcement learning action space are prioritized to generate an action priority weight table; Constructing a reinforcement learning training environment including protocol parameter constraints and a dynamic reward function according to the action priority weight table and the real-time communication delay threshold of the link state data set; In the reinforcement learning training environment, the mapping relationship between the network state and the protocol parameters is explored by the policy gradient algorithm - using the balanced training process to generate an initial dynamic adjustment strategy; Based on the historical execution success rate and link health index of the initial dynamic adjustment strategy, the initial dynamic adjustment strategy is screened for effectiveness through a strategy evaluation function to generate an optimized protocol parameter dynamic adjustment strategy.

4. The method for optimizing the multi-platform compatibility of a handling equipment controller according to claim 1, characterized in that: The method dynamically adjusts the protocol parameters according to the protocol parameters, performs real-time switching processing on the cross-platform communication protocol stack, and dynamically loads the protocol adaptation layer based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms, including: Based on the protocol priority rules in the protocol parameter dynamic adjustment strategy, the candidate protocols of the cross-platform communication protocol stack are weighted and sorted to generate a protocol priority table; According to the protocol priority table and the current network load status, the instruction streams of the primary and standby protocol stacks are cached in parallel and conflict detection is processed through the dual protocol stack buffer queue to generate a conflict-free protocol switching instruction; Based on the hardware instruction set architecture and peripheral interface type of the target platform, feature analysis is performed on the driver module of the protocol adaptation layer to generate hardware compatibility configuration parameters; According to the hardware compatibility configuration parameters, dynamically load a protocol adaptation layer that matches the target platform, and perform instruction set conversion processing on the conflict-free protocol switching instruction to generate an intermediate standardized instruction stream; Based on the data frame verification result of the intermediate standardized instruction stream, the control instruction data stream compatible with multiple platforms is generated through redundant bit filling and protocol header correction processing.

5. The method for optimizing the multi-platform compatibility of a handling equipment controller according to claim 4, characterized in that: The method of performing parallel caching and conflict detection processing on the instruction stream of the primary and standby protocol stacks through the dual protocol stack buffer queues according to the protocol priority table and the current network load state, and generating a conflict-free protocol switching instruction, includes: Based on the protocol weight values ​​in the protocol priority table and the current network load status, priority verification processing is performed on the instruction streams of the primary and standby protocol stacks to generate a dynamically adjusted protocol execution priority sequence; Performing parallel caching and timestamp alignment processing on the instruction streams of the primary and standby protocol stacks through a dual-protocol stack buffer queue to generate a synchronous buffer instruction queue; According to a preset protocol conflict rule library, conflict feature matching processing is performed on the data frame format and instruction parameters in the synchronization buffer instruction queue to generate a conflict detection result set; Based on the conflict detection result set and the dynamically adjusted protocol execution priority sequence, protocol field replacement or priority overwriting processing is performed on the conflict instruction stream to generate the conflict-free protocol switching instruction.

6. The method for optimizing the multi-platform compatibility of a handling equipment controller according to claim 1, characterized in that: The control instruction data stream based on the multi-platform compatibility verifies the protocol switching delay and data integrity in the simulation environment, triggers the main and standby channel switching through the redundant link backup mechanism, generates a link health report and a stable transmission control instruction data stream, including: Based on the protocol type of the control instruction data stream compatible with multiple platforms and the hardware characteristics of the target platform, a simulation verification environment including multi-dimensional network state simulation parameters is constructed; In the simulation verification environment, dynamic threshold detection processing is performed on the response delay fluctuation of the protocol switching instruction and the data frame integrity to generate a protocol switching performance evaluation result; Based on the delay exceeding limit and data loss events in the protocol switching performance evaluation results, the switching priority of the primary and backup channels is dynamically adjusted through the redundant link backup mechanism to generate an optimized link switching strategy; According to the optimized link switching strategy, the control instruction stream of the primary and standby links is time-aligned and redundant check bits are filled through a dual-channel synchronization check mechanism to generate a conflict-free redundant instruction stream; Based on the transmission success rate of the conflict-free redundant instruction stream and the channel load balancing index, a link health quantification model is constructed to generate the link health report and the control instruction data stream for stable transmission.

7. The method for optimizing the multi-platform compatibility of a handling equipment controller according to claim 1, characterized in that: Based on the link health report and the protocol switching log, the reward function of the reinforcement learning model is dynamically updated, the parameter weights of the protocol decision table are optimized, and the protocol parameter optimization is triggered to be re-executed to generate an iteratively optimized protocol parameter dynamic adjustment strategy, including: Based on the transmission success rate, delay fluctuation and load balancing indicators in the link health report, a multi-dimensional link health evaluation matrix is ​​constructed to generate a dynamic reward function update coefficient set; According to the historical parameter configuration records and the switching success rate in the protocol switching log, the parameter weights of the protocol decision table are incrementally updated, the valid parameter weights that meet the preset health threshold are retained, and a candidate parameter weight set is generated; Based on the dynamic reward function update coefficient set, the instant reward calculation rule of the reinforcement learning model is adjusted by gradient back-propagation to generate a reinforcement learning model adapted to the current link state; Through the reinforcement learning model adapted to the current link state, multiple rounds of Monte Carlo strategy evaluation processing are performed on the candidate parameter weight set to screen out the optimized parameter weights that meet the stability and efficiency balance conditions; According to the optimization parameter weights and the failure event types in the protocol switching log, a protocol parameter optimization re-execution instruction is triggered to generate the iteratively optimized protocol parameter dynamic adjustment strategy.

8. The multi-platform compatibility optimization system for handling equipment controllers is characterized by: The system comprises: Dynamic topology monitoring module, which is used to dynamically monitor and perform topology analysis on the connection relationship of network nodes in the handling equipment cluster based on the real-time status data of network nodes collected by distributed probes, and generate dynamic network topology diagrams and link status data sets; A reinforcement learning training module is used to train the mapping relationship between network status and protocol parameters through a reinforcement learning model based on the dynamic network topology map and link status data set, and generate a dynamic adjustment strategy for protocol parameters and a protocol decision table; The protocol switching adaptation module is used to dynamically adjust the strategy according to the protocol parameters, perform real-time switching processing on the cross-platform communication protocol stack, and dynamically load the protocol adaptation layer based on the hardware characteristics of the target platform to generate a control instruction data stream compatible with multiple platforms; A simulation verification redundant switching module is used to verify the protocol switching delay and data integrity in a simulation environment based on the control instruction data stream compatible with multiple platforms, trigger the main and standby channel switching through a redundant link backup mechanism, generate a link health report and a stably transmitted control instruction data stream, and control the handling equipment to perform operations based on the stably transmitted control instruction data stream; The dynamic optimization iteration module is used to dynamically update the reward function of the reinforcement learning model based on the link health report and the protocol switching log, optimize the parameter weights of the protocol decision table, trigger the re-execution of the protocol parameter optimization, and generate an iteratively optimized protocol parameter dynamic adjustment strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for optimizing the multi-platform compatibility of a handling equipment controller according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for optimizing the multi-platform compatibility of a handling equipment controller according to any one of claims 1 to 7 are implemented.

Images