Parameter dynamic configuration method and system of multi-mode wireless module

Abstract

The invention provides a parameter dynamic configuration method and system for a multi-mode wireless module, and the method comprises the steps: obtaining the operation data of the multi-mode wireless module, carrying out the real-time knowledge extraction, and constructing a dynamic knowledge graph; performing graph neural network reasoning on the dynamic knowledge graph to generate an initial parameter configuration scheme; acquiring real-time demand parameters of the multi-mode wireless module, and inputting the real-time demand parameters into a first correction model to obtain a first correction value; acquiring real-time environment parameters of the environment where the multi-mode wireless module is located, and inputting the real-time environment parameters into a second correction model to obtain a second correction value; and correcting the initial parameter configuration scheme based on the first correction value and the second correction value to obtain a final parameter configuration scheme. According to the method and the device, the defects that dynamic association among parameters is difficult to capture in real time, and parameter configuration scheme optimization cannot be carried out by quickly responding to real-time environment parameters and user demand changes are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for dynamically configuring parameters of a multi-mode wireless module. Background Art

[0002] Multi-mode wireless modules (such as DTUs integrating Wi-Fi and BLE) are increasingly used in industrial automation, smart devices, and other scenarios. These modules require dynamic adjustment of configuration parameters (such as operating mode, transmit power, and serial port baud rate) based on real-time operating status, user needs, and environmental conditions to balance performance, power consumption, and reliability. However, existing parameter configuration methods suffer from the following technical bottlenecks: Traditional methods rely on manually defined rules or single machine learning models to process data. However, multi-mode module operational data (such as serial port communication status, wireless signal strength, and power consumption curves) is heterogeneous and multi-source, with complex dependencies between parameters (such as the coupling effect between operating mode and channel selection, and transmit power and temperature). Existing technologies struggle to capture the dynamic correlations between parameters in real time, resulting in configuration solutions that fail to fully reflect the module's true operating status.

[0003] Module operating environments (such as industrial site temperature and electromagnetic interference) and user requirements (such as sudden high-speed transmission or low-power mode) are highly dynamic. Traditional methods typically use fixed thresholds or offline training models for parameter adjustment. These methods cannot quickly respond to real-time environmental parameters (such as sudden temperature changes and increased channel interference) or changing user requirements (such as prioritizing transmission stability). This results in configuration delays and impacts device performance. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method and system for dynamic parameter configuration of a multi-mode wireless module, aiming to overcome the defects of the current method in that it is difficult to capture the dynamic correlation between parameters in real time, and cannot quickly respond to real-time environmental parameters and user demand changes to optimize parameter configuration schemes.

[0005] To achieve the above object, the present invention provides a method for dynamically configuring parameters of a multi-mode wireless module, comprising the following steps: Obtain operating data from multi-mode wireless modules, perform real-time knowledge extraction, and build a dynamic knowledge graph; Performing graph neural network reasoning on the dynamic knowledge graph to generate an initial parameter configuration scheme; Acquire real-time demand parameters of the multi-mode wireless module, input the real-time demand parameters into a first correction model, and obtain a first correction value for the initial parameter configuration solution; Acquire real-time environmental parameters of the environment in which the multi-mode wireless module is located, and input the real-time environmental parameters into a second correction model to obtain a second correction value for the initial parameter configuration scheme; The initial parameter configuration scheme is corrected based on the first correction value and the second correction value to obtain a final parameter configuration scheme.

[0006] Furthermore, the operating data of the multi-mode wireless module includes serial port communication data and power consumption data.

[0007] Furthermore, real-time knowledge extraction is performed to build a dynamic knowledge graph, including: Using named entity recognition technology to extract key entities from the operating data; the key entities include configuration parameters, real-time status, and performance indicators; Identify the association relationships between the key entities through a relationship extraction algorithm; Construct a three-layer knowledge graph including parameter layer, status layer, and indicator layer; store configuration parameters and their value ranges in the parameter layer; store real-time status and its parameters in the status layer; and store performance indicators and their parameters in the indicator layer; Based on the association relationship, the relationship between key entities in the three-layer knowledge graph is annotated to obtain the dynamic knowledge graph.

[0008] Furthermore, graph neural network reasoning is performed on the dynamic knowledge graph to generate an initial parameter configuration scheme, including: Performing graph embedding processing on the dynamic knowledge graph to obtain a time-series enhanced node vector representation; Performing layered graph neural network inference processing on the node vector representation to obtain a parameter association matrix, constraint filtering results, and performance prediction vectors; Performing a multi-objective optimization search process on the parameter association matrix, the constraint filtering result, and the performance prediction vector to obtain an optimal parameter solution set; The optimal parameter solution set is subjected to historical data verification and anomaly detection processing to obtain an initial parameter configuration solution.

[0009] Furthermore, the real-time demand parameter is input into a first correction model to obtain a first correction value for the initial parameter configuration scheme, including: Performing normalization preprocessing on the real-time demand parameters to obtain a normalized demand vector; Performing demand intent analysis on the normalized demand vector to obtain a multi-objective weight distribution vector; Performing parameter sensitivity analysis on the multi-objective weight distribution vector and the initial parameter configuration scheme to obtain a parameter adjustment priority matrix; performing an incremental parameter search on the parameter adjustment priority matrix to obtain a candidate correction parameter set; The candidate correction parameter set is fused to obtain a first correction value.

[0010] Furthermore, the real-time environmental parameters are input into a second correction model to obtain a second correction value for the initial parameter configuration scheme, including: Performing spatiotemporal feature extraction processing on the real-time environmental parameters to obtain an environmental state feature vector; Performing an environmental risk assessment on the environmental state characteristic vector to obtain a parameter constraint adjustment matrix; Performing conflict detection on the initial parameter configuration scheme and the parameter constraint adjustment matrix to obtain an environment-sensitive parameter list; Performing adaptive compensation calculation on the environmental sensitive parameter list to obtain an environmental correction parameter set; The environmental correction parameter set is optimized to obtain the second correction value.

[0011] The present invention also provides a parameter dynamic configuration system for a multi-mode wireless module, comprising: A construction unit is used to obtain the operating data of the multi-mode wireless module, perform real-time knowledge extraction, and build a dynamic knowledge graph; An inference unit, configured to perform graph neural network inference on the dynamic knowledge graph to generate an initial parameter configuration scheme; A first correction unit is configured to obtain real-time demand parameters of the multi-mode wireless module, input the real-time demand parameters into a first correction model, and obtain a first correction value for the initial parameter configuration solution; a second correction unit, configured to obtain real-time environmental parameters of the environment in which the multi-mode wireless module is located, and input the real-time environmental parameters into a second correction model to obtain a second correction value for the initial parameter configuration scheme; The configuration unit is configured to correct the initial parameter configuration scheme based on the first correction value and the second correction value to obtain a final parameter configuration scheme.

[0012] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0013] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0014] The present invention provides a method and system for dynamic configuration of parameters of a multi-mode wireless module, including: obtaining the operating data of the multi-mode wireless module, performing real-time knowledge extraction, and constructing a dynamic knowledge graph; performing graph neural network reasoning on the dynamic knowledge graph to generate an initial parameter configuration scheme; obtaining the real-time demand parameters of the multi-mode wireless module, inputting the real-time demand parameters into a first correction model, and obtaining a first correction value for the initial parameter configuration scheme; obtaining the real-time environmental parameters of the environment in which the multi-mode wireless module is located, inputting the real-time environmental parameters into a second correction model, and obtaining a second correction value for the initial parameter configuration scheme; correcting the initial parameter configuration scheme based on the first correction value and the second correction value to obtain a final parameter configuration scheme. In the present invention, a dynamic knowledge graph reflecting parameter association is constructed through real-time knowledge extraction, an initial scheme is generated using graph neural network reasoning, and the initial scheme is optimized by combining real-time demand and environmental parameters through a dual correction model, breaking through the data association analysis limitations of traditional methods and improving the environmental adaptability, demand response speed, and multi-objective optimization capabilities of the configuration scheme. It overcomes the shortcomings of current methods that are difficult to capture the dynamic correlation between parameters in real time, and cannot quickly respond to changes in real-time environmental parameters and user needs to optimize parameter configuration solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 1 is a schematic diagram of the steps of a method for dynamically configuring parameters of a multi-mode wireless module in one embodiment of the present invention; Figure 2 This is a structural block diagram of a parameter dynamic configuration system for a multi-mode wireless module according to an embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0016] The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with embodiments. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] Reference Figure 1 In one embodiment of the present invention, a method for dynamically configuring parameters of a multi-mode wireless module is provided, comprising the following steps: Step S1: Acquire the operating data of the multi-mode wireless module, perform real-time knowledge extraction, and construct a dynamic knowledge graph; Step S2, performing graph neural network reasoning on the dynamic knowledge graph to generate an initial parameter configuration scheme; Step S3, obtaining real-time demand parameters of the multi-mode wireless module, inputting the real-time demand parameters into a first correction model, and obtaining a first correction value for the initial parameter configuration solution; Step S4, obtaining real-time environmental parameters of the environment in which the multi-mode wireless module is located, and inputting the real-time environmental parameters into a second correction model to obtain a second correction value for the initial parameter configuration scheme; Step S5: Correct the initial parameter configuration scheme based on the first correction value and the second correction value to obtain a final parameter configuration scheme.

[0019] In one embodiment, as described in step S1 above, operational data is first obtained from the multi-mode wireless module, including serial port communication parameters (e.g., baud rate, parity bit setting), wireless signal indicators (e.g., Wi-Fi signal strength RSSI, Bluetooth connection status), power consumption information, system status information (e.g., operating temperature, supply voltage), and historical configuration records. This data comes from a wide range of sources and has different formats and characteristics, representing multi-source heterogeneous data.

[0020] Next, real-time knowledge extraction is performed on this data. Using natural language processing techniques like named entity recognition and relation extraction, key entities (such as "transmit power" and "operating mode") and relationships between them (such as "high temperatures cause transmit power to decrease" and "AP mode limits the maximum number of connections") are extracted from the data. The extracted knowledge is also timestamped to record the sequence of parameter changes and performance changes, for example, "Switching the operating mode to STA at 2:20 PM resulted in a 10% throughput increase at 2:22 PM."

[0021] Finally, a dynamic knowledge graph is constructed based on the extracted knowledge. The graph consists of a parameter layer (storing configuration parameters and their value ranges), a status layer (recording real-time status data), and an indicator layer (reflecting performance indicators). Nodes in each layer are connected by directed edges, forming a network of relationships between parameters, status, and performance. A graph database (such as Neo4j) is used to update the graph in real time, with an update frequency of no more than 100ms. This ensures that the knowledge graph always reflects the latest operating status of the module, providing structured and dynamic knowledge support for subsequent reasoning.

[0022] As described in step S2 above, deep reasoning is performed using a graph neural network to generate an initial configuration plan that meets basic performance requirements. First, graph embedding techniques (such as Node2Vec) are used to map nodes (parameters, states, and indicators) in the knowledge graph into low-dimensional vectors. This preserves node attributes while capturing the relationship characteristics between nodes. Furthermore, a position-aware graph attention mechanism is used to enhance the weights of timing-dependent edges (such as the latency impact of parameter changes on performance) and causal edges (such as the relationship between baud rate and bit error rate), highlighting the impact of key relationships on reasoning.

[0023] Subsequently, reasoning is performed through a layered graph neural network: in the parameter association layer, a graph convolutional network (GCN) is used to calculate the correlation between parameters and identify strongly correlated parameter groups (for example, "working mode" and "channel selection" need to be configured collaboratively); in the constraint reasoning layer, invalid configurations that do not meet the conditions are filtered out (for example, prohibiting STA mode without an AP hotspot configured) based on hardware restrictions (such as the power supply voltage range of 3.3V±0.15V) and communication protocol specifications (such as Wi-Fi security protocol requirements); in the performance prediction layer, a graph neural network is used to predict the performance indicators corresponding to different parameter combinations (for example, predicting the throughput under "AP mode + channel 6").

[0024] Next, candidate parameter combinations are generated based on the inference results. Monte Carlo Tree Search (MCTS) is used to optimize multiple objective functions (such as maximizing throughput, reliability, and minimizing power consumption). Weight coefficients are adjusted (initially set to a balanced mode, such as [0.4, 0.3, 0.3]) to balance these objectives. Finally, the feasibility of the candidate solutions is verified using historical data. Configurations that result in excessively high bit error rates (e.g., >5%) or excessive power consumption (e.g., >500mW) are eliminated, resulting in an initial parameter configuration, such as "STA mode, 9600bps baud rate, and 15dBm transmit power."

[0025] As described in step S3 above, real-time demand parameters are obtained. These parameters are derived from manual user settings (such as high-speed transmission mode and low power consumption priority) or task instructions issued by the upper-layer system. Demand intent is analyzed through natural language processing or preset tags, and the requirements are converted into a multi-objective weight vector. For example, if the requirement is "high-speed transmission mode," the weight vector can be set to [0.6, 0.2, 0.2] to prioritize the throughput target.

[0026] Next, a sensitivity analysis is performed on the parameters in the initial configuration. The gradient of each parameter with respect to the performance indicator is calculated, and a parameter-indicator sensitivity matrix is constructed to clarify the impact of each parameter change on different performance indicators. For example, the baud rate has a sensitivity of 0.8 to throughput, indicating that increasing the baud rate significantly increases throughput; the transmit power has a sensitivity of -0.5 to power consumption, meaning that reducing transmit power effectively reduces power consumption. Combining the weight vectors, an adjustment priority matrix is generated to prioritize parameter adjustments, such as prioritizing the baud rate parameter, which has a greater impact on key objectives.

[0027] Next, a small-step search is performed within the parameter constraint space (e.g., adjusting the baud rate by ±10%). Local linear approximation is used to predict the performance change after the parameter adjustment, generating a candidate set of corrected parameters. Finally, a reinforcement learning model (based on Q-value evaluation of historical configurations), a causal inference model (analyzing the causal effects of parameter adjustments), and an expert rule engine (e.g., security protocols must comply with the WPA2-PSK standard) are integrated to comprehensively evaluate the candidate parameter sets and generate the first corrected value. For example, increasing the baud rate by 20% can increase throughput by 15%, but also increase power consumption by 8%. This result is the concrete embodiment of the first corrected value and is used to modify the initial configuration plan.

[0028] As described in step S4 above, the configuration scheme is further optimized to improve environmental adaptability based on the real-time environmental conditions of the wireless module. First, real-time environmental parameters are collected, including temperature, humidity, electromagnetic interference intensity, and metal obstruction rate around the antenna. A sliding window Fourier transform is used to analyze the electromagnetic signal and extract the interference frequency band characteristics. A spatial interpolation algorithm is then used to generate a metal obstruction heat map of the antenna layout, quantifying the environmental impact on signal transmission.

[0029] Next, a risk assessment is conducted based on the collected environmental parameters. An environmental risk assessment model is constructed, and response strategies are set for different environmental conditions. For example, when the temperature exceeds 80°C, it is identified as a high-temperature risk, and the transmit power limit is forced to be reduced (for example, from 17dBm to 15dBm) to prevent overheating. When strong electromagnetic interference is detected in the 5GHz band, the channel is automatically switched to an idle 2.4GHz channel (for example, from channel 11 to channel 1). This generates a parameter constraint adjustment matrix, limiting the value range of sensitive parameters and ensuring that the configuration plan adapts to environmental requirements.

[0030] The initial configuration is then compared with the constraint adjustment matrix to detect conflicting items. For example, if the transmit power in the initial plan is 17dBm, but in a high-temperature environment it exceeds the upper limit set by the constraint matrix, adjustments are required. An adaptive compensation algorithm is designed to adjust parameters based on environmental changes, such as reducing transmit power by 2dBm for every 10°C increase or switching channels in real time based on interference bands.

[0031] Finally, the stability of the compensated solution is verified using an environmental simulator (such as a high-temperature box to simulate a high-temperature environment and an electromagnetic interference generator to simulate signal interference) to ensure that the module can still operate reliably after the configuration adjustment. This generates a second correction value, such as reducing the transmit power by 2dBm and switching the channel to 1, providing an optimization basis for the environmental dimension of the final solution.

[0032] As described in step S5 above, the goal is to integrate optimization information from both the demand and environment dimensions to generate a globally optimal final configuration solution. First, a weighted summation or priority arbitration strategy is used to combine the first correction value (demand-driven) and the second correction value (environment-driven). For example, if the user demand is "high-speed transmission," temperature restrictions can be appropriately relaxed, if environmental conditions permit, prioritizing throughput requirements. However, when the ambient temperature exceeds 90°C, the module is forced into low-power mode to ensure safe operation. In this case, the environment takes precedence over demand.

[0033] Next, the feasibility of the integrated parameter combination is verified. This checks whether the configuration meets hardware constraints (e.g., module supply current does not exceed 500mA) and communication protocol specifications (e.g., the Bluetooth network configuration command format is correct). It also verifies whether configuration adjustments will cause system anomalies (e.g., a persistently high NET indicator indicates a network connection failure). If any issues exist, the system returns to adjust the corrected values or re-evaluate the parameter combination.

[0034] Finally, a final configuration plan is generated, including specific parameter combinations (such as "STA mode + baud rate 115200bps + transmit power 15dBm + channel 1"), performance predictions (e.g., expected throughput 60Mbps, power consumption 220mW), and risk warnings (e.g., recommended cooling measures in high-temperature environments). This plan comprehensively considers module operating status, user needs, and environmental conditions, achieving multi-dimensional dynamic optimization to ensure stable and efficient operation of the wireless module in complex scenarios.

[0035] In this embodiment, the operating data of the multi-mode wireless module includes serial port communication data and power consumption data.

[0036] In one embodiment, real-time knowledge extraction is performed to construct a dynamic knowledge graph, including: Using named entity recognition technology to extract key entities from the operating data; the key entities include configuration parameters, real-time status, and performance indicators; Identify the association relationships between the key entities through a relationship extraction algorithm; Construct a three-layer knowledge graph including parameter layer, status layer, and indicator layer; store configuration parameters and their value ranges in the parameter layer; store real-time status and its parameters in the status layer; and store performance indicators and their parameters in the indicator layer; Based on the association relationship, the relationship between key entities in the three-layer knowledge graph is annotated to obtain the dynamic knowledge graph.

[0037] In one embodiment, the operational data of the multi-mode wireless module is first processed. This operational data includes serial port communication records, wireless signal status, system operating parameters, and other information in various formats and types. To extract useful information from this complex data, named entity recognition (named entity recognition) is used. This technology can accurately locate specific names in text. Key entities are divided into three categories: configuration parameters, real-time status, and performance indicators. Configuration parameters include manually configurable or modifiable parameters such as operating mode (e.g., AP mode, STA mode), transmit power, and serial port baud rate. Real-time status represents the module's current operational status, such as current temperature, wireless signal strength (RSSI), and the number of connected devices. Performance indicators measure module performance, such as data throughput, bit error rate during transmission, and power consumption during operation. Using named entity recognition, the system can quickly and accurately identify these key entities from the operational data, laying the foundation for subsequent knowledge graph construction.

[0038] After identifying key entities, further clarification is needed regarding the inherent connections between them. This is where the relationship extraction algorithm comes in. Several types of relationships are predefined, including causal relationships, where changes in one entity trigger changes in another. For example, an increase in module operating temperature may lead to a decrease in transmit power. Configuration dependencies refer to the constraints between certain configuration parameters. For example, when the operating mode is set to AP mode, the maximum number of connected devices is limited. Temporal relationships describe the temporal order of entity changes. For example, changing the serial port baud rate first leads to a change in the data transmission bit error rate. Finally, numerical mapping relationships indicate a numerical correspondence between two entities. For example, a specific transmit power corresponds to a certain range of wireless signal coverage distance. The relationship extraction algorithm analyzes the contextual information of key entities in the data, as well as their frequency and regularity of occurrence, to determine the specific type of relationship between entities. Furthermore, the reliability of some relationships is assessed by counting the number of times they co-occur in the data to ensure the authenticity and validity of the identified associations.

[0039] Based on the key entities extracted and the relationships identified previously, a knowledge graph is constructed. This knowledge graph adopts a hierarchical structure, consisting of a parameter layer, a status layer, and an indicator layer. The parameter layer primarily stores information such as configuration parameters and their value ranges. Each configuration parameter has a specific name, such as "transmit power," and specifies the range of values it can be set. For example, transmit power is typically adjustable within a certain decibel milliwatt (dBm) range. The default value of the parameter is also recorded for convenient reference during initial setup or restoration. The status layer stores real-time status and related parameters. Each real-time status node includes the status name, such as "current temperature," as well as the specific value and collection time, such as "current temperature = 75°C, collection time: May 20, 2025, 14:30:00." This information provides a clear understanding of the module's operating status at a specific moment. The indicator layer stores performance indicators and their parameters. In addition to the indicator name and calculation method, thresholds are also set. For example, the normal threshold for the bit error rate is set to less than 1%, allowing for subsequent assessment of module performance. These three layers are not independent of each other, but are closely connected through the association relationship between entities. For example, changes in the configuration parameters of the parameter layer will affect the real-time status of the status layer, and then affect the performance indicators of the indicator layer.

[0040] After completing the hierarchical construction of the knowledge graph, the nodes in the knowledge graph are annotated based on the relationships between the key entities identified previously. When annotating, directed edges are used to indicate the direction of the relationship. For example, a directed edge from the "Transmit Power" node to the "Radio Signal Strength (RSSI)" node indicates that changes in transmit power will affect RSSI, and the edge indicates that the relationship type is causal. Each edge also includes attribute information such as weight and confidence. The weight reflects the degree of influence of the relationship, while the confidence reflects the reliability of the relationship. For example, a causal relationship with a weight of 0.8 and a confidence of 95% indicates that transmit power has a significant impact on RSSI and the relationship is highly reliable. In addition, the knowledge graph has the ability to be dynamically updated. When new operating data is monitored and new associations are identified, this information will be added to the graph in a timely manner. For relationships that are no longer valid over time, they will be deleted or marked as invalid according to the set rules, thereby ensuring that the knowledge graph can always accurately reflect the latest status of key entities and their relationships during the operation of the multi-mode wireless module, becoming a dynamic and fresh knowledge network, providing strong support for the reasoning and optimization of subsequent module parameter configurations.

[0041] In this embodiment, graph neural network reasoning is performed on the dynamic knowledge graph to generate an initial parameter configuration scheme, including: Performing graph embedding processing on the dynamic knowledge graph to obtain a time-series enhanced node vector representation; Performing layered graph neural network inference processing on the node vector representation to obtain a parameter association matrix, constraint filtering results, and performance prediction vectors; Performing a multi-objective optimization search process on the parameter association matrix, the constraint filtering result, and the performance prediction vector to obtain an optimal parameter solution set; The optimal parameter solution set is subjected to historical data verification and anomaly detection processing to obtain an initial parameter configuration solution.

[0042] In this embodiment, the dynamic knowledge graph graphically stores the complex relationships between various parameters, states, and indicators during the operation of a multi-mode wireless module. However, this structured data format is difficult to directly use for algorithmic calculations. Therefore, graph embedding technology is used to convert each node in the knowledge graph, namely entities such as configuration parameters, real-time status, and performance indicators, into a low-dimensional vector that can be processed by computers. During this conversion process, a time sequence enhancement mechanism can be introduced to better capture the temporal sequence and causal logic of parameter changes. For example, information such as the switching time of the module operating mode and the change time of performance indicators after transmit power adjustment are incorporated into the node vector. In this way, the knowledge originally present in the form of nodes and edges in the graph is transformed into a numerical vector with time dimension features. This not only preserves the associations between entities but also highlights the temporal characteristics of data changes, providing a richer information foundation for subsequent reasoning and calculation.

[0043] After obtaining the time-enhanced node vector representation, a layered graph neural network is used for in-depth analysis. In the first parameter association layer, the graph neural network calculates the similarity and correlation between node vectors to identify close relationships between different configuration parameters. For example, operating mode and channel selection often require coordinated settings. These relationships are ultimately presented in the form of a parameter association matrix, clearly demonstrating which parameters are strongly correlated and which are relatively independent. Next, the constraint reasoning layer screens all possible parameter combinations in the parameter association matrix based on the wireless module's hardware constraints, such as the supply voltage range and transmit power limit, as well as communication protocol specifications such as Wi-Fi security standards. Invalid configurations that do not meet the requirements are filtered out, such as prohibiting STA mode when no AP hotspot is configured, thus obtaining the constraint filtering results. Finally, in the performance prediction layer, the graph neural network uses the information processed by the previous two layers and combines historical data on the correspondence between parameter configurations and performance indicators to predict the module's potential performance, such as throughput, power consumption, and bit error rate, for different parameter combinations. These predictions are summarized into a performance prediction vector, providing a quantitative basis for subsequent parameter optimization.

[0044] Based on the parameter correlation matrix, constraint filtering results, and performance prediction vector obtained in the previous step, a multi-objective optimization search begins. Wireless module parameter configuration often requires balancing multiple objectives, such as maximizing data throughput to meet the need for fast data exchange, minimizing power consumption to extend device battery life, and ensuring connection reliability to reduce bit error rates. Taking these objectives into consideration, algorithms such as Monte Carlo tree search are used to continuously explore and evaluate different parameter configuration solutions within the space of valid parameter combinations that meet hardware and protocol constraints. During the search, each solution's performance on each objective is evaluated based on the performance prediction vector, and a pre-defined trade-off strategy is used to comprehensively evaluate the pros and cons of each solution. For example, for a solution that significantly improves throughput but consumes too much power, and for a solution that consumes less power but has average throughput, the optimal parameter combination that strikes a balance between these multiple objectives is found based on pre-defined weights or dynamically adjusted priorities. This ultimately results in a set of optimal parameter solutions, each of which represents a preferred configuration option under the current conditions.

[0045] After obtaining the optimal parameter solution, historical data is used to verify and detect anomalies to ensure that these parameter combinations are feasible, stable, and reliable in actual operation. First, each parameter combination in the optimal parameter solution is compared with a large amount of actual data recorded during past module operation to examine whether these configurations have historically caused performance anomalies or device failures. For example, a combination of high transmit power and a specific operating mode is examined to determine whether it has historically caused module overheating and shutdown. Anomaly detection algorithms are also used to predict potential anomalies caused by these parameter combinations and analyze whether these configurations violate implicit constraints that are not explicitly defined but exist in practice. For example, certain parameter combinations may cause a sharp increase in wireless signal interference. Through historical data verification and anomaly detection, problematic or high-risk parameter combinations are eliminated from the solution. The final selected parameter combinations constitute the initial parameter configuration solution. This solution comprehensively considers relational reasoning based on knowledge graphs, multi-objective optimization, and practical feasibility, laying a solid foundation for subsequent optimization based on real-time needs and the environment.

[0046] In one embodiment, inputting the real-time demand parameter into a first correction model to obtain a first correction value for the initial parameter configuration solution includes: Performing normalization preprocessing on the real-time demand parameters to obtain a normalized demand vector; Performing demand intent analysis on the normalized demand vector to obtain a multi-objective weight distribution vector; Performing parameter sensitivity analysis on the multi-objective weight distribution vector and the initial parameter configuration scheme to obtain a parameter adjustment priority matrix; performing an incremental parameter search on the parameter adjustment priority matrix to obtain a candidate correction parameter set; The candidate correction parameter set is fused to obtain a first correction value.

[0047] In this embodiment, after acquiring real-time demand parameters, these parameters come from different sources and have different dimensions and value ranges. For example, some parameters are expressed as percentages, while others are specific values. To facilitate subsequent processing and comparison, they need to be normalized. The normalization process is similar to converting items of varying specifications into standard units. This process converts various real-time demand parameters into a unified numerical range, typically between 0 and 1. After this processing, all demand parameters are integrated into a normalized demand vector. Each element in this vector represents a standardized demand parameter, eliminating differences in the dimensions and scales of the original parameters. This allows subsequent analysis and calculations to treat each demand parameter more fairly and accurately.

[0048] After obtaining the normalized demand vector, it's necessary to deeply understand the true intent behind these requirements. Specifically, it's necessary to clarify the user's or upper-layer system's emphasis on the performance of the multi-mode wireless module. For example, when "high-speed transmission mode" appears in the demand parameters, it's necessary to interpret this as indicating that the user prioritizes data throughput; while "low power consumption priority" indicates that the user wants the module to consume as little energy as possible during operation. Based on preset rules or trained models, these demand intents are converted into weights for different performance objectives. For example, if it's determined that the user prioritizes throughput, then the multi-objective weight distribution vector will have a relatively high weight for throughput, while the weights for other objectives, such as power consumption and reliability, will be reduced accordingly. In this way, abstract demand intent is converted into a concrete, computationally applicable multi-objective weight distribution vector, providing clear guidance for subsequent parameter adjustments.

[0049] After obtaining the multi-objective weight allocation vectors, we conduct a sensitivity analysis of each parameter, combined with the initial parameter configuration plan. The purpose of parameter sensitivity analysis is to determine the extent to which each parameter affects different performance objectives. For example, for the throughput performance objective, changes in the baud rate parameter may have a significant impact, while for the power consumption objective, adjustments to the transmit power parameter may be more critical. By analyzing the impact of small changes in each parameter in different directions on each performance objective, a parameter adjustment priority matrix is constructed. In this matrix, each element represents the importance of a parameter to a specific performance objective, with parameters with higher importance positioned higher in the matrix. This clearly identifies which parameters should be adjusted first and the effectiveness of these adjustments in achieving different performance objectives, providing a scientific basis for subsequent parameter optimization.

[0050] Based on the parameter adjustment priority matrix, an incremental parameter search begins to find a parameter configuration that better meets real-time requirements. This incremental search means that the system doesn't make large, all-at-once adjustments to parameters. Instead, it explores the parameter space in small steps. Starting from the initial parameter configuration, the system makes small increases or decreases to higher-priority parameters according to the priority order specified in the parameter adjustment priority matrix. After each adjustment, the impact on performance objectives is evaluated and recorded. By continuously performing these small-step parameter adjustments and evaluating their effects, the system gradually searches for a more optimal parameter configuration in the parameter space. Ultimately, all evaluated and performing parameter combinations are collected to form a candidate correction parameter set. Each parameter combination in this set represents a configuration option that may better meet real-time requirements than the initial solution.

[0051] After obtaining the candidate correction parameter set, the final first correction value must be determined from these candidate solutions. Each solution in the candidate parameter set may have advantages and disadvantages regarding different performance objectives. For example, some solutions offer high throughput but high power consumption, while others offer low power consumption but slightly lower reliability. These factors need to be comprehensively considered and integrated. During the integration process, the weight distribution vector for multiple objectives is referenced, with higher-weighted performance objectives given greater weight. Furthermore, practical factors such as the feasibility and stability of parameter adjustments, as well as compatibility with hardware and protocols, are considered. Through comprehensive evaluation and trade-offs, a parameter combination that best balances these requirements is selected from the candidate correction parameter set. The difference between this parameter combination and the initial parameter configuration is the final first correction value. This first correction value is used to refine the initial parameter configuration, ensuring that the module configuration better meets the user's real-time needs.

[0052] In one embodiment, inputting the real-time environmental parameters into a second correction model to obtain a second correction value for the initial parameter configuration scheme includes: Performing spatiotemporal feature extraction processing on the real-time environmental parameters to obtain an environmental state feature vector; Performing an environmental risk assessment on the environmental state characteristic vector to obtain a parameter constraint adjustment matrix; Performing conflict detection on the initial parameter configuration scheme and the parameter constraint adjustment matrix to obtain an environment-sensitive parameter list; Performing adaptive compensation calculation on the environmental sensitive parameter list to obtain an environmental correction parameter set; The environmental correction parameter set is optimized to obtain the second correction value.

[0053] In this embodiment, after obtaining the real-time environmental parameters of the environment in which the multi-mode wireless module is located, since these parameters contain rich temporal and spatial information, it is necessary to further explore and refine the key features. For example, the changing trend of the ambient temperature over a period of time, the distribution of electromagnetic interference intensity in different frequency bands and positions, and the difference in metal shielding rate around the antenna with spatial position, etc. The system extracts feature information that can reflect the dynamic changes and spatial characteristics of the environment from these real-time environmental parameters by adopting methods such as sliding window analysis and spatial interpolation. These feature information are integrated and encoded to eventually form an environmental state feature vector. This vector comprehensively and concisely summarizes the key status of the current environment, providing an intuitive and effective data basis for subsequent analysis and decision-making.

[0054] With the environmental state feature vector in hand, a pre-set environmental risk assessment model is used to conduct an in-depth analysis of the current environmental conditions and determine the potential impact of environmental factors on wireless module operation. For example, high ambient temperatures can cause module overheating, leading to performance degradation or even damage; excessive electromagnetic interference can severely impact wireless signal transmission quality. Based on the different environmental state characteristics, the corresponding risk level is assessed and the module configuration parameters that require adjustment to mitigate the risk are determined. These assessment results are then organized into a parameter constraint adjustment matrix. This matrix clearly defines the value range, adjustment direction, and adjustment amplitude for each configuration parameter under specific environmental conditions. For example, when the temperature exceeds a certain threshold, the matrix limits the maximum transmit power to prevent module failure due to overheating, thus providing clear rules and a basis for subsequent parameter adjustments.

[0055] After obtaining the parameter constraint adjustment matrix, the system compares and analyzes it with the initial parameter configuration plan to identify parameters in the initial plan that do not match the current environmental conditions and may cause operational problems. Each parameter in the initial parameter configuration plan is checked one by one to determine whether it meets the constraints specified in the parameter constraint adjustment matrix. If a parameter exceeds the value range set in the matrix, or its configuration method poses a risk in the current environment, then this parameter is identified as an environmentally sensitive parameter. For example, in an environment with strong electromagnetic interference, the specific communication frequency band used in the initial plan may be severely interfered with. In this case, the frequency band parameter is an environmentally sensitive parameter. All these environmentally sensitive parameters are screened to form an environmentally sensitive parameter list, so that these parameters can be adjusted and optimized in a targeted manner later.

[0056] Adaptive compensation calculations are performed for the parameters in the environmentally sensitive parameter list based on the current environmental conditions and the requirements of the parameter constraint adjustment matrix. Adaptive compensation calculations involve the system using appropriate algorithms and strategies to adjust parameters based on different environmental conditions and parameter characteristics. For example, for transmit power, which is listed as an environmentally sensitive parameter due to excessive temperature, its value is automatically reduced according to specific rules to reduce module heat generation. For communication frequency band parameters affected by electromagnetic interference, a relatively idle frequency band with less interference is automatically selected as a replacement based on the distribution of interfering frequency bands. By performing such adaptive adjustments on each parameter in the environmentally sensitive parameter list, a new set of parameter values is obtained, which constitute the environmental correction parameter set. The parameter configurations in this set are designed to enable the module to better adapt to current environmental conditions and reduce operational risks caused by environmental factors.

[0057] After obtaining the environmental correction parameter set, it is further optimized to ensure that the final parameter configuration not only adapts to the environment but also achieves optimal performance and stability. During the optimization process, multiple factors are considered, including the impact of parameter adjustments on various module performance indicators, the compatibility of the adjusted parameters, and the feasibility and complexity of the adjustment operation. For example, if adjusting a parameter reduces environmental risks but significantly impacts the module's data transmission rate, the adjustment strategy will be reassessed to find a more optimal balance. By continuously evaluating, adjusting, and validating the parameters in the environmental correction parameter set, an optimal set of parameter adjustments is ultimately determined. The difference between these adjusted values and the initial parameter configuration is the second correction value. This second correction value is used to modify the initial parameter configuration, ensuring stable and efficient operation of the wireless module in the current environment.

[0058] In one embodiment, after obtaining the final parameter configuration solution, the following steps are included: Extract parameters from the parameter configuration scheme, and add characters in each parameter to a matrix one by one to obtain a parameter character matrix; Obtain identification information of the multi-mode wireless module, extract character attributes in the identification information, and determine corresponding adjustment rules based on the character attributes; Performing character adjustment on the parameter character matrix based on the adjustment rule to obtain an adjusted character matrix; Separating the adjusted character matrix into a first matrix with three rows and two columns and a second matrix with two rows and two columns, and multiplying the first matrix by the second matrix to obtain a target matrix; The characters in the target matrix are combined into a communication key, which is used as the communication key between the multi-mode wireless module and the external device.

[0059] In this embodiment, after determining the final parameter configuration scheme, a parameter extraction operation is first performed on the parameter configuration scheme in order to further process and utilize the parameter information. The parameter configuration scheme includes multiple parameters such as operating mode, transmit power, and serial port baud rate, each of which is in the form of characters or numbers. The characters in these parameters are separated one by one and added to a matrix in a specific order. This matrix stores the character information of the parameter configuration scheme in a structured manner, providing a unified data format for subsequent processing.

[0060] After constructing the parameter character matrix, the next step is to obtain the multimode wireless module's identification information. This identification information typically includes the module's model, production number, serial number, and other information. Each character has specific attributes, such as its type (number, letter, or special symbol), its position within the identification information, and its frequency of occurrence. The characters in this identification information are analyzed in depth to extract these character attributes. Then, based on a pre-defined rule library, the corresponding adjustment rules are determined based on the extracted character attributes.

[0061] After determining the adjustment rules, the parameter character matrix is manipulated according to these rules. Each character in the parameter character matrix is transformed according to the corresponding adjustment rule. For example, if the adjustment rule requires converting letters to uppercase, all lowercase letters in the matrix are converted; if the rule specifies a specific replacement operation for numbers, matching numbers are replaced with the specified value. By adjusting each character in the parameter character matrix one by one, a new matrix is ultimately obtained: the adjusted character matrix. The characters in this matrix are the result of rule processing. Compared to the original parameter character matrix, both the form and content of the characters have changed to meet specific needs and security requirements.

[0062] After obtaining the adjusted character matrix, a matrix segmentation operation is performed to further generate the communication key. According to pre-defined rules, the adjusted character matrix is divided into a first matrix with three rows and two columns and a second matrix with two rows and two columns. This segmentation method is determined based on the algorithm and logic for generating the communication key, and is intended to rationally group the character information. After the segmentation is completed, a specific multiplication calculation is performed on the two matrices. In this embodiment, the matrix multiplication calculation can be performed directly, or the characters in corresponding positions of the two matrices can be combined or transformed according to a preset algorithm. Through a series of calculation steps, a new matrix, namely the target matrix, is ultimately obtained. This target matrix integrates the information of the two sub-matrices and generates a new character combination through calculation.

[0063] After obtaining the target matrix through the previous steps, the characters in the target matrix are combined in sequence. This combination process also follows specific rules. Characters can be extracted from left to right, top to bottom, or arranged in the order specified by a certain encryption algorithm. These characters are combined to form a complete string, which is the communication key. This communication key serves as an important basis for authentication and data encryption when the multi-mode wireless module communicates with external devices. In subsequent communication processes, only when the external device uses the same communication key for authentication and data processing can it successfully establish a secure and reliable connection with the module, thereby ensuring correct data transmission and interaction, and ensuring the security and accuracy of communication.

[0064] In one embodiment, after obtaining the final parameter configuration solution, the following steps are included: Extract parameters from the parameter configuration scheme, and add characters in each parameter to a matrix one by one to obtain a parameter character matrix; Obtain identification information of the multi-mode wireless module, extract numeric characters in the identification information, and generate a corresponding curve based on the numeric characters; superimposing the curve into the parameter character matrix according to a preset rule, and dividing the parameter character matrix based on the curve to obtain a plurality of sub-matrices; Superimposing the curve in each sub-matrix according to a preset rule, and obtaining a matrix element in each sub-matrix that satisfies a preset distance relationship with the curve as a target element; The target elements are combined in sequence to obtain an element combination, which serves as a communication key between the multi-mode wireless module and an external device.

[0065] In this embodiment, after determining the final parameter configuration scheme, the parameters in the scheme are first broken down and analyzed. A parameter configuration scheme typically includes multiple specific parameters such as operating mode, transmit power, and communication frequency, each composed of different characters. These characters are then separated one by one and entered into a pre-defined matrix structure in a specific order. This consolidates the previously dispersed parameter information into a structured parameter character matrix, providing a unified data format and operational foundation for subsequent processing.

[0066] After completing the construction of the parameter character matrix, the system obtains the identification information of the multi-mode wireless module, which usually includes the module model, serial number, production batch, etc. All numeric characters are filtered out from these identification information, such as extracting 1, 2, 3, 4, and 5 from the serial number "ABC12345". Next, the corresponding curve is generated based on these numeric characters. Specifically, each numeric character is mapped to a specific coordinate point, and then these coordinate points are connected in sequence according to the order in which the numbers appear in the identification information to form a continuous curve. The shape and trend of this curve are determined by the specific values and arrangement order of the numeric characters. Therefore, the curve generated by each module is unique and contains the identity feature information of the module.

[0067] After obtaining the curve, it is superimposed on the parameter character matrix according to preset rules. This superposition process is like drawing a path on an image, and the curve will cover some elements in the parameter character matrix. The preset rules include the starting position, direction, and extension method of the curve in the matrix. After the superposition is completed, the parameter character matrix is separated according to the position and direction of the curve in the matrix. For example, the curve divides the matrix into multiple areas such as top and bottom, left and right, or irregular areas, and each area forms a submatrix. In this way, the originally unified parameter character matrix is divided into multiple submatrices with specific associations, providing more detailed operation units for subsequent target element extraction.

[0068] After obtaining multiple sub-matrices, the curve is again superimposed on each sub-matrix according to the preset rules. Unlike before, this superposition is performed separately for each sub-matrix, and the curve will occupy a specific position in each sub-matrix. Next, in each sub-matrix, find the matrix elements that meet the preset distance relationship with the curve. The preset distance relationship can be elements directly adjacent to the curve, elements within a certain range from the curve, or elements that meet a certain specific geometric relationship. For example, the element closest to the curve, or the element within a specific range on both sides of the curve is selected as the target element. In this way, qualified elements are screened out from each sub-matrix, and these elements will serve as key data for generating communication keys.

[0069] After obtaining the target elements from each sub-matrix, these target elements are combined in sequence. The combination order is usually related to the division order of the sub-matrices and the direction of the curve in each sub-matrix. For example, the target elements in each sub-matrix can be connected in sequence from top to bottom and from left to right of the sub-matrix. Through this combination method, the target elements scattered in each sub-matrix are integrated into a complete element combination. This element combination contains the dual characteristics of the parameter character matrix and the module identification information. It has high uniqueness and security. Therefore, it can be used as the key for authentication and data encryption when the multi-mode wireless module communicates with external devices. In the subsequent communication process, only the communication key generated by the same method can achieve secure connection and data transmission between devices, thereby ensuring the reliability and security of communication.

[0070] Reference Figure 2 In another embodiment of the present invention, a system for dynamically configuring parameters of a multi-mode wireless module is provided, comprising: A construction unit is used to obtain the operating data of the multi-mode wireless module, perform real-time knowledge extraction, and build a dynamic knowledge graph; An inference unit, configured to perform graph neural network inference on the dynamic knowledge graph to generate an initial parameter configuration scheme; A first correction unit is configured to obtain real-time demand parameters of the multi-mode wireless module, input the real-time demand parameters into a first correction model, and obtain a first correction value for the initial parameter configuration solution; a second correction unit, configured to obtain real-time environmental parameters of the environment in which the multi-mode wireless module is located, and input the real-time environmental parameters into a second correction model to obtain a second correction value for the initial parameter configuration scheme; The configuration unit is configured to correct the initial parameter configuration scheme based on the first correction value and the second correction value to obtain a final parameter configuration scheme.

[0071] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0072] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0073] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0074] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0075] In summary, the method and system for dynamic configuration of parameters of a multi-mode wireless module provided in an embodiment of the present invention include: obtaining the operating data of the multi-mode wireless module, performing real-time knowledge extraction, and constructing a dynamic knowledge graph; performing graph neural network reasoning on the dynamic knowledge graph to generate an initial parameter configuration scheme; obtaining the real-time demand parameters of the multi-mode wireless module, inputting the real-time demand parameters into a first correction model, and obtaining a first correction value for the initial parameter configuration scheme; obtaining the real-time environmental parameters of the environment in which the multi-mode wireless module is located, inputting the real-time environmental parameters into a second correction model, and obtaining a second correction value for the initial parameter configuration scheme; correcting the initial parameter configuration scheme based on the first correction value and the second correction value to obtain a final parameter configuration scheme. In the present invention, a dynamic knowledge graph reflecting parameter association is constructed through real-time knowledge extraction, an initial scheme is generated using graph neural network reasoning, and the initial scheme is optimized through a dual correction model in combination with real-time demand and environmental parameters, breaking through the data association analysis limitations of traditional methods and improving the environmental adaptability, demand response speed, and multi-objective optimization capabilities of the configuration scheme. It overcomes the shortcomings of current methods that are difficult to capture the dynamic correlation between parameters in real time, and cannot quickly respond to changes in real-time environmental parameters and user needs to optimize parameter configuration solutions.

[0076] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0077] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0078] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for dynamically configuring parameters of a multi-mode wireless module, characterized in that: The following steps are involved: Obtain operating data from multi-mode wireless modules, perform real-time knowledge extraction, and build a dynamic knowledge graph; Performing graph neural network reasoning on the dynamic knowledge graph to generate an initial parameter configuration scheme; Acquire real-time demand parameters of the multi-mode wireless module, input the real-time demand parameters into a first correction model, and obtain a first correction value for the initial parameter configuration solution; Acquire real-time environmental parameters of the environment in which the multi-mode wireless module is located, and input the real-time environmental parameters into a second correction model to obtain a second correction value for the initial parameter configuration scheme; The initial parameter configuration scheme is corrected based on the first correction value and the second correction value to obtain a final parameter configuration scheme.

2. The method for dynamic parameter configuration of a multi-mode wireless module according to claim 1, wherein: The operating data of the multi-mode wireless module includes serial port communication data and power consumption data.

3. The method for dynamic parameter configuration of a multi-mode wireless module according to claim 1, wherein: Perform real-time knowledge extraction and build a dynamic knowledge graph, including: Using named entity recognition technology to extract key entities from the operating data; the key entities include configuration parameters, real-time status, and performance indicators; Identify the association relationships between the key entities through a relationship extraction algorithm; Construct a three-layer knowledge graph including parameter layer, status layer, and indicator layer; store configuration parameters and their value ranges in the parameter layer; store real-time status and its parameters in the status layer; and store performance indicators and their parameters in the indicator layer; Based on the association relationship, the relationship between key entities in the three-layer knowledge graph is annotated to obtain the dynamic knowledge graph.

4. The method for dynamic parameter configuration of a multi-mode wireless module according to claim 1, wherein: Perform graph neural network reasoning on the dynamic knowledge graph to generate an initial parameter configuration scheme, including: Performing graph embedding processing on the dynamic knowledge graph to obtain a time-series enhanced node vector representation; Performing layered graph neural network inference processing on the node vector representation to obtain a parameter association matrix, constraint filtering results, and performance prediction vectors; Performing a multi-objective optimization search process on the parameter association matrix, the constraint filtering result, and the performance prediction vector to obtain an optimal parameter solution set; The optimal parameter solution set is subjected to historical data verification and anomaly detection processing to obtain an initial parameter configuration solution.

5. The method for dynamic parameter configuration of a multi-mode wireless module according to claim 1, wherein: Inputting the real-time demand parameter into a first correction model to obtain a first correction value for the initial parameter configuration solution includes: Performing normalization preprocessing on the real-time demand parameters to obtain a normalized demand vector; Performing demand intent analysis on the normalized demand vector to obtain a multi-objective weight distribution vector; Performing parameter sensitivity analysis on the multi-objective weight distribution vector and the initial parameter configuration scheme to obtain a parameter adjustment priority matrix; performing an incremental parameter search on the parameter adjustment priority matrix to obtain a candidate correction parameter set; The candidate correction parameter set is fused to obtain a first correction value.

6. The method for dynamic parameter configuration of a multi-mode wireless module according to claim 1, wherein: Inputting the real-time environmental parameters into a second correction model to obtain a second correction value for the initial parameter configuration scheme includes: Performing spatiotemporal feature extraction processing on the real-time environmental parameters to obtain an environmental state feature vector; Performing an environmental risk assessment on the environmental state characteristic vector to obtain a parameter constraint adjustment matrix; Performing conflict detection on the initial parameter configuration scheme and the parameter constraint adjustment matrix to obtain an environment-sensitive parameter list; Performing adaptive compensation calculation on the environmental sensitive parameter list to obtain an environmental correction parameter set; The environmental correction parameter set is optimized to obtain the second correction value.

7. A parameter dynamic configuration system for a multi-mode wireless module, characterized in that: include: A construction unit is used to obtain the operating data of the multi-mode wireless module, perform real-time knowledge extraction, and build a dynamic knowledge graph; An inference unit, configured to perform graph neural network inference on the dynamic knowledge graph to generate an initial parameter configuration scheme; A first correction unit is configured to obtain real-time demand parameters of the multi-mode wireless module, input the real-time demand parameters into a first correction model, and obtain a first correction value for the initial parameter configuration solution; a second correction unit, configured to obtain real-time environmental parameters of the environment in which the multi-mode wireless module is located, and input the real-time environmental parameters into a second correction model to obtain a second correction value for the initial parameter configuration scheme; The configuration unit is configured to correct the initial parameter configuration scheme based on the first correction value and the second correction value to obtain a final parameter configuration scheme.

Images