A method, system, device and medium for verifying parameters of an ECU calibration file

Abstract

A method, system, device and medium for verifying parameters of an ECU calibration file, which relates to the field of parameter verification. In this method, key features are extracted from the parameters to be calibrated in the ECU calibration file, and a structured parameter feature vector is constructed according to the key features; a hybrid matching algorithm is used to screen out candidate parameters from a preset calibration library whose similarity to the structured parameter feature vector is higher than a threshold, a confidence score is assigned to each candidate parameter, and a candidate parameter set is constructed based on the candidate parameters; an optimal calibration path is recommended according to the candidate parameter set, and the parameters to be calibrated are calibrated according to the optimal calibration path to obtain calibrated parameters; a rule engine is used to perform basic rule verification on the calibrated parameters, a machine learning model is used to perform anomaly detection on the calibrated parameters, and it is determined whether the calibrated parameters meet the requirements according to the results of the basic rule verification and the anomaly detection. Implementing the technical solution provided by this application improves the accuracy and efficiency of parameter verification for ECU calibration files.

Description

Technical Field

[0001] This application relates to the technical field of parameter verification, and specifically relates to a method, system, device, and medium for verifying ECU calibration file parameters. Background Art

[0002] ECU (Electronic Control Unit) calibration technology plays a crucial role in modern industrial automation and automotive electronics fields. It optimizes device performance, improves system efficiency, and ensures operation safety by precisely setting control parameters. With the rapid development of electronic control technology, ECU calibration has become the core link for efficient debugging and optimization of complex control systems, greatly promoting the development of fields such as intelligent manufacturing and intelligent transportation.

[0003] In the prior art, to solve the parameter matching and optimization problems in the ECU calibration process, a manual calibration method based on manual experience is usually adopted, relying on engineers' professional knowledge to complete parameter adjustment. However, the above method has the defect of being difficult to comprehensively consider the coupling relationship and dynamic change characteristics between parameters, resulting in insufficient calibration accuracy or low efficiency, and unable to meet the requirements of modern high-precision calibration tasks. Summary of the Invention

[0004] This application provides a method, system, device, and medium for verifying ECU calibration file parameters, improving the accuracy and efficiency of ECU calibration file parameter verification.

[0005] In the first aspect of this application, a method for verifying ECU calibration file parameters is provided, which is applied to a parameter verification platform. The method includes:

[0006] Extract key features from the parameters to be calibrated in the ECU calibration file, and construct a structured parameter feature vector based on the key features. The key features include parameter name, type, value range, physical meaning, maturity index, and task relevance;

[0007] Use a hybrid matching algorithm to screen out candidate parameters with a similarity higher than a threshold from a preset calibration library, assign a confidence score to each candidate parameter, and construct a candidate parameter set based on the candidate parameters;

[0008] Recommend an optimal calibration path according to the candidate parameter set, and calibrate the parameters to be calibrated according to the optimal calibration path to obtain calibrated parameters;

[0009] Use a rule engine to perform basic rule verification on the calibrated parameters, use a machine learning model to perform anomaly detection on the calibrated parameters, and determine whether the calibrated parameters meet the requirements according to the basic rule verification results and anomaly detection results.

[0010] Optionally, the process of screening candidate parameters with a similarity higher than a threshold from a preset calibration library using the hybrid matching algorithm includes:

[0011] Generate a semantic vector based on the text field of the candidate parameter in the preset calibration library, and calculate the cosine similarity between the structured parameter feature vector and the semantic vector to obtain the semantic similarity;

[0012] Construct a global parameter dependency graph based on the control logic dependencies between parameters, and calculate the topological correlation degree between the parameter to be calibrated and the candidate parameter in the global parameter dependency graph through a graph neural network;

[0013] Use bidirectional LSTM to extract the first temporal feature of the parameter to be calibrated and the second temporal feature of the candidate parameter, and calculate the temporal matching degree between the first temporal feature and the second temporal feature through the dynamic time warping algorithm;

[0014] Perform weighted summation on the semantic similarity, the topological correlation degree, and the temporal matching degree to obtain the similarity value of the candidate parameter, and use the candidate parameter with a similarity value higher than the threshold as a candidate parameter.

[0015] Optionally, the process of assigning a confidence score to each candidate parameter and constructing a candidate parameter set based on the candidate parameters includes:

[0016] Perform linear mapping on the similarity value to obtain the basic confidence level, obtain the maturity index of the candidate parameter, and use the logarithmic change value of the maturity index as the correction value;

[0017] Perform weighted summation on the basic confidence level and the correction value to obtain the confidence score, and construct a candidate parameter set with candidate parameters whose confidence scores are greater than the confidence threshold.

[0018] Optionally, the process of recommending an optimal calibration path based on the candidate parameter set includes:

[0019] Based on the dependency relationships of the parameters in the candidate parameter set, construct a calibration dependency graph including node weights and edge weights, where nodes represent the parameters to be calibrated, and the edge weights include the coupling strength between parameters and the calibration order constraint;

[0020] Determine the initial calibration sequence based on the calibration dependency graph, identify whether there is a calibration conflict, and when a calibration conflict is detected, adjust the initial calibration sequence based on the calibration resource occupancy rate;

[0021] Use a genetic algorithm to optimize and iterate the adjusted initial calibration sequence to obtain the optimal calibration path.

[0022] Optionally, the basic rule verification of the calibration parameters using the rule engine includes:

[0023] Analyze the metadata structure of the calibration parameters, perform type matching verification, value range boundary detection, and physical unit conversion consistency verification, and generate a first-level verification flag bit;

[0024] Verify the control logic conflict situation based on the global parameter dependency graph, and generate a second-level verification flag bit;

[0025] Monitor the occupancy status of calibration resources, implement pre-allocation verification of storage space and peak pressure test of communication bandwidth, and generate a third-level verification flag bit;

[0026] Generate a verification flag bit according to the first-level verification flag bit, the second-level verification flag bit, and the third-level verification flag bit.

[0027] Optionally, the abnormal detection of the calibration parameters using the machine learning model, and determining whether the calibration parameters meet the requirements according to the basic rule verification result and the abnormal detection result includes:

[0028] Extract the distribution skewness, time series fluctuation entropy value, and cross-parameter covariance matrix eigenvalue of the calibration parameters, and construct a multi-dimensional verification vector including space-time joint features;

[0029] Input the multi-dimensional verification vector into a CNN-BiLSTM hybrid neural network, where the CNN convolutional layer extracts the spatial correlation features between parameters, and the BiLSTM layer captures the long-term and short-term time series dependency relationships, and outputs an abnormal probability value;

[0030] Encode the verification flag bit into a feature vector, and jointly input it into the gradient boosting decision tree model with the abnormal probability value, and generate a final detection conclusion through a weighted voting mechanism.

[0031] Optionally, the method further includes:

[0032] Obtain the feedback data of the calibration parameters, where the feedback data includes a maturity increment value, a calibration evaluation report, and a task relevance, and dynamically adjust the maturity index, evaluation level, and task association degree index of the corresponding parameters in the preset calibration library based on the feedback data through the Bayesian update algorithm;

[0033] Generate knowledge graph supplementary data based on the calibration conflict resolution record, and update the newly emerged parameter coupling relationship and resource occupancy mode to the global parameter dependency graph and the calibration resource constraint model.

[0034] In the second aspect of the present application, a calibration file parameter verification system for an ECU is provided, which is characterized by including a feature module, a screening module, a calibration module, and a verification module, where:

[0035] A feature module, configured to extract key features from the parameters to be calibrated in the ECU calibration file, and construct a structured parameter feature vector according to the key features, where the key features include parameter name, type, value range, physical meaning, maturity index, and task correlation degree;

[0036] A screening module, configured to use a hybrid matching algorithm to screen out candidate parameters with a similarity higher than a threshold from a preset calibration library, assign a confidence score to each candidate parameter, and construct a candidate parameter set based on the candidate parameters;

[0037] A calibration module, configured to recommend an optimal calibration path according to the candidate parameter set, and calibrate the parameter to be calibrated according to the optimal calibration path to obtain a calibrated parameter;

[0038] A verification module, configured to perform basic rule verification on the calibrated parameter using a rule engine, perform anomaly detection on the calibrated parameter using a machine learning model, and determine whether the calibrated parameter meets the requirements according to the basic rule verification result and the anomaly detection result.

[0039] In a third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. Both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the electronic device executes the method described in any one of the above.

[0040] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions, and when the instructions are executed, the method described in any one of the above is executed.

[0041] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0042] 1. Standardize the parameters in the ECU calibration file, including unifying the naming convention and performing unit conversion, etc., to ensure the consistency and comparability of the parameters, and provide high-quality input for subsequent matching and verification; use a hybrid matching algorithm, combining multiple matching methods such as semantic similarity matching, topological association analysis, and time series pattern matching, to screen out the candidate parameter set with the highest similarity to the parameter to be verified from the knowledge base, and assign a confidence score to each candidate parameter to improve the accuracy and reliability of the matching;

[0043] 2. Based on the candidate parameter set, use Petri net modeling to mine the expert operation sequence. Combine the parameter dependency relationship graph and the calibrated resource occupancy situation, and through genetic algorithm optimization and iteration, recommend the optimal calibration path, reduce blind attempts, improve the calibration efficiency and quality, and quickly reach the ideal calibration state; Adjust and set the ECU parameters according to the optimal calibration path to ensure the rationality and effectiveness of the parameter configuration, improve the performance and control accuracy of the ECU, and reduce the performance problems and failure risks caused by improper parameter settings;

[0044] 3. Use a rule engine to perform basic rule verification, build a multi-dimensional verification rule library covering rules such as parameter value range constraints, logical dependencies, and physical unit consistency; Use a machine learning model to perform anomaly detection on parameters, extract the time series, topology, and calibration process characteristics of parameters, build a multi-dimensional verification vector, and through model training and optimization, accurately identify the abnormal patterns and potential risks in the parameters, further improve the comprehensiveness and accuracy of parameter verification, reduce the ECU failure rate caused by parameter anomalies, and improve product quality and reliability. Brief Description of the Drawings

[0045] Figure 1 is a schematic flowchart of the method for verifying the parameters of the ECU calibration file disclosed in the embodiments of the present application;

[0046] Figure 2 is another schematic flowchart of the method for verifying the parameters of the ECU calibration file disclosed in the embodiments of the present application;

[0047] Figure 3 is a schematic block diagram of the system for verifying the parameters of the ECU calibration file disclosed in the embodiments of the present application;

[0048] Figure 4 is a schematic structural diagram of an electronic device disclosed in the embodiments of the present application.

[0049] Description of the reference numerals: 301, feature module; 302, screening module; 303, calibration module; 304, verification module; 401, processor; 402, communication bus; 403, user interface; 404, network interface; 405, memory. Detailed Embodiments

[0050] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0051] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for illustration" is intended to present related concepts in a specific manner.

[0052] In the description of the embodiments of the present application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0053] This embodiment discloses a method for verifying ECU calibration file parameters. Figure 1 is a schematic flowchart of the method for verifying ECU calibration file parameters disclosed in the embodiments of the present application, as Figure 1 shown, the method includes the following steps:

[0054] S101. Extract key features from the parameters to be calibrated in the ECU calibration file, and construct a structured parameter feature vector according to the key features. The key features include parameter name, type, value range, physical meaning, maturity index, and task relevance;

[0055] S102. Use a hybrid matching algorithm to screen out candidate parameters from a preset calibration library that have a similarity higher than a threshold with the structured parameter feature vector, assign a confidence score to each candidate parameter, and construct a candidate parameter set based on the candidate parameters;

[0056] S103. Recommend an optimal calibration path according to the candidate parameter set, and calibrate the parameters to be calibrated according to the optimal calibration path to obtain calibrated parameters;

[0057] S104. Use a rule engine to perform basic rule verification on the calibrated parameters, use a machine learning model to perform anomaly detection on the calibrated parameters, and determine whether the calibrated parameters meet the requirements according to the basic rule verification result and the anomaly detection result.

[0058] Parameter Name: Identifies the uniqueness of the parameter, such as "engine fuel injection volume" or "brake pedal force feedback coefficient". Type: The data type of the parameter (such as integer, floating point, boolean, etc.), which determines the subsequent processing logic. Value Range: The reasonable value range of the parameter (such as 0 - 100% duty cycle), which is used to constrain the calibration result. Physical Meaning: The physical meaning of the parameter in the actual system (such as "fuel injection volume per unit time"), which ensures the physical rationality of the calibration. Maturity Index: Reflects the historical calibration reliability of the parameter (such as a score from 0 - 1, where 1 represents high reliability). Task Relevance: The degree of association between the parameter and the current calibration task (such as direct control parameters having a high weight, and indirectly affecting parameters having a low weight). Convert the above key features into a numerical or encoded vector form (such as [parameter name hash value, type code, value range upper and lower limits, physical meaning vector, maturity index, task relevance]). The vector structure facilitates subsequent algorithm processing (such as similarity calculation, input to machine learning models). Semantic Similarity: Generate a semantic vector based on text fields (such as parameter name, physical meaning), and calculate the semantic matching degree with the parameters in the calibration library through cosine similarity. Topological Relevance: Utilize the global parameter dependency graph (such as a control logic diagram), and calculate the topological association strength between the parameter to be calibrated and the parameters in the library through a graph neural network. Temporal Matching Degree: Extract the temporal features of the parameter (such as dynamic change patterns), and calculate the temporal similarity using the dynamic time warping algorithm. Weighted sum of the semantic similarity, topological relevance, and temporal matching degree to obtain a comprehensive similarity value. Screen parameters with a similarity higher than a preset threshold as candidate parameters. A confidence level can be assigned to each parameter, and only parameters with a confidence score higher than the threshold are retained to form a candidate set. Use the candidate parameters as nodes and the dependency relationships between parameters (such as coupling strength, calibration order constraints) as edge weights to construct a directed weighted graph. Generate an initial calibration sequence based on the dependency graph (such as topological sorting). Detect calibration conflicts (such as resource competition, logical contradictions), and adjust the sequence based on the calibration resource occupancy rate. Use a genetic algorithm to iteratively optimize the initial sequence with the goal of minimizing the calibration time, resource consumption, or error. Output the optimal calibration path (such as the parameter calibration order and resource allocation plan). Perform actual calibration on the parameters to be calibrated according to the optimal path to generate calibrated parameters. Use a rule engine to perform basic rule verification on the calibrated parameters to determine whether the calibrated parameters meet the basic rules, and use a machine learning model to perform anomaly detection on the calibrated parameters to determine whether there are anomalies in the calibrated parameters, and determine whether the calibrated parameters meet the requirements according to the basic rule verification result and the anomaly detection result.

[0059] Figure 2 is another schematic flow diagram of the method for verifying the parameters of the ECU calibration file disclosed in the embodiments of the present application, as Figure 2As shown, the calibration work begins. Similarity matching is performed on the calibration parameters to find reference historical data or cases. Based on the similarity matching, exact matching is carried out by parameter names. The maturity of the parameters is evaluated, and parameters at the corresponding maturity level are matched. Other parameter tasks related to the current calibration task are determined. The calibration process of experts is matched to utilize expert experience to guide the current calibration. According to the matching results, the specific parameters of this calibration task are determined. The determined calibration parameters are verified to ensure their accuracy and applicability. The calibration parameters are compared with the rule library to verify whether they comply with the established rules. Relevant data is collected during the calibration process to provide a basis for subsequent analysis and evaluation. The calibration results are evaluated to determine whether they meet the expected effects. According to the calibration results, the parameter maturity, evaluation, task relevance and other indicators and files in the calibration library are updated, and the entire calibration process is recorded. The calibration work is completed and the process ends.

[0060] Optionally, the screening of candidate parameters with a similarity higher than the threshold to the structured parameter feature vector from the preset calibration library by using the hybrid matching algorithm includes:

[0061] Generate a semantic vector based on the text field of the parameter to be selected in the preset calibration library, and calculate the cosine similarity between the structured parameter feature vector and the semantic vector to obtain the semantic similarity.

[0062] Construct a global parameter dependence graph based on the control logic dependence between parameters, and calculate the topological correlation degree between the parameter to be calibrated and the parameter to be selected in the global parameter dependence graph through a graph neural network.

[0063] Use bidirectional LSTM to extract the first time series feature of the parameter to be calibrated and the second time series feature of the parameter to be selected, and calculate the time series matching degree between the first time series feature and the second time series feature through the dynamic time warping algorithm.

[0064] Perform weighted summation on the semantic similarity, the topological correlation degree, and the time series matching degree to obtain the similarity value of the parameter to be selected, and use the parameter to be selected with the similarity value higher than the threshold as the candidate parameter.

[0065] Semantic similarity is used to measure the semantic similarity between the parameter to be calibrated and the parameters in the calibration library. Semantic vectors can be generated based on the text fields (such as parameter descriptions, names, etc.) of the candidate parameters in the preset calibration library, and the cosine similarity between the structured parameter feature vector and this semantic vector is calculated to obtain the semantic similarity. Ensure that the selected candidate parameters are highly relevant semantically to the parameter to be calibrated. For example, parameters with similar names or descriptions are more likely to be functionally or application - related. Topological association degree is used to analyze the association and dependency relationships between the parameter to be calibrated and the parameters in the calibration library in the system. A global parameter dependency graph can be constructed based on the control logic dependencies between parameters, and the topological association degree between the parameter to be calibrated and the candidate parameters in this graph is calculated through a graph neural network. Identify the logical relationships between parameters, such as mutual exclusion or co - existence, to ensure that the selected candidate parameters are coordinated in the system and avoid conflicts between parameters. Temporal matching degree is used to evaluate the matching degree between the parameter to be calibrated and the parameters in the calibration library in the time series. Bidirectional LSTM (Long Short - Term Memory Network) can be used to extract the first temporal feature of the parameter to be calibrated and the second temporal feature of the candidate parameters, and the temporal matching degree between these two temporal features is calculated through the dynamic time warping algorithm. Capture the variation patterns and trends of parameters over time to ensure that the selected candidate parameters are similar to the parameter to be calibrated in dynamic behavior, which is particularly important for time - dependent parameters (such as sensor data, control signals, etc.). Considering semantic similarity, topological association degree, and temporal matching degree comprehensively, select the candidate parameter with the highest similarity to the parameter to be calibrated. The above three similarity metrics can be weighted and summed to obtain the comprehensive similarity value of the candidate parameters. The candidate parameters with similarity values higher than the set threshold are used as candidate parameters. Through multi - dimensional similarity evaluation, ensure that the candidate parameters have a high degree of matching with the parameter to be calibrated in terms of semantics, structure, and dynamic behavior, improve the accuracy and reliability of the screening, and provide a high - quality set of candidate parameters for subsequent calibration path recommendation and parameter calibration.

[0066] By combining semantic similarity matching, topological association analysis, and temporal pattern matching, the similarity between the parameter to be calibrated and the parameters in the preset calibration library can be evaluated from multiple perspectives. Compared with single-dimensional matching, this comprehensive matching method can more comprehensively and accurately screen out candidate parameters with high similarity to the target parameter, improving the accuracy and reliability of the matching. Semantic vectors are generated based on the text fields of the candidate parameters in the preset calibration library, and the cosine similarity with the structured parameter feature vectors is calculated to achieve an in-depth understanding and matching of the semantic information of the parameters. This method can effectively handle semantic differences in parameter descriptions, improve the matching accuracy, and especially when facing parameters from different projects or different sources, it can better understand their semantic meanings and find more suitable matching items. By constructing a global parameter dependency graph and using a graph neural network to calculate the topological association degree between the parameter to be calibrated and the candidate parameters, this method fully considers the control logic dependency relationships between parameters. This helps ensure the consistency and coordination of the selected candidate parameters in the system, avoid problems caused by incompatibility or conflicts between parameters, and improve the stability and reliability of the entire ECU system. Using bidirectional LSTM to extract the temporal features of the parameter to be calibrated and the candidate parameters, and calculating the temporal matching degree through the dynamic time warping algorithm, it can effectively capture the variation laws and trends of the parameters in the time series. This is particularly important for ECU parameters with dynamic characteristics because it can ensure that the matched parameters are not only similar in static features but also highly consistent in dynamic behavior, improving the dynamic adaptability of the matching.

[0067] Optionally, assigning a confidence score to each of the candidate parameters and constructing a candidate parameter set based on the candidate parameters includes:

[0068] Performing a linear mapping on the similarity value to obtain a basic confidence level, obtaining the maturity index of the candidate parameter, and using the logarithmic change value of the maturity index as a correction value;

[0069] Performing a weighted sum of the basic confidence level and the correction value to obtain a confidence score, and constructing a candidate parameter set with candidate parameters whose confidence scores are greater than the confidence threshold.

[0070] Convert the similarity value of the candidate parameter into an initial confidence score. The similarity value can be mapped to the interval [0, 1] through a linear function, and the mapped value is used as the basic confidence. Adjust the basic confidence using the maturity index of the candidate parameter to reflect the historical calibration reliability. The maturity index of the candidate parameter can be extracted from a preset calibration library. Perform a logarithmic transformation (such as the natural logarithm or logarithm with base 10) on the maturity index to generate a correction value. The logarithmic transformation can amplify the differences in the maturity index and enhance the discrimination of low-maturity parameters. Integrate the basic confidence and the correction value to generate the final confidence score. The basic confidence and the correction value can be weighted and summed to obtain a comprehensive confidence score. For example, the confidence score = w1 × basic confidence + w2 × correction value, where w1 and w2 are the weights corresponding to the basic confidence and the correction value respectively. This can balance the contributions of the similarity matching result and the historical calibration reliability. Screen out the candidate parameters with a confidence score higher than the threshold to form the final set. A confidence threshold (such as 0.6) can be set, and only the candidate parameters with a confidence score higher than this threshold are retained. Sort the filtered candidate parameters according to the confidence score to construct a candidate parameter set.

[0071] By linearly mapping the similarity value to obtain the basic confidence and introducing the logarithmic change value of the maturity index of the candidate parameter as the correction value, this quantitative evaluation method comprehensively considers the similarity and maturity of the parameters, providing a more comprehensive measure for the reliability of the candidate parameters. The confidence score not only reflects the similarity between the candidate parameter and the target parameter but also takes into account the maturity of the parameter, which helps to more accurately screen out high-quality candidate parameters, reduce misjudgments caused by relying solely on similarity, and improve the accuracy of subsequent calibration and verification. Weighted summation of the basic confidence and the correction value to obtain the final confidence score. This method allows adjusting the weights of the two according to specific application scenarios and requirements, flexibly balancing the relative importance of similarity and maturity in confidence evaluation, and making the confidence score more in line with the requirements of the actual calibration task. By setting a confidence threshold and constructing a candidate parameter set with candidate parameters having a score greater than the threshold, it is possible to quickly and efficiently screen out candidate parameters with high confidence, reduce the amount of data for subsequent processing, and improve the efficiency of the entire calibration process.

[0072] Optionally, the recommending the optimal calibration path according to the candidate parameter set includes:

[0073] Based on the dependency relationships of the parameters in the candidate parameter set, construct a calibration dependency graph including node weights and edge weights, where the nodes represent the parameters to be calibrated, and the edge weights include the coupling strength between parameters and the calibration order constraint;

[0074] Determine the initial calibration sequence according to the calibration dependency graph, identify whether there is a calibration conflict, and when a calibration conflict is detected, adjust the initial calibration sequence based on the calibration resource occupancy rate;

[0075] Use a genetic algorithm to optimize and iterate the adjusted initial calibration sequence to obtain the optimal calibration path.

[0076] Convert the parameters in the candidate parameter set and their dependencies into a graph structure, providing a basis for subsequent path planning. The nodes in the graph represent the parameters to be calibrated (from the candidate parameter set). The edges represent the dependencies between the parameters, and the edge weights include the coupling strength and the calibration order constraint. Coupling strength: Quantify the degree of mutual influence between parameters (such as a value between 0 and 1, where 1 represents strong coupling). Calibration order constraint: Indicate the order of parameter calibration (such as parameter A must be calibrated before parameter B). The coupling strength can be determined through the correlation analysis between parameters (such as control logic dependency, data interaction frequency). The calibration order constraint can be defined through a rule engine or an expert knowledge base. Use a topological sorting algorithm to process the calibration dependency graph and generate an initial calibration sequence. Topological sorting ensures that the calibration order satisfies the dependencies (such as calibrating the prerequisite parameters first). Check whether there are calibration conflicts in the initial sequence. For example, resource competition: Multiple parameters require the same calibration resource at the same time (such as a communication channel, storage space). Logical contradiction: The calibration order violates the dependencies or physical constraints. When a conflict is detected, adjust the sequence based on the calibration resource occupancy rate: Calculate the resource requirements of each parameter (such as bandwidth, memory). Prioritize calibrating the parameters with low resource occupancy rates to reduce resource competition. Optimize the initial calibration sequence through a genetic algorithm to obtain the optimal calibration path. Encode the calibration sequence as a chromosome (such as [parameter 1, parameter 2, parameter 3,...]). Define a fitness function to evaluate the quality of the calibration path. For example, calibration time: The total time required to calibrate all parameters in the path. Resource consumption: The resource (such as CPU, memory) occupancy during the calibration process. Error accumulation: The error accumulation caused by the mutual influence between calibrated parameters. Select excellent individuals (calibration paths) based on the fitness to enter the next generation. Generate new individuals through crossover operations (such as swapping the order of some parameters in two paths). Randomly change the order of some parameters in the individual to increase the search diversity. Reach the preset number of iterations or the fitness value converges.

[0077] Based on the dependency relationships among the parameters in the candidate parameter set, a calibrated dependency graph including node weights and edge weights is constructed, where the nodes represent the parameters to be calibrated, and the edge weights include the coupling strength between parameters and the calibration order constraint. This graph model can intuitively display the associations and dependencies among the parameters, providing a basis for subsequent path planning. By constructing the calibrated dependency graph, not only the direct dependency relationships among the parameters are considered, but also the importance of the parameters and the constraints on the calibration order are reflected through the weights, making the path planning more scientific and reasonable. According to the constructed calibrated dependency graph, an initial calibration sequence is determined, providing a starting point for subsequent optimization. Identify the calibration conflicts existing in the initial calibration sequence. When a conflict is detected, adjust the initial calibration sequence based on the calibration resource occupancy rate. This method can timely discover and solve the possible resource conflict problems in the calibration process, ensuring the smooth progress of the calibration process. By reasonably adjusting the initial calibration sequence, unnecessary calibration steps and resource waste are reduced, and the efficiency of the entire calibration process is improved. The genetic algorithm is used to optimize and iterate the adjusted initial calibration sequence. The genetic algorithm has global search ability and optimization ability, and can effectively find the optimal solution in a large-scale search space. Through continuous iteration and optimization of the genetic algorithm, the optimal calibration path is finally obtained, and this path can enable the calibration process to achieve optimal performance indicators, such as minimizing the calibration time, resource consumption, or maximizing the calibration accuracy, etc. The determination of the optimal calibration path ensures that the order and manner of parameter calibration are optimal, thereby improving the calibration quality of the entire ECU system and reducing the problems caused by improper calibration order or unreasonable resource allocation.

[0078] Optionally, the basic rule verification of the calibration parameters using the rule engine includes:

[0079] Parse the metadata structure of the calibration parameters, perform type matching verification, value range boundary detection, and physical unit conversion consistency verification, and generate the first-level verification flag bit;

[0080] Verify the control logic conflict situation based on the global parameter dependency graph, and generate the second-level verification flag bit;

[0081] Monitor the calibration resource occupancy status, implement pre-allocation verification of the storage space and peak pressure test of the communication bandwidth, and generate the third-level verification flag bit;

[0082] Generate a verification flag bit according to the first-level verification flag bit, the second-level verification flag bit, and the third-level verification flag bit.

[0083] Parse the metadata structure of the calibration parameters. Key information such as the type, value range, and physical unit of the parameters can be extracted, and type matching verification, value range boundary detection, and physical unit conversion consistency verification can be performed. Check whether the data type of the parameter conforms to the preset requirements, such as integers, floating-point numbers, boolean values, etc., to ensure the consistency and correctness of the parameter in terms of data type. Verify that the value of the parameter is within the specified range, including the limits of the minimum and maximum values, to prevent system anomalies or failures caused by the parameter exceeding the reasonable range. Based on the International System of Units conversion matrix, verify the physical unit of the parameter to ensure that the unit conversion between different parameters is correct and consistent, and avoid calculation errors or logical problems caused by unit mismatches. According to the results of the above three verifications, generate the first-level verification flag bit to identify whether the parameter passes the verification at the basic attribute level. Then, based on the global parameter dependency graph, check whether there are conflicts in the control logic between the parameters. The pre-constructed global parameter dependency graph can be used to analyze the mutual dependency relationship and control logic between the parameters, and detect whether there are mutually exclusive conditions, circular dependencies, or other logical conflict situations. Ensure that the collaborative work of the parameters in the system will not cause abnormal behavior or performance problems due to logical conflicts. According to the detection results of the control logic conflicts, generate the second-level verification flag bit to reflect the compliance of the parameters at the logical level. Next, pay attention to the resource occupancy situation during the calibration process. Check whether the storage space required for the calibration parameters has been reasonably pre-allocated to prevent data loss or system crashes caused by insufficient storage space. Monitor and test the usage of communication bandwidth during the calibration process to ensure that the communication bandwidth can meet the data transmission requirements during the calibration process, and avoid communication delays or packet loss problems caused by insufficient bandwidth. Ensure the stability and reliability of the calibration process, and prevent calibration failures or system performance degradation caused by insufficient resources. According to the monitoring results of the resource occupancy status, generate the third-level verification flag bit to indicate the reasonableness of the parameters in terms of resource utilization. Integrate the results of the first three levels of verification to generate the final verification flag bit. Integrate and evaluate the first-level, second-level, and third-level verification flag bits, and determine whether the calibration parameters pass the basic rule verification according to the preset rules and logic. Provide a clear result identifier for the entire basic rule verification process, indicating whether the calibration parameters meet the basic rule requirements, and providing a basis for subsequent anomaly detection and calibration result evaluation.

[0084] Using a rules engine can automatically parse the metadata structure of calibration parameters and perform various verification tasks, such as type matching verification, value range boundary detection, and physical unit conversion consistency verification, etc., which greatly improves the efficiency and speed of verification, and reduces the time and workload of manual verification. The rules engine can process a large number of calibration parameters simultaneously, quickly generate the first-level, second-level, and third-level verification flag bits, and realizes the efficient batch verification of numerous parameters. By setting the three-level verification flag bits, comprehensive verification is carried out from aspects such as the basic attributes, control logic, and resource occupancy of the parameters, ensuring the compliance, logical correctness, and rationality of resource use of the parameters, and avoiding problems that may be missed by a single verification method. Finally, a comprehensive verification flag bit is generated according to the three-level verification flag bits, which comprehensively reflects the verification results of the calibration parameters in all aspects and provides a comprehensive basis for subsequent decision-making. The rules engine can accurately match predefined business rules and strictly verify the calibration parameters. For example, in type matching verification, ensure that the type of the parameter is consistent with the expectation; in value range boundary detection, accurately judge whether the parameter value exceeds the allowable range; in physical unit conversion consistency verification, verify the correctness of unit conversion, thus improving the accuracy of verification. Based on the global parameter dependency graph to verify the control logic conflict situation, it can accurately identify possible logical contradictions between parameters and avoid system failures caused by logical errors.

[0085] Optionally, the use of a machine learning model to perform anomaly detection on the calibration parameters and determine whether the calibration parameters meet the requirements according to the basic rule verification results and anomaly detection results includes:

[0086] Extract the distribution skewness, time series fluctuation entropy value, and cross-parameter covariance matrix eigenvalue of the calibration parameters, and construct a multi-dimensional verification vector containing space-time joint features;

[0087] Input the multi-dimensional verification vector into a CNN-BiLSTM hybrid neural network, where the CNN convolutional layer extracts the spatial correlation features between parameters, and the BiLSTM layer captures long-term and short-term time series dependencies, and outputs an anomaly probability value;

[0088] Encode the verification flag bits into a feature vector, and jointly input it with the anomaly probability value into a gradient boosting decision tree model, and generate a final detection conclusion through a weighted voting mechanism.

[0089] Extract the distribution skewness, temporal fluctuation entropy value, and cross-parameter covariance matrix eigenvalues of the calibration parameters. These features reflect the statistical characteristics and dynamic behaviors of the parameters from different perspectives. Distribution skewness: Measures the asymmetry of the data distribution, helping to identify the skewness of the parameter values. Temporal fluctuation entropy value: Reflects the fluctuation complexity of the parameters in the time series, capturing the dynamic change patterns of the parameters. Cross-parameter covariance matrix eigenvalues: Reveal the linear correlations between different parameters, helping to discover the co-variation relationships between the parameters. Multidimensional verification vector construction: Integrate the above-extracted features to construct a multidimensional verification vector containing space-temporal joint features. This vector comprehensively characterizes the characteristics of the calibration parameters in multiple dimensions, providing rich information for subsequent anomaly detection. Input the constructed multidimensional verification vector into the CNN-BiLSTM hybrid neural network. Among them, the convolutional layer of the CNN (Convolutional Neural Network) is responsible for extracting the spatial correlation features between the parameters and can automatically learn the local correlations between the features; the BiLSTM (Bidirectional Long Short-Term Memory Network) layer captures the long-term and short-term temporal dependencies and effectively captures the dynamic change trends of the parameters in the time dimension. Through the processing of the hybrid neural network, the anomaly probability value is finally output. This probability value reflects the likelihood of the calibration parameters being abnormal, providing a quantitative basis for subsequent decision-making. Encode the verification flag bits generated by the rule engine into a feature vector and jointly input it into the Gradient Boosting Decision Tree (GBDT) model with the previously obtained anomaly probability value. The GBDT model can comprehensively consider various factors through the ensemble learning of multiple decision trees, improving the accuracy and robustness of the prediction. Inside the GBDT model, the input feature vector and anomaly probability value are comprehensively evaluated through a weighted voting mechanism, and finally, a detection conclusion of whether it meets the requirements is generated. This mechanism fully integrates the results of rule verification and anomaly detection, making the final conclusion more reliable and comprehensive.

[0090] Extract the distribution skewness, temporal fluctuation entropy value, and cross-parameter covariance matrix eigenvalues of the calibration parameters, and construct a multi-dimensional verification vector containing spatio-temporal joint features. This multi-dimensional feature extraction method can comprehensively capture the characteristics of the parameters in different aspects, providing richer information for subsequent anomaly detection. Combining the spatial correlation features and temporal dependence relationships of the parameters to form a comprehensive feature vector can more accurately reflect the actual situation of the parameters and improve the accuracy of anomaly detection. Using the convolutional layer of CNN (Convolutional Neural Network) can effectively extract the spatial correlation features between parameters, automatically learn the local patterns and structures in the data, and help discover the complex relationships between parameters. The BiLSTM layer can capture the long-term and short-term temporal dependence relationships of the parameters. For ECU parameters with dynamic characteristics, it can better understand their variation laws in the time series and improve the sensitivity to abnormal temporal patterns. The CNN-BiLSTM hybrid neural network combines the advantages of both, being able to process both spatial and temporal features, providing a more comprehensive feature learning ability, thus improving the accuracy and robustness of anomaly detection. Encode the verification flag bits generated by the rule engine into a feature vector, and jointly input it with the anomaly probability value into the gradient boosting decision tree model to generate the final detection conclusion through a weighted voting mechanism. This method combines rule-based verification and data-based anomaly detection results, making full use of the advantages of both.

[0091] Optionally, the method further includes:

[0092] Obtain the feedback data of the calibration parameters, where the feedback data includes the maturity increment value, calibration evaluation report, and task relevance. Based on the feedback data, dynamically adjust the maturity index, evaluation level, and task association degree index of the corresponding parameters in the preset calibration library through the Bayesian update algorithm;

[0093] Generate knowledge graph supplementary data based on the calibration conflict resolution records, and update the newly emerged parameter coupling relationships and resource occupancy patterns to the global parameter dependence graph and calibration resource constraint model.

[0094] Collect feedback data for calibration parameters to evaluate the calibration effect and update parameter metrics. Maturity increment value: The amount of improvement in parameter maturity after calibration (e.g., 0.1 indicates a 10% increase in maturity). Calibration evaluation report: Includes a qualitative evaluation of the calibration result (such as "successful", "partially successful", "failed") and a detailed analysis. Task relevance: A score representing the degree of association between the calibration parameter and the current task (e.g., 1 - 5 points, with 5 being the highest). Dynamically adjust the metrics of the corresponding parameters in the preset calibration library using the Bayesian update algorithm. The initial maturity index, evaluation level, and task relevance of the parameters in the preset calibration library serve as the prior distribution. Construct a likelihood function based on the feedback data to reflect the relationship between the observed data (feedback) and the parameter metrics. For example, the maturity increment value can be modeled as a normal distribution, and the evaluation report can be mapped to a classification probability. Calculate the posterior distribution using Bayes' formula and update the maturity index, evaluation level, and task relevance of the parameters according to the posterior distribution. For example, the maturity index is updated to the expected value of the posterior distribution. Immediately obtain feedback data and update the parameter metrics after each calibration to ensure the timeliness of the calibration library. Retain historical update records to avoid data overwriting and support long-term trend analysis. Collect records of conflict resolution during calibration for improving the global parameter dependency graph and calibration resource constraint model. Record content: Conflict type (such as resource competition, logical contradiction), solution (such as adjusting the calibration order, increasing resource allocation), parameters involved and their coupling relationships. Convert the conflict resolution records into supplementary data for the knowledge graph to enhance the model's understanding of parameter dependencies and resource constraints. Identify entities such as parameters, resources, and conflict types in the records. Extract the coupling relationships between parameters (such as "Parameter A has a resource competition with Parameter B"). Extract the relationship between resources and parameters (such as "Parameter C requires communication channel X"). Store the entities and relationships in a graph structure to form supplementary data for the knowledge graph. Add the newly emerged parameter coupling relationships to the global parameter dependency graph and update the edge weights. Adjust the direction and strength of the dependency relationships based on the conflict resolution records to improve the accuracy of the graph. Analyze the resource allocation scheme in the conflict resolution records to learn the resource occupancy pattern of the parameters. Add the newly learned resource constraint rules (such as "Parameter D needs to exclusively occupy memory Y during calibration") to the model.

[0095] By obtaining feedback data of calibration parameters, including maturity increment values, calibration evaluation reports, task relevance, etc., the maturity index, evaluation level, and task association degree indicators of the corresponding parameters in the preset calibration library are dynamically adjusted using the Bayesian update algorithm. This method can reflect the performance and changes of parameters in actual applications in real time, keeping the parameter indicators in the calibration library up-to-date and most accurate. Dynamically updating parameter indicators helps improve the accuracy and reliability of subsequent calibration work. For example, adjusting the maturity index according to the actually feedback maturity increment value can more accurately evaluate the stability and reliability of parameters, so as to select more appropriate parameters during the calibration process and reduce calibration errors caused by outdated or inaccurate parameters. During the calibration process, new parameter coupling relationships and resource occupancy patterns may occur. By generating knowledge graph supplementary data based on calibration conflict resolution records and updating these newly emerged relationships and patterns to the global parameter dependency graph and calibration resource constraint model, the system can flexibly adapt to these changes, continuously optimize its knowledge structure and model, and improve its adaptability to complex and changing calibration environments. When encountering new calibration conflicts or resource allocation problems, the updated global parameter dependency graph and resource constraint model can provide the system with more comprehensive and accurate information support, helping the system find solutions more quickly and effectively and avoiding decision-making mistakes caused by insufficient or inaccurate information.

[0096] This embodiment also discloses a verification system for ECU calibration file parameters. Figure 3 It is a schematic diagram of the modules of the verification system for ECU calibration file parameters disclosed in the embodiments of the present application, as Figure 3 shown. The system includes a feature module 301, a screening module 302, a calibration module 303, and a verification module 304, where:

[0097] The feature module 301 is configured to extract key features from the parameters to be calibrated in the ECU calibration file and construct a structured parameter feature vector according to the key features. The key features include parameter name, type, value range, physical meaning, maturity index, and task relevance.

[0098] The screening module 302 is configured to use a hybrid matching algorithm to screen out candidate parameters with a similarity higher than a threshold from the preset calibration library, assign a confidence score to each candidate parameter, and construct a candidate parameter set based on the candidate parameters.

[0099] The calibration module 303 is configured to recommend an optimal calibration path according to the candidate parameter set and calibrate the parameters to be calibrated according to the optimal calibration path to obtain calibrated parameters.

[0100] The verification module 304 is configured to perform basic rule verification on the calibration parameters using a rule engine, perform anomaly detection on the calibration parameters using a machine learning model, and determine whether the calibration parameters meet the requirements according to the basic rule verification result and the anomaly detection result.

[0101] Optionally, the screening module 302 is configured to:

[0102] Generate a semantic vector based on the text field of the parameter to be selected in the preset calibration library, and calculate the cosine similarity between the structured parameter feature vector and the semantic vector to obtain the semantic similarity;

[0103] Construct a global parameter dependency graph based on the control logic dependencies between parameters, and calculate the topological correlation degree between the parameter to be calibrated and the parameter to be selected in the global parameter dependency graph through a graph neural network;

[0104] Use bidirectional LSTM to extract the first temporal feature of the parameter to be calibrated and the second temporal feature of the parameter to be selected, and calculate the temporal matching degree between the first temporal feature and the second temporal feature through a dynamic time warping algorithm;

[0105] Perform weighted summation on the semantic similarity, the topological correlation degree, and the temporal matching degree to obtain the similarity value of the parameter to be selected, and use the parameter to be selected with a similarity value higher than the threshold as a candidate parameter.

[0106] Optionally, the screening module 302 is configured to:

[0107] Perform a linear mapping on the similarity value to obtain a basic confidence level, obtain the maturity index of the candidate parameter, and use the logarithmic change value of the maturity index as a correction value;

[0108] Perform weighted summation on the basic confidence level and the correction value to obtain a confidence score, and construct a candidate parameter set with candidate parameters whose confidence score is greater than the confidence threshold.

[0109] Optionally, the calibration module 303 is configured to:

[0110] Based on the dependency relationships of the parameters in the candidate parameter set, construct a calibration dependency graph including node weights and edge weights, where the nodes represent the parameters to be calibrated, and the edge weights include the coupling strength between parameters and the calibration order constraint;

[0111] Determine an initial calibration sequence according to the calibration dependency graph, identify whether there is a calibration conflict, and when a calibration conflict is detected, adjust the initial calibration sequence based on the calibration resource occupancy rate;

[0112] Use a genetic algorithm to optimize and iterate the adjusted initial calibration sequence to obtain an optimal calibration path.

[0113] Optionally, the verification module 304 is configured to:

[0114] Parse the metadata structure of the calibration parameters, perform type matching verification, value range boundary detection, and physical unit conversion consistency verification, and generate a first-level verification flag bit;

[0115] Verify the control logic conflict situation based on the global parameter dependency graph, and generate a second-level verification flag bit;

[0116] Monitor the occupancy status of calibration resources, perform pre-allocation verification of storage space and peak pressure test of communication bandwidth, and generate a third-level verification flag bit;

[0117] Generate a verification flag bit according to the first-level verification flag bit, the second-level verification flag bit, and the third-level verification flag bit.

[0118] Optionally, the verification module 304 is configured to:

[0119] Extract the distribution skewness, time series fluctuation entropy value, and cross-parameter covariance matrix eigenvalue of the calibration parameters, and construct a multi-dimensional verification vector including space-time joint features;

[0120] Input the multi-dimensional verification vector into a CNN-BiLSTM hybrid neural network, where the CNN convolutional layer extracts the spatial correlation features between parameters, and the BiLSTM layer captures the long-term and short-term time series dependency relationships, and outputs an anomaly probability value;

[0121] Encode the verification flag bit into a feature vector, and jointly input it with the anomaly probability value into a gradient boosting decision tree model, and generate a final detection conclusion through a weighted voting mechanism.

[0122] Optionally, the system further includes an update module, which is configured to:

[0123] Obtain the feedback data of the calibration parameters, where the feedback data includes a maturity increment value, a calibration evaluation report, and a task relevance, and dynamically adjust the maturity index, evaluation level, and task association index of the corresponding parameters in the preset calibration library based on the feedback data through the Bayesian update algorithm;

[0124] Generate knowledge graph supplementary data based on the calibration conflict resolution records, and update the newly emerged parameter coupling relationships and resource occupancy patterns to the global parameter dependency graph and the calibration resource constraint model.

[0125] It should be noted that: when the device provided in the above embodiment realizes its functions, only the division of the above functional modules is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept. For the specific implementation process, please refer to the method embodiment and will not be elaborated here.

[0126] This embodiment also discloses an electronic device. Referring to Figure 4 , the electronic device may include: at least one processor 401, at least one communication bus 402, a user interface 403, a network interface 404, and at least one memory 405.

[0127] Among them, the communication bus 402 is used to realize the connection and communication between these components.

[0128] Among them, the user interface 403 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 403 may further include a standard wired interface and a wireless interface.

[0129] Among them, the network interface 404 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0130] Among them, the processor 401 may include one or more processing cores. The processor 401 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 405, and by calling the data stored in the memory 405, the processor 401 executes various functions of the server and processes data. Optionally, the processor 401 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 401 may integrate one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 401 and may be implemented separately by a single chip.

[0131] Among them, the memory 405 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 405 includes a non-transitory computer-readable storage medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 405 may also be at least one storage device located far from the aforementioned processor 401. As Figure 4 shown, in the memory 405 as a computer storage medium, there may be included an operating system, a network communication module, a user interface module, and an application program for the ECU calibration file parameter verification method.

[0132] In Figure 4 the electronic device shown, the user interface 403 is mainly used to provide an input interface for the user and obtain the data input by the user; while the processor 401 can be used to call the application program for the ECU calibration file parameter verification method stored in the memory 405. When executed by one or more processors 401, the electronic device is caused to execute one or more of the methods in the above embodiments.

[0133] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0134] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0136] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 405 and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. And the aforementioned memory 405 includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0139] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the disclosure of the specification. The present application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for verifying ECU calibration file parameters, characterized in that: Applied to a parameter verification platform, the method comprises: Extract key features from the parameters to be calibrated in the ECU calibration file, and construct a structured parameter feature vector based on the key features, wherein the key features include parameter name, type, value range, physical meaning, maturity index and task relevance; A hybrid matching algorithm is used to screen out candidate parameters whose similarity with the structural parameter feature vector is higher than a threshold from a preset calibration library, a confidence score is assigned to each candidate parameter, and a candidate parameter set is constructed based on the candidate parameters, wherein the hybrid matching algorithm includes a cosine similarity algorithm, a graph neural network algorithm, and a dynamic time warping algorithm; recommending an optimal calibration path according to the candidate parameter set, and calibrating the parameters to be calibrated according to the optimal calibration path to obtain calibration parameters; A rule engine is used to perform basic rule verification on the calibration parameters, and a machine learning model is used to perform anomaly detection on the calibration parameters. Whether the calibration parameters meet the requirements is determined based on the basic rule verification results and the anomaly detection results.

2. The method for verifying ECU calibration file parameters according to claim 1, characterized in that: The method of using a hybrid matching algorithm to select candidate parameters from a preset calibration library whose similarity with the structural parameter feature vector is higher than a threshold value includes: Generate a semantic vector based on the text field of the candidate parameter in the preset calibration library, and calculate the cosine similarity between the structural parameter feature vector and the semantic vector to obtain the semantic similarity; A global parameter dependency graph is constructed based on the control logic dependency between the parameters, and the topological correlation between the parameters to be calibrated and the parameters to be selected in the global parameter dependency graph is calculated through a graph neural network; Using a bidirectional LSTM to extract a first time series feature of the parameter to be calibrated and a second time series feature of the parameter to be selected, and calculating a time series matching degree between the first time series feature and the second time series feature through a dynamic time warping algorithm; The semantic similarity, the topological association, and the temporal matching are weightedly summed to obtain similarity values ​​of the candidate parameters, and the candidate parameters whose similarity values ​​are higher than the threshold are taken as candidate parameters.

3. The method for verifying ECU calibration file parameters according to claim 2, characterized in that: The step of assigning a confidence score to each of the candidate parameters and constructing a candidate parameter set based on the candidate parameters includes: Linearly mapping the similarity value to obtain a basic confidence, obtaining a maturity index of the candidate parameter, and using a logarithmic change value of the maturity index as a correction value; A confidence score is obtained by weighted summing the basic confidence and the correction value, and candidate parameters having confidence scores greater than a confidence threshold are used to construct a candidate parameter set.

4. The method for verifying ECU calibration file parameters according to claim 1, characterized in that: The recommending the optimal calibration path according to the candidate parameter set comprises: Based on the dependency relationship of each parameter in the candidate parameter set, a calibration dependency graph including node weights and edge weights is constructed, wherein the nodes represent the parameters to be calibrated, and the edge weights include the coupling strength between parameters and the calibration order constraints; determining an initial calibration sequence according to the calibration dependency graph, identifying whether there is a calibration conflict, and when a calibration conflict is detected, adjusting the initial calibration sequence based on a calibration resource occupancy rate; A genetic algorithm is used to optimize and iterate the adjusted initial calibration sequence to obtain an optimal calibration path.

5. The method for verifying ECU calibration file parameters according to claim 2, characterized in that: The using a rule engine to perform basic rule verification on the calibration parameters includes: Parsing the metadata structure of the calibration parameters, performing type matching check, value range boundary check and physical unit conversion consistency check, and generating a first-level check flag; Verify the control logic conflict situation based on the global parameter dependency graph and generate a second level check flag; Monitor and calibrate resource occupancy status, implement storage space pre-allocation verification and communication bandwidth peak pressure test, and generate third-level verification flags; A check flag is generated according to the first-level check flag, the second-level check flag and the third-level check flag.

6. The method for verifying ECU calibration file parameters according to claim 5, characterized in that: The using of the machine learning model to perform anomaly detection on the calibration parameters, and determining whether the calibration parameters meet the requirements according to the basic rule verification result and the anomaly detection result includes: Extracting the distribution skewness, time series fluctuation entropy value and cross-parameter covariance matrix eigenvalue of the calibration parameters, and constructing a multidimensional calibration vector containing space-time series joint features; Input the multidimensional check vector into a CNN-BiLSTM hybrid neural network, wherein the CNN convolution layer extracts spatial correlation features between parameters, the BiLSTM layer captures long-term and short-term temporal dependencies, and outputs an abnormal probability value; The check flag is encoded as a feature vector and input into the gradient boosting decision tree model together with the abnormal probability value, and the final detection conclusion is generated through a weighted voting mechanism.

7. The method for verifying ECU calibration file parameters according to claim 2, characterized in that: The method further comprises: Acquire feedback data of the calibration parameters, the feedback data including a maturity increment value, a calibration evaluation report and a task relevance, and dynamically adjust the maturity index, evaluation level and task relevance index of the corresponding parameters in the preset calibration library through a Bayesian update algorithm based on the feedback data; The knowledge graph supplementary data is generated based on the calibration conflict resolution records, and the newly emerged parameter coupling relationships and resource occupancy patterns are updated to the global parameter dependency graph and calibration resource constraint model.

8. A verification system for ECU calibration file parameters, characterized in that: It includes feature module, screening module, calibration module and verification module, among which: A feature module is configured to extract key features from the parameters to be calibrated in the ECU calibration file, and construct a structured parameter feature vector according to the key features, wherein the key features include parameter name, type, value range, physical meaning, maturity index and task relevance; A screening module is configured to screen out candidate parameters whose similarity with the structured parameter feature vector is higher than a threshold from a preset calibration library using a hybrid matching algorithm, assign a confidence score to each of the candidate parameters, and construct a candidate parameter set based on the candidate parameters, wherein the hybrid matching algorithm includes a cosine similarity algorithm, a graph neural network algorithm, and a dynamic time warping algorithm; A calibration module, configured to recommend an optimal calibration path according to the candidate parameter set, and calibrate the parameters to be calibrated according to the optimal calibration path to obtain calibration parameters; The verification module is configured to use a rule engine to perform basic rule verification on the calibration parameters, use a machine learning model to perform anomaly detection on the calibration parameters, and determine whether the calibration parameters meet the requirements based on the basic rule verification results and the anomaly detection results.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images