Method and System for Solving Hierarchical Decoupling Parameters Based on Feedback Optimization

Abstract

The present invention relates to the technical field of decoupling of in-vehicle infotainment systems. The present invention discloses a method and system for solving hierarchical decoupling parameters based on feedback optimization. The method includes determining decoupling standard parameters based on decoupling requirement data and basic function data, performing decoupling operations according to the decoupling standard parameters to generate a first decoupling configuration result, testing the first decoupling configuration result to obtain first performance data during the testing process, determining a parameter perturbation factor based on decoupling feedback data and the first performance data, generating M decoupling scheme parameters based on the parameter perturbation factor and the decoupling standard parameters, and generating optimal scheme parameters based on an intelligent optimization algorithm, second performance data, and the M decoupling scheme parameters. In this way, through the evaluation and optimization of the decoupling scheme parameters, the adaptability of the decoupling configuration and the overall performance of the system are improved, thereby better solving the problem of unstable decoupling effect in the prior art in the field of in-vehicle infotainment systems.

Description

Technical Field

[0001] The present invention relates to the technical field of in-vehicle system decoupling. More specifically, the present invention relates to a method and system for solving hierarchical decoupling parameters based on feedback optimization. Background Art

[0002] Hierarchical decoupling refers to isolating each functional module of the in-vehicle system by dividing different levels of the system (such as the signal layer, application layer, and middleware layer, etc.). In this way, the business logic can be decoupled from the underlying hardware signals, ensuring that differences in different vehicle models or underlying protocols do not affect the development and iteration of application functions. This decoupling method makes each level of the system independent of each other, facilitating the optimization of signal management, function expansion, and system adaptation. Although there are related contents about hierarchical decoupling in the prior art, there are still certain problems when directly applied to the field of in-vehicle systems.

[0003] For example, the Chinese patent application with the publication number CN111258786A discloses a decoupling method, device, terminal, and storage medium in a hierarchical architecture. This patent defines a target interface and marks its implementation in the upper-layer implementation, enabling the target layer to call the services provided by the upper layer through a mapping relationship. This method reduces the coupling between levels, solves the dependence of the lower layer on the upper layer, and improves the execution speed.

[0004] Although the above prior art can achieve hierarchical decoupling, in the field of in-vehicle systems, due to the differences in signal standards of different vehicle models and the models of mobile devices, the parameters required in the hierarchical decoupling process are different, such as interface adaptation parameters and communication protocol parameters. In addition, there are few evaluation means for the hierarchical decoupling effect in the prior art, so it is difficult to determine the optimal decoupling parameter configuration, which to a certain extent affects the optimization of the overall system performance.

[0005] In view of this, the present invention proposes a method and system for solving hierarchical decoupling parameters based on feedback optimization to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for solving hierarchical decoupling parameters based on feedback optimization.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] In the first aspect, a method for solving hierarchical decoupling parameters based on feedback optimization is provided, including:

[0009] Obtain decoupling requirement data and the basic function data corresponding to the middleware, determine decoupling standard parameters based on the decoupling requirement data and the basic function data, perform a decoupling operation according to the decoupling standard parameters, and generate a first decoupling configuration result;

[0010] Obtain decoupling feedback data during the decoupling operation process, test the first decoupling configuration result, obtain the first performance data during the test process, and determine the parameter perturbation factor according to the decoupling feedback data and the first performance data;

[0011] Generate M decoupling scheme parameters based on the parameter perturbation factor and the decoupling standard parameters, and perform decoupling operations according to the M decoupling scheme parameters to generate corresponding second decoupling configuration results;

[0012] Obtain the second performance data corresponding to the second decoupling configuration result, and generate the optimal scheme parameters based on the intelligent optimization algorithm, the second performance data, and the M decoupling scheme parameters.

[0013] Furthermore, the method for determining the decoupling standard parameters includes:

[0014] Determine the relationship between the first element in the decoupling requirement data and the second element in the basic function data, use the associated first element and second element as nodes, and use the relationship between the first element and the second element as edges to construct a decoupling requirement graph, and retrieve the corresponding decoupling standard parameters from the pre-constructed database according to the decoupling requirement graph.

[0015] Furthermore, the method for determining the parameter perturbation factor according to the decoupling feedback data and the first performance data includes:

[0016] Divide the decoupling feedback data into H groups of sub-feedback data, calculate the feedback deviation distance based on the H groups of sub-feedback data, divide the first performance data into Q groups of sub-performance data, calculate the performance deviation distance based on the Q groups of sub-performance data, and fuse the feedback deviation distance and the performance deviation distance to generate the parameter perturbation factor, where H and Q are integers greater than 1, and H = Q.

[0017] Furthermore, the method for calculating the feedback deviation distance based on the H groups of sub-feedback data includes:

[0018] Combine the corresponding element indicators in the H groups of sub-feedback data to construct S fuzzy sets, determine the optimal element indicator and the worst element indicator in the S fuzzy sets based on the preset feedback range value, combine the optimal element indicators in the S fuzzy sets to construct a positive fuzzy ideal solution, combine the worst element indicators in the S fuzzy sets to construct a negative fuzzy ideal solution, calculate the positive deviation distance between the H groups of sub-feedback data and the positive fuzzy ideal solution, calculate the negative deviation distance between the H groups of sub-feedback data and the negative fuzzy ideal solution, and geometrically average the positive deviation distance and the negative deviation distance to determine the feedback deviation distance.

[0019] Furthermore, the calculation method of the positive deviation distance includes:

[0020] ;

[0021] In the formula, is the positive deviation distance between the -th group of sub-feedback data and the positive fuzzy ideal solution, is the -th element index in the -th group of sub-feedback data, is the corresponding optimal element index in the positive fuzzy ideal solution, and G is the total number of element indexes in the -th group of sub-feedback data.

[0022] Furthermore, the method for calculating the negative deviation distance includes:

[0023] ;

[0024] In the formula, is the negative deviation distance between the -th group of sub-feedback data and the negative fuzzy ideal solution, is the -th element index in the -th group of sub-feedback data, is the corresponding worst element index in the negative fuzzy ideal solution.

[0025] Furthermore, the method for generating M decoupling scheme parameters based on the parameter perturbation factor and the decoupling standard parameter includes:

[0026] Input the parameter perturbation factor and the decoupling standard parameter into a pre-constructed decoupling scheme model to obtain M decoupling scheme parameters.

[0027] The construction method of the decoupling scheme model includes:

[0028] Obtain a sample data set, which includes historical parameter perturbation factors, historical decoupling standard parameters, and historical decoupling scheme parameters;

[0029] Divide the sample data set into a sample training set and a sample test set, and construct a regression network;

[0030] Use the historical parameter perturbation factors and historical decoupling standard parameters in the sample training set as the input data of the regression network, and use the historical decoupling scheme parameters in the sample training set as the output data of the regression network to train the regression network to obtain an initial regression network for predicting decoupling scheme parameters;

[0031] Use the sample test set to test the initial regression network, and output the initial regression network with an error value less than the preset error value as the decoupling scheme model.

[0032] Furthermore, the method for generating optimal scheme parameters based on the intelligent optimization algorithm, the second performance data, and M decoupling scheme parameters includes:

[0033] S401: Use the M decoupling solution parameters as the initial population, calculate the performance influence degree value according to the second performance data, and use the performance influence degree value as the fitness function to calculate the fitness value of each individual in the initial population;

[0034] S402: Adopt the tournament selection strategy, randomly select 4 individuals from the initial population, compare the fitness values of the 4 individuals, and select the individual with the smallest fitness value as the parent individual;

[0035] S403: Repeat the selection process of S402 until N parent individuals are selected, and then transfer to S404;

[0036] S404: Select a crossover point on the path of each pair of parent individuals, and use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new offspring individuals;

[0037] S405: Randomly select two nodes for each offspring individual, exchange the positions of the two nodes, form a new population with all offspring individuals, and replace the original population to ensure that the size of the new population is still N;

[0038] S406: Preset the convergence threshold of the fitness value as CT, repeat the above S404 - S405, if the change in the fitness value of the optimal individual in the population for K consecutive generations is less than CT, the algorithm terminates;

[0039] S407: At the end of the algorithm, the offspring individual with the smallest fitness value in the population is the optimal solution parameter.

[0040] Furthermore, the second performance data includes data transmission delay, packet loss rate, fault occurrence frequency, and application response time, and the performance influence degree value is calculated according to the data transmission delay, packet loss rate, fault occurrence frequency, and application response time.

[0041] In the second aspect, a solution system for hierarchical decoupling parameters based on feedback optimization is provided, which is used to implement the above-mentioned solution method for hierarchical decoupling parameters based on feedback optimization, including:

[0042] Preliminary decoupling module: used to obtain decoupling requirement data and the basic function data corresponding to the middleware, determine the decoupling standard parameters based on the decoupling requirement data and the basic function data, and perform decoupling operations according to the decoupling standard parameters to generate the first decoupling configuration result;

[0043] Data processing module: used to obtain the decoupling feedback data during the decoupling operation, test the first decoupling configuration result, obtain the first performance data during the test, and determine the parameter perturbation factor according to the decoupling feedback data and the first performance data;

[0044] Parameter modification module: Generate M decoupling scheme parameters based on parameter perturbation factors and decoupling standard parameters, and perform decoupling operations according to the M decoupling scheme parameters to generate corresponding second decoupling configuration results;

[0045] Parameter optimization module: Used to obtain the second performance data corresponding to the second decoupling configuration result, and generate optimal scheme parameters based on the intelligent optimization algorithm, the second performance data, and the M decoupling scheme parameters.

[0046] In a third aspect, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for solving hierarchical decoupling parameters based on feedback optimization is implemented.

[0047] In a fourth aspect, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium, and when the computer program is executed, the above-mentioned method for solving hierarchical decoupling parameters based on feedback optimization is implemented.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0049] The present invention first determines decoupling standard parameters based on decoupling requirement data and basic function data, performs decoupling operations according to the decoupling standard parameters to generate a first decoupling configuration result, tests the first decoupling configuration result to obtain first performance data during the test process, determines parameter perturbation factors based on decoupling feedback data and the first performance data, generates M decoupling scheme parameters based on the parameter perturbation factors and the decoupling standard parameters, and generates optimal scheme parameters based on the intelligent optimization algorithm, the second performance data, and the M decoupling scheme parameters. In this way, by evaluating and optimizing the decoupling scheme parameters, the adaptability of the decoupling configuration and the overall performance of the system are improved, thereby better solving the problem of unstable decoupling effect in the prior art in the field of in-vehicle infotainment systems, and ensuring that the decoupled signal layer and service layer can work efficiently and stably. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic flowchart of the method for solving hierarchical decoupling parameters based on feedback optimization in the present invention;

[0051] Figure 2 It is a schematic structural diagram of the system for solving hierarchical decoupling parameters based on feedback optimization in the present invention;

[0052] Figure 3 It is a schematic diagram of the un-decoupled in-vehicle infotainment system in the prior art of the present invention;

[0053] Figure 4 It is a schematic diagram of the in-vehicle infotainment system in the prior art after decoupling using the method for solving hierarchical decoupling parameters based on feedback optimization. Detailed implementation manners

[0054] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] Embodiment 1

[0056] Please refer to Figure 1 As shown, the present embodiment discloses a method for solving the hierarchical decoupling parameters based on feedback optimization, including:

[0057] S10: Obtain decoupling requirement data and basic function data corresponding to the middleware, determine decoupling standard parameters based on the decoupling requirement data and the basic function data, and perform a decoupling operation according to the decoupling standard parameters to generate a first decoupling configuration result;

[0058] As Figure 3 shown, Figure 3 It shows vehicle model signal 1, vehicle model signal 2, android9, android10, settings app, air conditioner app, vehicle settings app, and voice app, etc. As Figure 3 can be seen, each vehicle model signal needs to be docked with multiple apps. For example, vehicle model signal 1 is respectively docked with the settings app, the air conditioner app, the vehicle settings app, and the voice app. Then, when the in-vehicle system in the prior art is not decoupled, due to the change of the vehicle model or the change of the CAN signal interface, the problem of needing to re-dock all occurs. In this embodiment, as Figure 4 shown, Figure 4It also includes vehicle model signal 1, vehicle model signal 2, Android 9, Android 10, settings app, air conditioner app, vehicle settings app, and voice app, etc. However, after applying the method for solving the hierarchical decoupling parameters based on feedback optimization disclosed in this application, decoupling is performed through the middleware to generate a signal layer and a service layer. The signal layer includes vehicle model signal 1, vehicle model signal 2, Android 9, Android 10, etc., while the service layer includes settings app, air conditioner app, vehicle settings app, and voice app, etc. Through the idea of hierarchical decoupling, the service layer and the signal layer are completely separated. The service layer only needs to focus on the business logic, and the method of interacting with the signal layer is uniformly encapsulated by the middleware. The middleware refers to the intermediate software layer used to provide communication, data transmission, and function coordination between different levels of the in-vehicle system (such as the signal layer, service layer, etc.). The middleware plays a bridging role in the in-vehicle system, responsible for managing the interaction between the underlying hardware (such as sensors, communication modules) and the upper-layer application functions, so that the business logic is decoupled from the underlying hardware, thereby enhancing the scalability and adaptability of the system.

[0059] In this embodiment, the decoupling requirement data includes, but is not limited to, vehicle model signal protocol parameters, software interface adaptation, and the dependency relationships of business logic and application functions. Since the CAN bus and other communication protocols of different vehicle models are different, the differences in these protocol vehicle model signal protocol parameters need to be considered during the decoupling process to ensure that the signal layer can accurately transmit data. For the adaptation of different operating system versions (such as Android 9, 10) and in-vehicle applications, the decoupling requirement data needs to define interface adaptation parameters. The dependency relationships of business logic and application functions refer to the specific requirements of each application function (such as settings app, air conditioner app, voice app, etc.) in the service layer for the underlying data and device functions provided by the signal layer. Such dependency relationships determine which information and services the service layer needs to obtain from the signal layer during actual operation to ensure that each application function can work properly.

[0060] Among them, the basic function data includes, but is not limited to, communication protocol support information, hardware interface types, application protocol stack configurations, etc. The communication protocol support information refers to the basic information of communication protocols such as CAN bus, LIN bus, or Ethernet supported by the in-vehicle system for effective connection with the signal layer. The application protocol stack configuration refers to the configuration information of the protocol stack (such as TCP / IP, HTTP) that supports in-vehicle applications to ensure normal communication and data exchange among various business applications. The hardware interface type refers to the physical and wireless connection interface types supported in the in-vehicle system for data exchange and control connection with external devices or networks, such as USB, Bluetooth, Wi-Fi, etc.

[0061] The methods for determining the decoupling standard parameters include:

[0062] Determine the relationship between the first element in the decoupling requirement data and the second element in the basic function data. Take the associated first and second elements as nodes and the relationship between the first and second elements as edges to construct a decoupling requirement graph. Then, retrieve the corresponding decoupling standard parameters from the pre-built database according to the decoupling requirement graph.

[0063] It should be noted that the first element mentioned above refers to the specific requirement item in the decoupling requirement data, and the second element refers to the specific function item in the basic function data. Exemplarily, the first element can be the vehicle model signal protocol parameter, and the second element can be the communication protocol support information. Then, the relationship between the first and second elements is that the vehicle model signal protocol parameter (the first element) depends on the communication protocol support information (the second element). Because the business layer needs to confirm whether the signal layer can support the specific communication protocol of the vehicle model (such as the CAN bus protocol) to ensure the accurate transmission of data. Based on this association relationship, the CAN protocol parameter adapted to the vehicle model signal can be retrieved from the pre-built database and defined as the decoupling standard parameter. For example, set the baud rate of the CAN bus to 500 kbps to match the data transmission requirements of the vehicle model, and specify the message format (such as 11-bit or 29-bit ID format) and specific signal mapping parameters to ensure the consistency of data transmission.

[0064] In this embodiment, the decoupling operation according to the decoupling standard parameters means configuring and separating the signal layer and the business layer of the in-vehicle system based on the determined decoupling standard parameters to ensure that the business layer can function smoothly independently of the changes in specific vehicle models or protocols. Then, the generation of the first decoupling configuration result represents the specific configuration state after the configuration and separation of the signal layer and the business layer are completed according to the decoupling standard parameters.

[0065] S20: Obtain the decoupling feedback data during the decoupling operation, test the first decoupling configuration result, obtain the first performance data during the test, and determine the parameter perturbation factor according to the decoupling feedback data and the first performance data.

[0066] Among them, the decoupling feedback data includes but is not limited to the number of interface calls, the number of decoupling errors, and the number of incompatibilities. The number of interface calls refers to the number of successful interface calls during the decoupling operation. The number of decoupling errors refers to the number of errors that occur during the decoupling operation. The number of incompatibilities refers to the number of interface incompatibilities that occur during the decoupling operation.

[0067] It can be understood that the first decoupling configuration result represents the specific configuration state after the configuration and separation of the signal layer and the service layer according to the decoupling standard parameters. Then, testing the first decoupling configuration result refers to verifying the performance and stability of the signal layer and the service layer after decoupling configuration. Specifically, this includes simulating the normal operations of the in-vehicle system in the actual operating environment, checking whether the first decoupling configuration result meets the expected independence and compatibility requirements, so as to ensure that the service layer can operate normally without being affected by the signal layer or vehicle model changes. Then, the first performance data includes, but is not limited to, data transmission delay, packet loss rate, fault occurrence frequency, and application response time. In this embodiment, the application response time refers to the average response time of the service layer application after receiving the signal layer data, reflecting the impact of decoupling on the application performance.

[0068] The method for determining the parameter perturbation factor based on the decoupling feedback data and the first performance data includes:

[0069] Dividing the decoupling feedback data into H groups of sub-feedback data, calculating the feedback deviation distance based on the H groups of sub-feedback data, dividing the first performance data into Q groups of sub-performance data, calculating the performance deviation distance based on the Q groups of sub-performance data, and fusing the feedback deviation distance and the performance deviation distance to generate the parameter perturbation factor, where H and Q are integers greater than 1 and H = Q.

[0070] It should be noted that taking the decoupling feedback data as an example, those skilled in the art will obtain a group of sub-feedback data during each decoupling operation. Similarly, the sub-feedback data includes the number of call interfaces, the number of decoupling errors, and the number of incompatibilities. Then, a decoupling configuration result will be obtained after each decoupling operation. After testing each decoupling configuration result, a corresponding group of sub-performance data will be obtained. Similarly, the sub-performance data includes data transmission delay, packet loss rate, fault occurrence frequency, and application response time.

[0071] The method for calculating the feedback deviation distance based on the H groups of sub-feedback data includes:

[0072] Combining the corresponding element indicators in the H groups of sub-feedback data to construct S fuzzy sets, determining the optimal element indicator and the worst element indicator in the S fuzzy sets based on the preset feedback range value, combining the optimal element indicators in the S fuzzy sets to construct the positive fuzzy ideal solution, combining the worst element indicators in the S fuzzy sets to construct the negative fuzzy ideal solution, calculating the positive deviation distance between the H groups of sub-feedback data and the positive fuzzy ideal solution, calculating the negative deviation distance between the H groups of sub-feedback data and the negative fuzzy ideal solution, and geometrically averaging the positive deviation distance and the negative deviation distance to determine the feedback deviation distance.

[0073] It is not difficult to understand that the combination of the corresponding element indicators mentioned above refers to summarizing the element indicators of the same type in the H groups of sub-feedback data. For example, if the sub-feedback data includes the number of times of calling the interface, the number of decoupling errors, and the number of incompatibilities, then the number of times of calling the interface in the H sub-feedback data is summarized to construct 3 fuzzy sets. The above preset feedback range value refers to the performance range of each element indicator under ideal conditions. Taking the number of times of calling the interface as an example, the feedback range value can be [80, 110]. 80 represents the lowest expected value of the number of times of calling the interface. A value lower than this may indicate poor system performance or unsatisfactory decoupling effect. 110 represents the highest expected value of the number of times of calling the interface. Exceeding this value may mean excessive use of system resources or redundant calls.

[0074] Among them, the positive fuzzy ideal solution represents the best combination of each element indicator, and the negative fuzzy ideal solution represents the worst combination of each element indicator.

[0075] The methods for calculating the positive deviation distance include:

[0076] ;

[0077] In the formula, is the positive deviation distance between the th group of sub-feedback data and the positive fuzzy ideal solution, is the th element indicator in the th group of sub-feedback data, is the optimal element indicator corresponding to the positive fuzzy ideal solution, and G is the total number of element indicators in the th group of sub-feedback data.

[0078] The methods for calculating the negative deviation distance include:

[0079] ;

[0080] In the formula, is the negative deviation distance between the th group of sub-feedback data and the negative fuzzy ideal solution, is the th element indicator in the th group of sub-feedback data, is the worst element indicator corresponding to the negative fuzzy ideal solution.

[0081] Similarly, the method for calculating the performance deviation distance is the same as the method for calculating the feedback deviation distance above, except that the sub-feedback data is replaced with sub-performance data, and the feedback range value is replaced with the performance range value. As for the performance range value, it is also preset according to expert experience and prior knowledge, and this embodiment will not elaborate on it too much.

[0082] In this embodiment, the fusion of the feedback deviation distance and the performance deviation distance can be cascaded fusion. Cascaded fusion means connecting the feedback deviation distance and the performance deviation distance in a certain order to form a comprehensive vector or matrix, so as to retain the characteristic information of both at the same time. This fusion method does not directly perform arithmetic combination on the feedback deviation distance and the performance deviation distance, but cascades them as independent parts, so that the influence of both deviations can be considered in the final analysis.

[0083] The decoupling configuration result first generated in this embodiment takes into account the independent requirements of the service logic and the signal layer, and is then verified through actual tests, which can ensure that the configuration result adapts to the changing environment between the signal layer and the service layer, making the system have better compatibility. By analyzing the decoupling feedback data and the first performance data of the first decoupling configuration result, the deficiencies in the current decoupling operation can be identified, providing a quantitative basis for the adjustment of the parameters of the subsequent decoupling scheme. This process can form a closed-loop optimization system, which is beneficial to gradually improving the decoupling scheme.

[0084] S30: Generate M decoupling scheme parameters based on the parameter perturbation factor and the decoupling standard parameter, and perform decoupling operations according to the M decoupling scheme parameters to generate corresponding second decoupling configuration results;

[0085] In an embodiment of the present invention, the method for generating M decoupling scheme parameters based on the parameter perturbation factor and the decoupling standard parameter includes:

[0086] Input the parameter perturbation factor and the decoupling standard parameter into a pre-constructed decoupling scheme model to obtain M decoupling scheme parameters.

[0087] The construction method of the decoupling scheme model includes:

[0088] Obtain a sample data set, where the sample data set includes historical parameter perturbation factors, historical decoupling standard parameters, and historical decoupling scheme parameters;

[0089] Divide the sample data set into a sample training set and a sample test set, and construct a regression network;

[0090] Use the historical parameter perturbation factors and historical decoupling standard parameters in the sample training set as the input data of the regression network, and use the historical decoupling scheme parameters in the sample training set as the output data of the regression network to train the regression network to obtain an initial regression network for predicting decoupling scheme parameters;

[0091] Use the sample test set to test the initial regression network, and output the initial regression network with an error value less than the preset error value as the decoupling scheme model. The initial regression network is a deep neural network model.

[0092] It should be added that in this embodiment, the decoupling standard parameters are modified based on the parameter perturbation factor to generate M sets of decoupling scheme parameters. During the process of modifying the decoupling standard parameters based on the parameter perturbation factor, the parameter perturbation factor will act as a "feedback adjustment mechanism" to help adjust the decoupling standard parameters to optimize the adaptability and performance of the system. The logic of this process is to use the feedback data obtained during the actual decoupling process (such as the success rate of interface calls, the number of decoupling errors, etc.), combined with the first performance data (such as data transmission delay, failure occurrence frequency, etc.), calculate the feedback and performance deviation, and then generate a perturbation factor, which is used to finely adjust the decoupling standard parameters to better adapt to the observed differences and demand changes in the actual operating environment.

[0093] Exemplarily, the decoupling standard parameters include the baud rate of the CAN bus, and the initial value is set to 500 kbps. During the decoupling process, it is found that the decoupling feedback data indicates that the "number of interface call errors" is relatively high, and the "data transmission delay" is also high in the first performance data. These problems may mean that the current baud rate cannot fully meet the transmission requirements. By calculating the deviation between the decoupling feedback data and the first performance data, a relatively large positive parameter perturbation factor is generated. Based on this parameter perturbation factor, the system adjusts the baud rate to a higher value (such as 550 kbps) to reduce the number of errors and delays, thereby optimizing the transmission performance.

[0094] S40: Obtain the second performance data corresponding to the second decoupling configuration result, and generate the optimal scheme parameters based on the intelligent optimization algorithm, the second performance data, and M sets of decoupling scheme parameters.

[0095] It can be understood that the second performance data has the same meaning as the first performance data, but only the expression is different. The second performance data includes but is not limited to data transmission delay, packet loss rate, failure occurrence frequency, and application response time. Then the method for obtaining the second performance data is also to test the second decoupling configuration result.

[0096] The intelligent optimization algorithm can be a genetic algorithm. Then the method for generating the optimal scheme parameters based on the intelligent optimization algorithm, the second performance data, and M sets of decoupling scheme parameters includes:

[0097] S401: Use M sets of decoupling scheme parameters as the initial population, calculate the performance influence degree value according to the second performance data, and use the performance influence degree value as the fitness function to calculate the fitness value of each individual in the initial population;

[0098] It is understandable that by calculating the fitness values of the decoupling scheme parameters to measure the actual performance of each scheme under the current configuration, the calculation method of the performance impact degree enables the fitness values to quantify the advantages and disadvantages of each scheme, identify the schemes with better and worse performance, and provide a basis for subsequent selection and optimization. Generally, the smaller the fitness value of an individual, the better its performance.

[0099] S402: Adopt the tournament selection strategy. Randomly select 4 individuals from the initial population, compare the fitness values of the 4 individuals, and select the individual with the smallest fitness value as the parent individual.

[0100] Among them, the tournament selection strategy is to randomly select several individuals from the population each time and determine the better parent individuals by comparing the fitness values. This process ensures that each round of selection can be based on the performance indicators and gradually select more potential individuals.

[0101] S403: Repeat the selection process of S402 until N parent individuals are selected, and then transfer to S404.

[0102] S404: Select a crossover point on the path of each pair of parent individuals and use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new offspring individuals.

[0103] Among them, single-point crossover is a commonly used genetic algorithm operation. By exchanging part of the gene information of the parent individuals to generate new individuals, this operation can produce offspring with different parameter combinations and enhance the diversity of the population.

[0104] S405: Randomly select two nodes for each offspring individual and exchange their positions. Combine all the offspring individuals to form a new population and replace the original population to ensure that the size of the new population is still N.

[0105] S406: Preset the convergence threshold of the fitness value as CT. Repeat S404 - S405. If the change in the fitness value of the optimal individual in the population for K consecutive generations is less than CT, the algorithm terminates.

[0106] S407: At the end of the algorithm, the offspring individual with the smallest fitness value in the population is the optimal solution parameter.

[0107] In this embodiment, by generating M decoupling scheme parameters and performing decoupling operations one by one to form the corresponding second decoupling configuration results, this step ensures that the actual performance of the system under different parameter combinations is fully tested. Then, according to the second performance data generated by each second decoupling configuration result, the optimal decoupling scheme parameters are selected through the intelligent optimization algorithm. This combination method ensures that not only diverse decoupling scheme parameters can be obtained, but also the optimal scheme parameters can be selected after actual performance verification.

[0108] The second performance data includes data transmission delay, packet loss rate, fault occurrence frequency, and application response time. The method for calculating the performance impact value based on the second performance data includes:

[0109] PID = ;

[0110] In the formula, PID is the performance impact value, is the data transmission delay, is the packet loss rate, is the fault occurrence frequency, is the application response time, is the arccotangent function, is the hyperbolic cosine function, is the hyperbolic sine function, is the arctangent function, is the logarithm function with base 3.

[0111] Among them, for the data transmission delay and the fault occurrence frequency, when the data transmission delay and the fault occurrence frequency are larger, it indicates that the performance of the second decoupling configuration result is poor. This means that the configuration result does not effectively optimize the response and stability of the system under these conditions. Therefore, from the above content, it can be seen that the larger the performance impact value, the worse the corresponding decoupling effect.

[0112] In this embodiment, first, the decoupling standard parameters are determined based on the decoupling requirement data and the basic function data. Decoupling operations are performed according to the decoupling standard parameters to generate the first decoupling configuration result. The first decoupling configuration result is tested to obtain the first performance data during the test process. The parameter perturbation factor is determined based on the decoupling feedback data and the first performance data. M decoupling scheme parameters are generated based on the parameter perturbation factor and the decoupling standard parameters. The optimal scheme parameters are generated based on the intelligent optimization algorithm, the second performance data, and the M decoupling scheme parameters. In this way, through the evaluation and optimization of the decoupling scheme parameters, the adaptability of the decoupling configuration and the overall performance of the system are improved, thus better solving the problem of unstable decoupling effect in the prior art in the field of in-vehicle infotainment systems and ensuring that the decoupled signal layer and service layer can work efficiently and stably.

[0113] Embodiment 2

[0114] Please refer to Figure 2 As shown, based on the same inventive concept, this embodiment discloses and provides a system for solving hierarchical decoupling parameters based on feedback optimization. For the content not detailed in this embodiment, please refer to the relevant part of the description in Embodiment 1. The system includes:

[0115] Initial decoupling module: It is used to obtain decoupling requirement data and basic function data corresponding to the middleware, determine decoupling standard parameters based on the decoupling requirement data and the basic function data, perform decoupling operations according to the decoupling standard parameters, and generate a first decoupling configuration result;

[0116] The method for determining the decoupling standard parameters includes:

[0117] Determine the relationship between the first element in the decoupling requirement data and the second element in the basic function data, use the associated first and second elements as nodes, and use the relationship between the first and second elements as edges to construct a decoupling requirement graph, and retrieve the corresponding decoupling standard parameters from the pre-constructed database according to the decoupling requirement graph.

[0118] Data processing module: It is used to obtain decoupling feedback data during the decoupling operation, test the first decoupling configuration result, obtain first performance data during the test, and determine a parameter perturbation factor based on the decoupling feedback data and the first performance data;

[0119] The method for determining the parameter perturbation factor based on the decoupling feedback data and the first performance data includes:

[0120] Divide the decoupling feedback data into H groups of sub-feedback data, calculate the feedback deviation distance based on the H groups of sub-feedback data, divide the first performance data into Q groups of sub-performance data, calculate the performance deviation distance based on the Q groups of sub-performance data, and fuse the feedback deviation distance and the performance deviation distance to generate a parameter perturbation factor, where H and Q are integers greater than 1, and H = Q.

[0121] The method for calculating the feedback deviation distance based on the H groups of sub-feedback data includes:

[0122] Combine the corresponding element indicators in the H groups of sub-feedback data to construct S fuzzy sets, determine the optimal element indicator and the worst element indicator in the S fuzzy sets based on the preset feedback range value, combine the optimal element indicators in the S fuzzy sets to construct a positive fuzzy ideal solution, combine the worst element indicators in the S fuzzy sets to construct a negative fuzzy ideal solution, calculate the positive deviation distance between the H groups of sub-feedback data and the positive fuzzy ideal solution, calculate the negative deviation distance between the H groups of sub-feedback data and the negative fuzzy ideal solution, and geometrically average the positive deviation distance and the negative deviation distance to determine the feedback deviation distance.

[0123] The method for calculating the positive deviation distance includes:

[0124] ;

[0125] In the formula, is the positive deviation distance between the th group of sub-feedback data and the positive fuzzy ideal solution, is the The element index in the group of sub-feedback data, is the optimal element index corresponding to the positive fuzzy ideal solution, and G is the total number of element indices in the group of sub-feedback data.

[0126] The methods for calculating the negative deviation distance include:

[0127] ;

[0128] In the formula, is the negative deviation distance between the group of sub-feedback data and the negative fuzzy ideal solution, is the element index in the group of sub-feedback data, is the worst element index corresponding to the negative fuzzy ideal solution.

[0129] Parameter modification module: Generate M decoupling scheme parameters based on the parameter perturbation factor and the decoupling standard parameter, perform decoupling operations according to the M decoupling scheme parameters, and generate corresponding second decoupling configuration results;

[0130] In an embodiment of the present invention, the method for generating M decoupling scheme parameters based on the parameter perturbation factor and the decoupling standard parameter includes:

[0131] Input the parameter perturbation factor and the decoupling standard parameter into a pre-constructed decoupling scheme model to obtain M decoupling scheme parameters.

[0132] The construction method of the decoupling scheme model includes:

[0133] Obtain a sample data set, where the sample data set includes historical parameter perturbation factors, historical decoupling standard parameters, and historical decoupling scheme parameters;

[0134] Divide the sample data set into a sample training set and a sample test set, and construct a regression network;

[0135] Use the historical parameter perturbation factors and historical decoupling standard parameters in the sample training set as the input data of the regression network, and use the historical decoupling scheme parameters in the sample training set as the output data of the regression network to train the regression network to obtain an initial regression network for predicting decoupling scheme parameters;

[0136] Use the sample test set to test the initial regression network, and output the initial regression network with an error value less than the preset error value as the decoupling scheme model. The initial regression network is a deep neural network model.

[0137] Parameter optimization module: used to obtain the second performance data corresponding to the second decoupling configuration result, and generate optimal solution parameters based on the intelligent optimization algorithm, the second performance data, and the M decoupling solution parameters.

[0138] Embodiment 3

[0139] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for solving the hierarchical decoupling parameters based on feedback optimization is implemented.

[0140] Since the electronic device introduced in this embodiment is the electronic device adopted for implementing the method for solving the hierarchical decoupling parameters based on feedback optimization in the embodiments of the present application, based on the method for solving the hierarchical decoupling parameters based on feedback optimization introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiments of the present application will not be described in detail here. As long as the electronic device adopted by those skilled in the art to implement the method for solving the hierarchical decoupling parameters based on feedback optimization in the embodiments of the present application falls within the scope of protection of the present application.

[0141] Embodiment 4

[0142] This embodiment publicly provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the above-mentioned method for solving the hierarchical decoupling parameters based on feedback optimization is implemented.

[0143] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the real situation. The selection of the preset parameters, weights, and thresholds in the formulas is set by those skilled in the art according to the actual situation.

[0144] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more collections of available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0145] Those of ordinary skill in the art will realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed in the present invention can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0146] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0147] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type, and there can be other division methods in actual implementation. 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 couplings, direct couplings, or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0148] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over 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.

[0149] In addition, in each embodiment of the present invention, each functional unit may be integrated in a processing unit, may exist physically alone for each unit, or two or more units may be integrated in one unit.

[0150] As described above, only the specific embodiments of the present invention are provided, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0151] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for solving hierarchical decoupling parameters based on feedback optimization, characterized in that: include: Obtaining decoupling requirement data and basic function data corresponding to the middleware, determining decoupling standard parameters based on the decoupling requirement data and the basic function data, performing a decoupling operation according to the decoupling standard parameters, and generating a first decoupling configuration result; Acquire decoupling feedback data during the decoupling operation, test the first decoupling configuration result, acquire first performance data during the test, and determine a parameter disturbance factor according to the decoupling feedback data and the first performance data; Generate M decoupling scheme parameters based on the parameter disturbance factor and the decoupling standard parameter, perform a decoupling operation according to the M decoupling scheme parameters, and generate a corresponding second decoupling configuration result; Obtaining second performance data corresponding to the second decoupling configuration result, and generating optimal solution parameters based on the intelligent optimization algorithm, the second performance data, and the M decoupling solution parameters; The method for generating optimal solution parameters based on the intelligent optimization algorithm, the second performance data and M decoupling solution parameters includes: S401: taking M decoupling scheme parameters as an initial population, calculating a performance influence value according to the second performance data, and taking the performance influence value as a fitness function to calculate a fitness value for each individual in the initial population; S402: Using the tournament selection strategy, randomly select 4 individuals from the initial population, compare the fitness values ​​of the 4 individuals, and select the individual with the smallest fitness value as the parent individual; S403: Repeat the selection process of S402 until N parent individuals are selected, and then proceed to S404; S404: Select a crossover point on the path of each pair of parent individuals, use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new child individuals; S405: Randomly select two nodes for each child individual and exchange the positions of the two nodes, form a new population with all the child individuals, and replace the original population, ensuring that the size of the new population is still N; S406: The convergence threshold of the preset fitness value is CT, and S404-S405 are repeated. If the fitness value change of the optimal individual in the population of consecutive K generations is less than CT, the algorithm terminates; S407: When the algorithm terminates, the sub-individual with the smallest fitness value in the population is the optimal solution parameter.

2. The method for solving hierarchical decoupling parameters based on feedback optimization according to claim 1 is characterized in that: The method for determining the decoupling standard parameters comprises: Determine the relationship between the first element in the decoupling requirement data and the second element in the basic function data, take the associated first and second elements as nodes, and the relationship between the first and second elements as edges, so as to construct a decoupling requirement graph, and retrieve the corresponding decoupling standard parameters from the pre-built database according to the decoupling requirement graph.

3. The method for solving hierarchical decoupling parameters based on feedback optimization according to claim 1 is characterized in that: The method for determining the parameter disturbance factor according to the decoupling feedback data and the first performance data includes: The decoupled feedback data is divided into H groups of sub-feedback data, and the feedback deviation distance is calculated based on the H groups of sub-feedback data. The first performance data is divided into Q groups of sub-performance data, and the performance deviation distance is calculated based on the Q groups of sub-performance data. The feedback deviation distance and the performance deviation distance are fused to generate a parameter disturbance factor, where H and Q are integers greater than 1, and H=Q.

4. The method for solving hierarchical decoupling parameters based on feedback optimization according to claim 3 is characterized in that: The method for calculating the feedback deviation distance based on the H group of sub-feedback data includes: The corresponding element indicators in the H group of sub-feedback data are combined to construct S fuzzy sets. The optimal element indicators and the worst element indicators in the S fuzzy sets are determined based on the preset feedback range value. The optimal element indicators in the S fuzzy sets are combined to construct a positive fuzzy ideal solution. The worst element indicators in the S fuzzy sets are combined to construct a negative fuzzy ideal solution. The positive deviation distance between the H group of sub-feedback data and the positive fuzzy ideal solution is calculated. The negative deviation distance between the H group of sub-feedback data and the negative fuzzy ideal solution is calculated. The feedback deviation distance is determined by geometrically averaging the positive deviation distance and the negative deviation distance.

5. The method for solving hierarchical decoupling parameters based on feedback optimization according to claim 4 is characterized in that: The calculation method of the positive deviation distance includes: ； In the formula, For the The positive deviation distance between the group feedback data and the positive fuzzy ideal solution, For the The first element index, is the optimal element index corresponding to the positive fuzzy ideal solution, G is The total number of element indicators in the group feedback data.

6. The method for solving hierarchical decoupling parameters based on feedback optimization according to claim 4 is characterized in that: Methods for calculating negative deviation distance include: ； In the formula, For the The negative deviation distance between the group feedback data and the negative fuzzy ideal solution, For the The first element index, is the worst element index corresponding to the negative fuzzy ideal solution.

7. The method for solving hierarchical decoupling parameters based on feedback optimization according to claim 6 is characterized in that: The method for generating M decoupling scheme parameters based on the parameter disturbance factor and the decoupling standard parameter includes: Input the parameter disturbance factor and the decoupling standard parameter into the pre-built decoupling scheme model to obtain M decoupling scheme parameters; The construction method of the decoupling solution model includes: Acquire a sample data set, wherein the sample data set includes a historical parameter disturbance factor, a historical decoupling standard parameter, and a historical decoupling scheme parameter; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical parameter disturbance factors and historical decoupling standard parameters in the sample training set are used as the input data of the regression network, and the historical decoupling scheme parameters in the sample training set are used as the output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the decoupling scheme parameters. The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than the preset error value is used as the decoupling solution model.

8. The method for solving hierarchical decoupling parameters based on feedback optimization according to claim 1 is characterized in that: The second performance data includes data transmission delay, packet loss rate, fault occurrence frequency and application response time, and the performance impact value is calculated based on the data transmission delay, packet loss rate, fault occurrence frequency and application response time.

9. A system for solving hierarchical decoupling parameters based on feedback optimization, which is used to implement the method for solving hierarchical decoupling parameters based on feedback optimization according to any one of claims 1 to 8, characterized in that: include: Preliminary decoupling module: used to obtain decoupling requirement data and basic function data corresponding to the middleware, determine decoupling standard parameters based on the decoupling requirement data and the basic function data, perform decoupling operations according to the decoupling standard parameters, and generate a first decoupling configuration result; Data processing module: used to obtain decoupling feedback data during the decoupling operation, test the first decoupling configuration result, obtain first performance data during the test, and determine the parameter disturbance factor according to the decoupling feedback data and the first performance data; Parameter modification module: generating M decoupling scheme parameters based on the parameter disturbance factor and the decoupling standard parameter, performing decoupling operation according to the M decoupling scheme parameters, and generating a corresponding second decoupling configuration result; Parameter optimization module: used to obtain the second performance data corresponding to the second decoupling configuration result, and generate optimal solution parameters based on the intelligent optimization algorithm, the second performance data and M decoupling solution parameters.

Images