ECU module configuration methods, devices, electronic equipment and storage media
By quantifying the multi-dimensional feature parameters of ECU modules to generate feature vectors, the system automatically recommends ECU module combinations, solving the problems of low configuration efficiency and poor accuracy in existing technologies. This achieves efficient and accurate ECU module configuration and reduces development costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- WUHAN JIANGXIA CHUNENG AUTOMOBILE TECHNOLOGY R&D CO LTD
- Filing Date
- 2026-03-18
- Publication Date
- 2026-06-30
Smart Images
Figure CN122308815A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of ECU software development technology, and in particular to an ECU module configuration method, apparatus, electronic device and storage medium. Background Technology
[0002] With the development of new energy vehicles and intelligent driving technologies, the functions of ECUs (Electronic Control Units) are becoming increasingly complex, and their development models are gradually shifting towards "low-code and modular" approaches. In current ECU model code generation solutions, the Autosar (Automotive Open System Architecture)-based model code generation method requires manufacturers to purchase expensive Autosar tools. Under the pressure of cost reduction in intelligent electric vehicles and the toolchain cost pressures of most small and medium-sized ECU manufacturers, mainstream OEMs (Original Equipment Manufacturers) are beginning to accept non-Autosar software architecture automotive electronic embedded software development methods. Gradually, Simulink has become the mainstream modeling and simulation tool in the automotive electronics field. With its graphical programming advantages, it has become the core platform for ECU development. Engineers can build control models by dragging and dropping pre-made modules, significantly reducing the development threshold.
[0003] Currently, ECU module configuration based on Simulink primarily relies on human experience. The core process involves engineers selecting target modules from the module library based on development requirements, manually verifying module interface compatibility, hardware adaptability, and safety level matching, and finally completing module combination and communication topology design. However, with the surge in the number of ECU functional modules and the continuous upgrading of performance / safety standards in intelligent driving scenarios, this manually-driven process has gradually revealed significant shortcomings: First, it is highly dependent on manual labor, resulting in low configuration efficiency. Faced with dozens or even hundreds of candidate modules, manual selection and multi-dimensional verification often take several hours, making it difficult to match the current tight development cycle of ECUs. Moreover, different engineers have different standards for judging module performance redundancy and safety level adaptability, which can easily lead to problems such as "functional compatibility but wasted hardware resources" and "interface compatibility but runtime conflicts." Second, it has a high matching error rate and high debugging costs in the later stages. Manual configuration is prone to overlooking cross-dimensional constraints, such as combining ASIL B-level sensor modules with ASIL D-level high-voltage control modules, or selecting driver modules that do not support the target MCU. Such errors are only exposed during the simulation testing phase, requiring additional time for debugging and increasing development costs.
[0004] Therefore, a new ECU module configuration method is urgently needed to solve the above problems. Summary of the Invention
[0005] In view of this, this application provides an ECU module configuration method, apparatus, electronic device, and storage medium, which can realize automatic configuration of ECU modules and improve the configuration efficiency and accuracy of ECU modules.
[0006] A first aspect of this application provides an ECU module configuration method, comprising: responding to a user's module operation on model design software, obtaining a target feature vector of a target ECU module corresponding to the module operation; wherein the target feature vector is obtained by quantizing multi-dimensional feature parameters of the target ECU module among multiple ECU modules, the elements in the target feature vector having the same dimension, and the multi-dimensional feature parameters including safety risk level, functional domain association, MCU hardware compatibility, communication protocol matching degree, and historical failure rate; determining multiple recommended ECU modules matching the target ECU module among the ECU modules based on the target feature vector and the feature vectors of other ECU modules; configuring the multiple recommended ECU modules and the target ECU module to generate a recommended combination of ECU modules.
[0007] In one possible implementation, the target feature vector includes a security risk level quantification value, a functional domain association quantification value, an MCU hardware compatibility quantification value, a communication protocol matching quantification value, and a historical failure rate quantification value. The target feature vector is obtained through the following methods: quantifying the security risk level to obtain quantification values corresponding to different security risk levels, wherein a higher security risk level corresponds to a smaller quantification value; quantifying the functional domain association to obtain quantification values corresponding to different functional domain associations, wherein a stronger association corresponds to a larger quantification value; quantifying the MCU hardware compatibility according to a preset MCU hardware compatibility processing rule to obtain the MCU hardware compatibility quantification value; quantifying the communication protocol matching according to a preset communication protocol matching rule to obtain the communication protocol matching quantification value; and quantifying the historical failure rate according to a preset historical failure rate processing rule to obtain the historical failure rate quantification value.
[0008] In one possible implementation, after obtaining the target feature vector of the target ECU module corresponding to the module operation, the method further includes: obtaining a target feature weight matrix to characterize the importance of each element in the target feature vector; the step of determining a plurality of recommended ECU modules matching the target ECU module in the ECU modules based on the target feature vector and the feature vectors of other ECU modules includes: determining the recommended ECU modules in the ECU modules based on the target feature vector, the target feature weight matrix, and the feature vectors of other ECU modules.
[0009] In one possible implementation, obtaining the target feature weight matrix used to characterize the importance of each element in the target feature vector includes: constructing a corresponding feature weight matrix for each of the preset multiple application scenarios, wherein the feature weight matrix is used to characterize the importance of each element in the feature vector; determining the target application scenario of the target ECU module, and determining the target feature weight matrix corresponding to the target application scenario from the multiple feature weight matrices.
[0010] In one possible implementation, determining the recommended ECU module among the ECU modules based on the target feature vector, the target feature weight matrix, and the feature vectors of other ECU modules includes: calculating the correlation degree between the target ECU module and other ECU modules according to the following formula: ; ;in, To determine the correlation between target ECU module A and other ECU module B, The scene weights of the i-th type of features in the target feature weight matrix are... Let be the similarity between target ECU module A and other ECU module B in the i-th type of features. Let be the quantized value of the i-th type of feature in the target feature vector of target ECU module A. The quantized value of the i-th type of feature in the feature vector of other ECU module B; the recommended ECU module is determined in the ECU module according to the correlation degree.
[0011] In one possible implementation, if the target feature vector is not configured with the target feature weight matrix, the method further includes: constructing an initial feature weight matrix for the target feature vector; and updating the initial feature weight matrix according to the following formula: ;in, This is the updated initial feature weight matrix. The preset weighting is the standard weighting percentage. The initial feature weight matrix is... For the historical feature vector of the ECU module required by the user, This refers to the historical feature vectors of sample ECU modules of the same type as the target ECU module; The historical configuration weights of sample ECU modules of the same category are defined; n is the number of sample ECU modules of the same category; the updated initial feature weight matrix is used as the target feature weight matrix.
[0012] In one possible implementation, after configuring the multiple recommended ECU modules and the target ECU module to generate a recommended combination of ECU modules, the method further includes: calculating a compatibility score for the recommended combination of ECU modules according to the following formula: ; in, The compatibility score is given. Recommended interface matching degree for the ECU module combination. Recommended communication protocol matching degree for the ECU module combination. Recommended safety risk level fit for the ECU module The hardware resource utilization rate of the recommended combination of the ECU modules is determined; if the compatibility score is detected to be greater than or equal to a preset score, simulation is performed based on the recommended combination of the ECU modules.
[0013] Secondly, embodiments of this application also provide an ECU module configuration device, including: an acquisition module, a determination module, and a generation module; the acquisition module is used to respond to a user's module operation on model design software and acquire a target feature vector of a target ECU module corresponding to the module operation; wherein, the target feature vector is obtained by quantizing the multi-dimensional feature parameters of the target ECU module among multiple ECU modules, the elements in the target feature vector have the same dimension, and the multi-dimensional feature parameters include safety risk level, functional domain correlation, MCU hardware adaptability, communication protocol matching degree, and historical failure rate; the determination module is used to determine multiple recommended ECU modules that match the target ECU module among the ECU modules based on the target feature vector and the feature vectors of other ECU modules; the generation module is used to configure the multiple recommended ECU modules and the target ECU module to generate a recommended combination of ECU modules.
[0014] Thirdly, embodiments of this application also provide an electronic device, the electronic device including a processor and a memory, the memory being used to store instructions, and the processor being used to call the instructions in the memory, causing the electronic device to execute the ECU module configuration method as described in the first aspect.
[0015] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores computer instructions that, when executed on an electronic device, cause the electronic device to perform the ECU module configuration method as described in the first aspect.
[0016] Compared with related technologies, the embodiments of this application have at least the following advantages: By quantifying the multi-dimensional feature parameters of the ECU module to obtain feature vectors, and since the elements in the feature vectors have the same dimension, differences in feature parameters of different dimensions can be judged using a unified numerical value. After the user operates the target ECU module on the model design software, the target feature vector of the target ECU module is obtained. Then, based on the target feature vector and the feature vectors of other ECU modules, multiple recommended ECU modules matching the target ECU module are determined. Finally, the multiple recommended ECU modules and the target ECU module are configured to generate a recommended combination of ECU modules. This method, on the one hand, realizes automatic recommendation and configuration of ECU module combinations, improving the configuration efficiency of ECU modules; on the other hand, since the multi-dimensional feature parameters include at least safety risk level, functional domain correlation, MCU hardware adaptability, communication protocol matching degree, and historical failure rate, these feature parameters cover the full-scenario requirements of automotive electronics, thereby solving the problem of general algorithms "only matching functions and ignoring safety / hardware constraints," and improving the accuracy of ECU module configuration. Furthermore, this application avoids issues such as "functional compatibility but wasted hardware resources" and "interface compatibility but runtime conflicts" caused by different engineers' differing judgment standards on ECU module performance redundancy and safety level adaptability, effectively avoiding additional simulation tests and reducing development costs.
[0017] The technical effects achieved by the second, third, and fourth aspects mentioned above are similar to those achieved by the corresponding technical means in the first aspect, and will not be repeated here. Attached Figure Description
[0018] Figure 1 A flowchart illustrating the steps of an ECU module configuration method provided in an embodiment of this application; Figure 2 A flowchart illustrating another step of the ECU module configuration method provided in one embodiment of this application; Figure 3A functional block diagram of an ECU module configuration device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0019] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.
[0020] The following description sets forth many specific details to provide a full understanding of this application. The described embodiments are only some, not all, of the embodiments of this application.
[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.
[0022] It should be further noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0023] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.
[0024] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.
[0025] For ease of understanding, some concepts related to the embodiments of this application are illustrated and explained by way of example.
[0026] Simulink is a graphical simulation tool in MATLAB, specifically designed for modeling, simulating, and analyzing dynamic systems. It allows users to intuitively build system models by dragging and dropping modules and connecting circuits, making it particularly suitable for handling continuous, discrete, or hybrid systems.
[0027] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating one embodiment of the ECU module configuration method provided in this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements.
[0028] It should be noted that the ECU module configuration method of this application embodiment can be applied to vehicle architecture simulation scenarios. The executing entity can be an ECU module configuration device. For example, when performing vehicle architecture simulation, the ECU module configuration device can automatically generate recommended combinations of ECU modules in Simulink, thereby achieving simulation of the target vehicle architecture. Of course, the ECU module configuration method can also be applied to other scenarios requiring vehicle architecture simulation, and this application does not specifically limit its application in this regard.
[0029] The specific process of this embodiment is as follows: Figure 1 As shown, it includes the following steps: S101 responds to the user's module operation on the model design software and obtains the target feature vector of the target ECU module corresponding to the module operation.
[0030] Specifically, the target feature vector is obtained by quantifying the multi-dimensional feature parameters of the target ECU module in multiple ECU modules. The elements in the target feature vector have the same dimension. The multi-dimensional feature parameters include safety risk level, functional domain correlation, MCU hardware compatibility, communication protocol matching degree, and historical failure rate.
[0031] In some embodiments, multi-dimensional feature parameters may also include other types. This embodiment does not specifically limit the types of feature parameters included in multi-dimensional feature parameters.
[0032] In some embodiments, the target feature vector includes a security risk level quantification value, a functional domain association quantification value, an MCU hardware compatibility quantification value, a communication protocol matching quantification value, and a historical failure rate quantification value. The target feature vector is obtained through the following methods: quantifying the security risk level to obtain security risk level quantification values corresponding to different security risk levels, wherein the higher the security risk level, the larger the corresponding security risk level quantification value; quantifying the functional domain association to obtain functional domain association quantification values corresponding to different functional domain associations, wherein the stronger the association of the functional domain association, the larger the corresponding functional domain association quantification value; quantifying the MCU hardware compatibility according to a preset MCU hardware compatibility processing rule to obtain an MCU hardware compatibility quantification value; quantifying the communication protocol matching degree according to a preset communication protocol matching degree processing rule to obtain a communication protocol matching quantification value; and quantifying the historical failure rate according to a preset historical failure rate processing rule to obtain a historical failure rate quantification value.
[0033] To facilitate understanding, the following example illustrates how the target feature vector is obtained in this embodiment: 1. Using an ordered numerical mapping method, the safety level is mapped to a quantified value of 1-5 according to the increasing risk. The formula is as follows: ;in, As a quantitative value for the safety risk level, , , , as well as All are classified as safety risk levels.
[0034] Understandably, this formula transforms qualitative security risk levels into calculable indicators through numerical conversion. ASIL D (the highest security level) corresponds to the highest quantifiable value of 5, ensuring that the proportion of security weight in the calculation meets actual needs.
[0035] 2. Construct a functional domain association matrix based on industry rules. If module A and module B have a mandatory association (such as ACC and torque control), the association coefficient is 1; if there is an optional association, it is 0.5; if there is no association, it is 0. The formula is: ;in, Quantify the functional domain association values between ECU module A and ECU module B. , as well as All of these are functional domain relationships.
[0036] 3. The quantified value of MCU hardware adaptation is calculated using a two-factor approach: "architecture matching degree + resource satisfaction degree". The formula is as follows: ;in, To adapt quantization values for MCU hardware, For the architecture matching value of the ECU module, To meet the computing power / storage requirements of the ECU module, This represents the upper limit of the target MCU's computing power / storage.
[0037] It is understood that the architecture matching value in this embodiment is the matching value between the ECU module and the target architecture to be simulated by the user. If the ECU module matches the target architecture, then... The value is 1; if there is no match, then The value is 0.
[0038] It is worth noting that in this embodiment, the architecture matching value is the core factor (with a weight of 0.6), and the resource satisfaction is the minimum value of "requirement / upper limit" (to ensure that it does not exceed the hardware capability), so as to avoid the module from running abnormally due to insufficient resources.
[0039] In some embodiments, the weight values 0.6 and 0.4 in the above formula can be modified according to actual needs. This embodiment does not impose specific limitations on this.
[0040] 4. Quantify the communication protocol matching degree according to the following formula: ;in, To match metric values for communication protocols, To support the baud rate of the ECU module, Set the preset baud rate for the bus.
[0041] 5. Quantify the historical failure rate according to the following formula: ;in, Quantified value of historical failure rate This refers to the historical number of faults of the ECU module. This represents the total number of times the ECU module has been configured.
[0042] It should also be noted that this embodiment will also construct a multi-dimensional feature library for the ECU module. After calculating the feature vector of each ECU module, the feature vector will be stored in the multi-dimensional feature library.
[0043] It is worth noting that the multi-dimensional feature library in this embodiment supports user-defined supplementary rules. For example, car manufacturers can add exclusive rules such as "a certain model of MCU will be preferentially matched with the XX brand driver module".
[0044] In some embodiments, the model design software can be Simulink, and the user's module operation on Simulink can be a drag-and-drop operation or a click operation on the target ECU module. This embodiment does not specifically limit the type of module operation.
[0045] S102, based on the target feature vector and the feature vectors of other ECU modules, determine multiple recommended ECU modules that match the target ECU module.
[0046] In some embodiments, after obtaining the target feature vector of the target ECU module corresponding to the module operation, the method further includes: obtaining a target feature weight matrix for characterizing the importance of each element in the target feature vector; and determining a plurality of recommended ECU modules that match the target ECU module in the ECU module based on the target feature vector and the feature vectors of other ECU modules, including: determining recommended ECU modules in the ECU module based on the target feature vector, the target feature weight matrix, and the feature vectors of other ECU modules.
[0047] Specifically, based on the target feature vector, the target feature weight matrix, and the feature vectors of other ECU modules, the recommended ECU module is determined among the ECU modules, including: calculating the correlation between the target ECU module and other ECU modules according to the following formula: ; ; in, To determine the correlation between target ECU module A and other ECU module B, The scene weights of the i-th type of feature in the target feature weight matrix. Let be the similarity between target ECU module A and other ECU module B in the i-th type of features. Let be the quantized value of the i-th type of feature in the target feature vector of target ECU module A. This is the quantized value of the i-th type of feature in the feature vector of other ECU module B.
[0048] It is worth noting that cosine similarity is used to quantify the degree of matching between two modules in a single feature dimension. After being weighted by the scene weight, the comprehensive correlation is obtained, ensuring that the recommended ECU module not only meets the functional requirements but also adapts to the scene priority.
[0049] It should also be noted that this embodiment can calculate the correlation between the target ECU module A and all other ECU modules B in the database, and can also calculate the correlation between the target ECU module A and ECU modules B in the database that have feature weight matrices, thereby reducing the amount of computation.
[0050] In some embodiments, the top N ECU modules are sorted from high to low in terms of relevance and are used as recommended ECU modules (N is greater than 1). The relevance score and core matching features of each recommended ECU module are labeled.
[0051] It is understood that this embodiment does not impose a specific limit on the number of recommended ECU modules, which can be set according to actual needs.
[0052] In some embodiments, obtaining a target feature weight matrix for characterizing the importance of each element in the target feature vector includes: constructing a corresponding feature weight matrix for each of a set of multiple application scenarios, wherein the feature weight matrix is used to characterize the importance of each element in the feature vector; determining the target application scenario of the target ECU module, and determining the target feature weight matrix corresponding to the target application scenario from the multiple feature weight matrices.
[0053] To facilitate understanding, the following provides a detailed explanation of how this embodiment constructs the corresponding feature weight matrix for each application scenario: 1. Application scenario is mass production verification scenario: Prioritize security and hardware stability, with security risk level of 35%, MCU hardware compatibility weight of 25%, communication protocol matching weight of 20%, functional domain association weight of 15%, and historical failure rate weight of 5%.
[0054] 2. Application scenario: R&D and debugging scenario. Emphasis is placed on functional expandability, with the following weightings: functional domain correlation (50%), communication protocol compatibility (20%), MCU hardware adaptability (15%), security risk level (10%), and historical failure rate (5%). 3. Application scenario is teaching and training scenario: simplify safety constraints, functional domain correlation weight 60%, MCU hardware compatibility weight 20%, communication protocol matching weight 15%, safety risk level weight 5%, historical failure rate weight 0%.
[0055] By allocating feature weights differently based on scenarios such as R&D and mass production, the matching degree between the recommendation results and actual needs is improved by 60% compared with fixed weight algorithms, avoiding the defects of "one-size-fits-all" recommendations.
[0056] S103 configures multiple recommended ECU modules and target ECU modules to generate a recommended combination of ECU modules.
[0057] In some embodiments, after configuring multiple recommended ECU modules and target ECU modules to generate a recommended combination of ECU modules, the method further includes: calculating a compatibility score for the recommended combination of ECU modules according to the following formula: ; in, For compatibility score, Recommended interface compatibility for ECU modules. Recommended communication protocol compatibility for ECU modules. Recommended safety risk level fit for ECU module combination The hardware resource utilization rate of the recommended combination of ECU modules; if the compatibility score is greater than or equal to the preset score, simulation is performed based on the recommended combination of ECU modules.
[0058] Specifically, when a compatibility score is detected to be greater than or equal to a preset score, the Simulink API is automatically invoked to generate a communication topology, configure bus parameters (message ID, period), and synchronize them to the AUTOSAR Dictionary. By embedding compatibility verification into the recommendation process, the accuracy and reliability of recommended ECU module combinations can be further improved, thereby enhancing the user experience.
[0059] In some embodiments, the interface matching degree of the recommended ECU module combination is the matching degree between the interface of the recommended ECU module combination and the current data format of Simulink. If there is a match, the value is 1; otherwise, the value is 0. The communication protocol matching degree of the recommended ECU module combination can be the average of the communication protocol matching degrees between each recommended ECU module in the recommended ECU module combination and the target ECU module. The calculation methods for security risk level adaptability and hardware resource utilization are similar to those for communication protocol matching degree, and will not be elaborated here.
[0060] Compared with related technologies, the embodiments of this application have at least the following advantages: By quantifying the multi-dimensional feature parameters of the ECU module to obtain feature vectors, and since the elements in the feature vectors have the same dimension, differences in feature parameters of different dimensions can be judged using a unified numerical value. After the user operates on the target ECU module in Simulink, the target feature vector of the target ECU module is obtained. Then, based on the target feature vector and the feature vectors of other ECU modules, multiple recommended ECU modules matching the target ECU module are determined. Finally, the multiple recommended ECU modules and the target ECU module are configured to generate a recommended combination of ECU modules. This method, on the one hand, realizes automatic recommendation and configuration of ECU module combinations, improving the configuration efficiency of ECU modules; on the other hand, since the multi-dimensional feature parameters include at least safety risk level, functional domain correlation, MCU hardware adaptability, communication protocol matching degree, and historical failure rate, these feature parameters cover the full-scenario requirements of automotive electronics, thereby solving the problem of general algorithms "only matching functions and ignoring safety / hardware constraints," and improving the accuracy of ECU module configuration. Furthermore, this application avoids issues such as "functional compatibility but wasted hardware resources" and "interface compatibility but runtime conflicts" caused by different engineers' differing judgment standards on ECU module performance redundancy and safety level adaptability, effectively avoiding additional simulation tests and reducing development costs.
[0061] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the steps of one embodiment of the ECU module configuration method of this application. Depending on different requirements, the order of the steps in this flowchart can be changed, and some steps can be omitted. This ECU module configuration method can be applied to the aforementioned ECU module configuration device, but is not limited thereto, and the embodiments of this application do not limit it in this regard.
[0062] This embodiment is a further improvement on the aforementioned embodiment. The main improvement is that, in this embodiment, even when the target feature vector is not configured with a target feature weight matrix, a feature weight matrix is still configured for the target feature vector. This approach effectively solves the cold start problem and further improves the reliability of the ECU module configuration method.
[0063] The specific process of this embodiment is as follows: Figure 2 As shown, it includes the following steps: S201 responds to the user's module operation on the model design software and obtains the target feature vector of the target ECU module corresponding to the module operation.
[0064] S202, Construct the initial feature weight matrix of the target feature vector.
[0065] In some embodiments, an initial feature weight matrix can be generated based on industry standard libraries such as ISO 26262 and AUTOSAR. Alternatively, if no target feature weight matrix is configured for the target feature vector, the initial feature weight matrix of the target feature vector can be assigned a preset value.
[0066] S203, update the initial feature weight matrix, and use the updated initial feature weight matrix as the target feature weight matrix.
[0067] Specifically, the initial feature weight matrix is updated according to the following formula: ;in, This is the updated initial feature weight matrix. The preset weighting is the standard weighting percentage. The initial feature weight matrix, For the historical feature vector of the ECU module required by the user, The historical feature vector of a sample ECU module of the same type as the target ECU module; The historical configuration weights of sample ECU modules of the same category; n is the number of sample ECU modules of the same category.
[0068] It is worth noting that by combining industry standards and data from the same category to generate initial weights, the problem of "no data to rely on" in the development of new models and new modules is solved, which increases the initial compatibility rate of ECU modules from 50% to over 85%.
[0069] S204. Based on the target feature vector, the target feature weight matrix, and the feature vectors of other ECU modules, determine multiple recommended ECU modules among the ECU modules.
[0070] S205 configures multiple recommended ECU modules and target ECU modules to generate a recommended combination of ECU modules.
[0071] Compared with related technologies, the embodiments of this application have at least the following advantages: By quantifying the multi-dimensional feature parameters of the ECU module to obtain feature vectors, and since the elements in the feature vectors have the same dimension, differences in feature parameters of different dimensions can be judged using a unified numerical value. After the user operates on the target ECU module in Simulink, the target feature vector of the target ECU module is obtained. Then, based on the target feature vector and the feature vectors of other ECU modules, multiple recommended ECU modules matching the target ECU module are determined. Finally, the multiple recommended ECU modules and the target ECU module are configured to generate a recommended combination of ECU modules. This method, on the one hand, realizes automatic recommendation and configuration of ECU module combinations, improving the configuration efficiency of ECU modules; on the other hand, since the multi-dimensional feature parameters include at least safety risk level, functional domain correlation, MCU hardware adaptability, communication protocol matching degree, and historical failure rate, these feature parameters cover the full-scenario requirements of automotive electronics, thereby solving the problem of general algorithms "only matching functions and ignoring safety / hardware constraints," and improving the accuracy of ECU module configuration. Furthermore, this application avoids issues such as "functional compatibility but wasted hardware resources" and "interface compatibility but runtime conflicts" caused by different engineers' differing judgment standards on ECU module performance redundancy and safety level adaptability, effectively avoiding additional simulation tests and reducing development costs.
[0072] Based on the same idea as the ECU module configuration method in the above embodiments, this application also provides an ECU module configuration device, which can be used to execute the above-described ECU module configuration method. For ease of explanation, the structural schematic diagram of the ECU module configuration device embodiment only shows the parts related to the embodiments of this application. Those skilled in the art will understand that the illustrated structure does not constitute a limitation on the device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0073] like Figure 3As shown, the ECU module configuration device 30 includes an acquisition module 301, a determination module 302, and a generation module 303. In some embodiments, the above modules can be programmable software instructions stored in memory and executable by a processor. It is understood that in other embodiments, the above modules can also be program instructions or firmware embedded in the processor.
[0074] The acquisition module 301 is used to respond to the user's module operation on the model design software and acquire the target feature vector of the target ECU module corresponding to the module operation; wherein, the target feature vector is obtained by quantizing the multi-dimensional feature parameters of the target ECU module among multiple ECU modules, and the elements in the target feature vector have the same dimension, and the multi-dimensional feature parameters include safety risk level, functional domain correlation, MCU hardware adaptability, communication protocol matching degree and historical failure rate; The determining module 302 is used to determine, based on the target feature vector and the feature vectors of other ECU modules, a plurality of recommended ECU modules that match the target ECU module among the ECU modules; The generation module 303 is used to configure multiple recommended ECU modules and the target ECU module to generate a recommended combination of ECU modules.
[0075] The ECU module configuration device 30 provided in the above embodiments can implement the technical solutions described in the above ECU module configuration method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above ECU module configuration method embodiments, and will not be repeated here.
[0076] Please refer to Figure 4 , Figure 4 This is a schematic diagram of an embodiment of the electronic device of this application. In this embodiment of the invention, the electronic device 400 includes a processor 401, a memory 402, and a display 403. Figure 4 Only some components of the electronic device 400 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.
[0077] In some embodiments, processor 401 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 402 or process data, such as the ECU module configuration method of the present invention.
[0078] In some embodiments, processor 401 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 401 may be local or remote. In some embodiments, processor 401 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, or any combination thereof.
[0079] In some embodiments, memory 402 may be an internal storage unit of electronic device 400, such as a hard disk or memory of electronic device 400. In other embodiments, memory 402 may also be an external storage device of electronic device 400, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 400.
[0080] Furthermore, the memory 402 may include both internal storage units of the electronic device 400 and external storage devices. The memory 402 is used to store application software and various types of data installed on the electronic device 400.
[0081] In some embodiments, display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 403 is used to display information from electronic device 400 and to display visual user applications. Components 401-403 of electronic device 400 communicate with each other via a system bus.
[0082] In one embodiment, when the processor 401 executes the ECU module configuration program in the memory 402, the following steps can be implemented: In response to user module operations on the model design software, a target feature vector of the target ECU module corresponding to the module operation is obtained; wherein, the target feature vector is obtained by quantizing the multi-dimensional feature parameters of the target ECU module among multiple ECU modules, and the elements in the target feature vector have the same dimension, the multi-dimensional feature parameters include safety risk level, functional domain correlation, MCU hardware adaptability, communication protocol matching degree and historical failure rate. Based on the target feature vector and the feature vectors of other ECU modules, a plurality of recommended ECU modules that match the target ECU module are determined among the ECU modules; Configure multiple recommended ECU modules and the target ECU module to generate a recommended combination of ECU modules.
[0083] It should be understood that when the processor 401 executes the ECU module configuration program in the memory 402, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.
[0084] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 400 mentioned. Electronic device 400 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 400 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).
[0085] Accordingly, this application also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, it can implement the steps or functions in the ECU module configuration method provided in the above-described method embodiments.
[0086] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.
[0087] The ECU module configuration method, apparatus, electronic device, and computer-readable storage medium provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. An ECU module configuration method characterized by, include: In response to user module operations on the model design software, a target feature vector of the target ECU module corresponding to the module operation is obtained; wherein, the target feature vector is obtained by quantizing the multi-dimensional feature parameters of the target ECU module among multiple ECU modules, and the elements in the target feature vector have the same dimension, the multi-dimensional feature parameters include safety risk level, functional domain correlation, MCU hardware adaptability, communication protocol matching degree and historical failure rate. Based on the target feature vector and the feature vectors of other ECU modules among the plurality of ECU modules, a plurality of recommended ECU modules that match the target ECU module are determined from among the other ECU modules; Configure multiple recommended ECU modules and the target ECU module to generate a recommended combination of ECU modules.
2. The ECU module configuration method according to claim 1, characterized by, The target feature vector includes a security risk level quantification value, a functional domain association quantification value, an MCU hardware adaptation quantification value, a communication protocol matching quantification value, and a historical failure rate quantification value. The target feature vector is obtained in the following way: The security risk levels are quantified to obtain quantified values of security risk levels corresponding to different security risk levels, wherein the higher the security risk level, the larger the corresponding quantified value of the security risk level; The functional domain association relationships are quantified to obtain quantified values of functional domain association relationships corresponding to different functional domain association relationships. The stronger the association of the functional domain association relationships, the larger the corresponding quantified value of the functional domain association relationships. According to the preset MCU hardware compatibility processing rules, the MCU hardware compatibility is quantified to obtain the quantified value of the MCU hardware compatibility. According to the preset communication protocol matching degree processing rules, the communication protocol matching degree is quantified to obtain the communication protocol matching degree quantification value; According to the preset historical failure rate processing rules, the historical failure rate is quantified to obtain the quantified value of the historical failure rate.
3. The ECU module configuration method of claim 1, wherein, After obtaining the target feature vector of the target ECU module corresponding to the module operation, the method further includes: Obtain the target feature weight matrix used to characterize the importance of each element in the target feature vector; The step of determining, based on the target feature vector and the feature vectors of other ECU modules, a plurality of recommended ECU modules matching the target ECU module are identified from among the ECU modules, including: The recommended ECU module is determined from the ECU modules based on the target feature vector, the target feature weight matrix, and the feature vectors of other ECU modules.
4. The ECU module configuration method according to claim 3, characterized by, The step of obtaining the target feature weight matrix used to characterize the importance of each element in the target feature vector includes: Based on multiple preset application scenarios, a corresponding feature weight matrix is constructed for each application scenario, wherein the feature weight matrix is used to characterize the importance of each element in the feature vector; The target application scenario of the target ECU module is determined, and the target feature weight matrix corresponding to the target application scenario is determined from multiple feature weight matrices.
5. The ECU module configuration method of claim 3, wherein, The step of determining the recommended ECU module among the ECU modules based on the target feature vector, the target feature weight matrix, and the feature vectors of other ECU modules includes: The correlation between the target ECU module and other ECU modules is calculated using the following formula: ； ； wherein, is the correlation degree of the target ECU module A and other ECU module B, is the scene weight of the i-th feature in the target feature weight matrix, is the similarity of the target ECU module A and other ECU module B in the i-th feature, is the quantized value of the i-th feature in the target feature vector of the target ECU module A, is the quantized value of the i-th feature in the feature vector of the other ECU module B; The recommended ECU module is determined in the ECU module based on the correlation.
6. The ECU module configuration method of claim 3, wherein, If the target feature vector is not configured with the target feature weight matrix, the method further includes: Construct the initial feature weight matrix of the target feature vector; The initial feature weight matrix is updated according to the following formula: ; wherein, is an updated initial feature weight matrix, is a preset standard weight proportion, is the initial feature weight matrix, is a historical feature vector of a user demand ECU module, is a historical feature vector of a sample ECU module of the same category as the target ECU module; is a historical configuration weight of the sample ECU module of the same category; n is the number of samples of the sample ECU module of the same category. The updated initial feature weight matrix is used as the target feature weight matrix.
7. The ECU module configuration method according to any one of claims 1 to 6, characterized by, After configuring the multiple recommended ECU modules and the target ECU module to generate a recommended combination of ECU modules, the method further includes: The compatibility score of the recommended combination of ECU modules is calculated using the following formula: ； wherein, is the compatibility score, is the interface matching degree of the ECU module recommended combination, is the communication protocol matching degree of the ECU module recommended combination, is the security risk level adaptation degree of the ECU module recommended combination, is the hardware resource occupation rate of the ECU module recommended combination; If the compatibility score is detected to be greater than or equal to a preset score, simulation is performed according to the combination recommended by the ECU module.
8. An ECU module configuration device characterized by comprising: include: Acquire module, determine module, and generate module; The acquisition module is used to respond to the user's module operation on the model design software and acquire the target feature vector of the target ECU module corresponding to the module operation; wherein, the target feature vector is obtained by quantizing the multi-dimensional feature parameters of the target ECU module among multiple ECU modules, and the elements in the target feature vector have the same dimension, and the multi-dimensional feature parameters include safety risk level, functional domain correlation, MCU hardware adaptability, communication protocol matching degree and historical failure rate. The determining module is used to determine, based on the target feature vector and the feature vectors of other ECU modules among the plurality of ECU modules, a plurality of recommended ECU modules that match the target ECU module; The generation module is used to configure multiple recommended ECU modules and the target ECU module to generate a recommended combination of ECU modules.
9. An electronic device comprising a processor and a memory, wherein the electronic device is configured to: The memory is used to store instructions, and the processor is used to call the instructions in the memory to cause the electronic device to execute the ECU module configuration method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on an electronic device, cause the electronic device to perform the ECU module configuration method as described in any one of claims 1 to 7.