Cloud-based vehicle development quality management system
By integrating and analyzing automotive R&D quality data through a cloud-based data processing platform and an AI-powered bidirectional correlation analysis module, the system solves the problem of time-consuming and labor-intensive manual analysis in existing systems, achieving efficient quality management and cost reduction, and improving R&D efficiency and market competitiveness.
Patent Information
- Application Number
- CN202610939754.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-26
- Publication Date
- 2026-11-03
AI Technical Summary
Existing automotive R&D quality management systems rely on human experience and simple data analysis tools, resulting in time-consuming and inaccurate quality problem analysis, making it difficult to improve R&D efficiency and reduce costs.
The system integrates multi-source automotive R&D quality data using a cloud-based data processing platform. Through AI bidirectional correlation analysis and collaborative quality management modules, it achieves efficient data integration and intelligent cross-module linkage. It utilizes deep learning and dual machine learning algorithms for feature extraction and correlation analysis to generate quality-related data and automate its management.
It has improved the efficiency of automotive R&D, reduced R&D costs and quality risks, enhanced market competitiveness, and enabled accurate and rapid data mining and cross-domain collaboration.
Smart Images
Figure CN123032201A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data management technology, and in particular to a cloud-based automotive R&D quality management system. Background Technology
[0002] As the automotive industry rapidly transforms towards intelligence, connectivity, and electrification, the complexity of automotive R&D technology continues to increase, and the quality-related data generated throughout the entire R&D process is showing an explosive growth trend.
[0003] In related technologies, current automotive R&D quality management systems mainly rely on human experience and simple data analysis tools for analyzing and judging quality problems, such as basic office data analysis tools, simple statistical analysis tools, and document data management tools.
[0004] However, the above solutions often require a lot of time and manpower for investigation, and the accuracy is not high, making it difficult to improve the R&D progress and reduce R&D costs, and urgently need to be improved. Summary of the Invention
[0005] This application provides a cloud-based automotive R&D quality management system, which can integrate multi-source automotive R&D quality-related data through the acquisition unit of the cloud data processing platform, and then accurately distribute the data to the AI bidirectional correlation analysis module and the collaborative quality management module through the transmission unit. This enables efficient integration of data, intelligent cross-module linkage and collaborative control, effectively breaking down data silos, thereby improving automotive R&D efficiency, reducing R&D costs and quality risks, and accelerating the development of the automotive industry.
[0006] The first aspect of this application provides a cloud-based automotive R&D quality management system, including: a cloud-based data processing platform, an AI bidirectional correlation analysis module, and a collaborative quality management module, wherein the cloud-based data processing platform is connected to the AI bidirectional correlation analysis module and the collaborative quality management module, respectively.
[0007] The cloud-based data processing platform includes a data acquisition unit and a data transmission unit. The data acquisition unit acquires vehicle design data, quality data, and management data. The data transmission unit sends the design data, quality data, and management data to the AI bidirectional correlation analysis module and the collaborative quality management module, respectively. The AI bidirectional correlation analysis module includes a feature extraction unit and a correlation analysis unit. The feature extraction unit extracts features from the design data, quality data, and management data to generate vehicle feature data. The correlation analysis unit analyzes the vehicle feature data to generate vehicle quality correlation data and sends the quality correlation data to the cloud-based data processing platform. The collaborative quality management module includes a collaborative management unit that generates a quality problem report for the vehicle based on the quality correlation data.
[0008] In one embodiment of this application, the data acquisition unit is further configured to: preprocess the design data, the quality data, and the management data respectively, wherein the preprocessing includes one or more of data cleaning, format conversion, deduplication, normalization, and annotation.
[0009] In one embodiment of this application, the cloud data processing platform further includes a data storage unit, wherein the data storage unit is configured to: classify the design data, the quality data, and the management data respectively to obtain structured data and unstructured data; and store the structured data and the unstructured data using a distributed storage architecture.
[0010] In one embodiment of this application, the cloud data processing platform further includes a data analysis unit, wherein the data analysis unit is configured to: analyze the quality-related data to obtain analysis results; and, in response to the analysis results meeting preset quality problem occurrence conditions, generate early warning information corresponding to the analysis results, and send the early warning information to the target terminal through the data transmission unit.
[0011] In one embodiment of this application, the cloud data processing platform further includes a data service unit, which provides multiple data service interfaces, wherein the data service interfaces are used to retrieve data from the cloud data processing platform.
[0012] In one embodiment of this application, the feature extraction unit is specifically used to: construct a bidirectional correlation analysis model based on a deep learning framework; and extract features from the design data, the quality data, and the management data through the bidirectional correlation analysis model to generate the vehicle feature data.
[0013] In one embodiment of this application, the vehicle feature data includes design parameter thresholds, quality defect levels, and after-sales fault types. The correlation analysis unit is specifically used for: constructing a forward correlation model and a reverse correlation model based on dual machine learning algorithms, wherein the forward correlation model and the reverse correlation model are mutually correlated; analyzing the design parameter thresholds, the quality defect levels, and the after-sales fault types through the forward correlation model to obtain problem impact weights; analyzing the design parameter thresholds, the quality defect levels, and the after-sales fault types through the reverse correlation model to obtain problem correlation weights; and generating the quality correlation data based on the problem impact weights and the problem correlation weights, wherein the quality correlation data includes quality correlation nodes.
[0014] In one embodiment of this application, the collaborative quality management module further includes a quality management unit, which has one or more of the following functions: quality problem management, design review management, recurrence prevention management, system audit problem management, zeroing management, and quality TFT management.
[0015] In one embodiment of this application, the collaborative management unit is specifically used to: obtain a preset problem threshold and a preset urgency level, and generate a quality problem order for the vehicle based on the quality-related data, the preset problem threshold, and the preset urgency level; and send the quality problem order to the cloud data processing platform so that the quality problem order can be sent to the target terminal through the data transmission unit.
[0016] A second aspect of this application provides an electronic device including a cloud-based automotive R&D quality management system as described in the above embodiments.
[0017] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0018] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a block diagram of a cloud-based automotive R&D quality management system according to an embodiment of this application; Figure 2 This is a block diagram of a cloud-based automotive R&D quality management system according to a specific embodiment of this application; Figure 3 This is an overall architecture diagram of a cloud-based automotive R&D quality management system provided according to a specific embodiment of this application; Figure 4This is a flowchart illustrating the workflow of a cloud-based data processing platform according to a specific embodiment of this application. Detailed Implementation
[0019] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0020] The following describes an embodiment of the cloud-based automotive R&D quality management system with reference to the accompanying drawings. Addressing the problem that current automotive R&D quality management systems often require significant time and manpower for quality problem analysis and judgment, and suffer from low accuracy, making it difficult to improve R&D progress and reduce costs, this application provides a cloud-based automotive R&D quality management system. In this system, scattered data can be integrated through a cloud platform, solving the problem of difficult interoperability of multi-source data; AI bidirectional correlation models replace manual analysis, accurately and quickly uncovering data correlations and reducing manpower consumption; and cloud-based collaborative functions enable efficient cross-domain collaboration and automatic task allocation for closed-loop management, thereby effectively improving the efficiency of automotive R&D quality control, accelerating progress, reducing costs, and enhancing market competitiveness.
[0021] Figure 1 This is a schematic diagram of the structure of the cloud-based automotive R&D quality management system according to an embodiment of this application.
[0022] like Figure 1 As shown, the cloud-based automotive R&D quality management system 10 includes: a cloud data processing platform 100, an AI bidirectional correlation analysis module 200, and a collaborative quality management module 300. The cloud data processing platform 100 is connected to the AI bidirectional correlation analysis module 200 and the collaborative quality management module 300, respectively.
[0023] The cloud data processing platform 100 includes a data acquisition unit 101 and a data transmission unit 102. The data acquisition unit 101 is used to acquire the vehicle's design data, quality data, and management data. The data transmission unit 102 is used to send the design data, quality data, and management data to the AI bidirectional correlation analysis module 200 and the collaborative quality management module 300, respectively.
[0024] Specifically, the data acquisition unit 101 can acquire various types of data, such as automotive design data, quality data, and management data (after-sales data), from automotive design department systems, quality management department systems, and sales department systems. Furthermore, it can use multi-interface adaptation technology to adapt data of different formats and storage methods (such as structured test reports, unstructured CAD drawings, etc.), and ensure the timeliness and integrity of data through timed acquisition and real-time triggered acquisition.
[0025] Furthermore, in one embodiment of this application, the data acquisition unit 101 is also used to: preprocess the design data, quality data and management data respectively, wherein the preprocessing includes one or more of data cleaning, format conversion, deduplication, normalization and annotation, which are not specifically limited here.
[0026] Specifically, after collecting various types of data, the collected data can be further preprocessed to improve data quality.
[0027] Data cleaning can include removing null values, outliers, and filler values. This means removing null fields, abnormally deviating values, and invalid redundant information from the collected data, and properly filling in and correcting data with missing key fields, as well as removing invalid and dirty data.
[0028] Format conversion can include unifying date, number, and unit formats, that is, standardizing and unifying the data formats output by different business systems, such as date formats, numerical precision, units of measurement, and text encoding, to eliminate differences in data formats from multiple sources.
[0029] When performing data deduplication, duplicate entries, duplicate ledgers and duplicate file information can be compared to automatically filter out duplicate data from the same source, thereby reducing data storage redundancy.
[0030] When performing data normalization, dimensionless unified conversion can be performed on business indicator data of different dimensions and magnitudes to adapt to subsequent intelligent analysis and calculation standards.
[0031] When labeling data, business tags, scenario tags, grade tags and classification identifiers can be matched to various types of data according to the business rules of R&D quality, so as to clarify the business dimension and application scenario to which the data belongs.
[0032] This application demonstrates that the data acquisition unit synchronously completes data acquisition and pre-processing, enabling initial quality optimization at the data source. This eliminates the need for subsequent platform rework, effectively improving the overall data processing efficiency in the cloud and ensuring the regularity, consistency, and usability of the data sent to the subsequent analysis and management modules.
[0033] Furthermore, the data transmission unit 102 can, through the constructed bidirectional data transmission channel, realize the internal data flow and scheduling of the cloud data processing platform on the one hand, and transmit the data results of the cloud data processing platform to the collaborative quality management and AI bidirectional correlation analysis module on the other hand. The transmission can adopt technologies such as SSL encryption, data compression and flow control to ensure the security, real-time performance and stability of data transmission.
[0034] Furthermore, in one embodiment of this application, such as Figure 2 As shown, the cloud data processing platform 100 also includes a data storage unit 103, which is used to: classify design data, quality data and management data respectively to obtain structured data and unstructured data; and store structured data and unstructured data using a distributed storage architecture.
[0035] Specifically, the data storage unit 103 can be used to standardize and centrally store and manage various automotive R&D-related data after they have been collected by the data acquisition unit and pre-processed. This system adopts a cloud-based distributed storage architecture, which can adapt to the needs of large-capacity storage and efficient retrieval of massive heterogeneous data.
[0036] During storage, data can be categorized and partitioned according to its format. Structured and organized data such as quality management ledgers, testing indicators, and process ledgers can be stored in dedicated areas in an orderly manner. At the same time, unstructured file data such as CAD design drawings, R&D plan documents, and experimental image data can be stored separately. This achieves physical partitioning and logically unified management of different types of data. Furthermore, a globally unified data indexing system can be built to configure standardized retrieval indexes for all inbound data. This supports rapid retrieval and location based on multiple dimensions such as data type, business department, R&D project, time node, and data purpose, significantly improving the efficiency of data retrieval and query.
[0037] In addition, a comprehensive data security system can be established, a routine and regular automatic data backup plan can be formulated, a fixed backup cycle can be set to complete full or incremental data backup, and a data emergency recovery mechanism for abnormal scenarios can be built simultaneously. In the event of unexpected situations such as storage failure, accidental deletion, or network anomalies, data can be quickly restored and repaired. From both architectural and institutional perspectives, the loss or damage of core R&D data can be prevented, and the long-term safe retention and stable availability of vehicle R&D quality-related data can be ensured.
[0038] Furthermore, in one embodiment of this application, such as Figure 2 As shown, the cloud data processing platform 100 also includes a data analysis unit 104, which is used to: analyze quality-related data to obtain analysis results; and generate early warning information corresponding to the analysis results in response to the analysis results meeting the preset quality problem occurrence conditions, and send the early warning information to the target terminal through the data transmission unit.
[0039] Specifically, the data analysis unit 104 can rely on the full amount of R&D quality data that has been systematically stored within the platform to actively call the data correlation analysis results of the three types of data (design, quality, and management) output by the AI bidirectional correlation analysis module 200, and deeply explore the inherent causal relationship between design elements and quality defects.
[0040] For example, the data analysis unit 104 can combine multi-dimensional information such as vehicle development parameters, historical fault samples, and actual quality inspection data to accurately calculate the probability and risk level of various quality hazards and faults in the subsequent mass production and assembly stages and actual use scenarios in the end market for products from the same batch of R&D. By comparing the compliance thresholds and risk thresholds of various design parameters in real time, once it identifies that a certain structural parameter, process parameter, material selection parameter, or other design-related parameter deviates from the standard range and is determined to be highly likely to induce various quality faults and pose a high quality risk, it automatically triggers a risk assessment mechanism and immediately generates standardized quality risk warning information. The warning information can clearly indicate the source of risk, the design parameters involved, the potential fault type, and the scope of risk impact, and is simultaneously pushed to the corresponding management port. This allows R&D personnel to optimize design schemes and adjust R&D indicators in advance, avoiding the generation of batch quality problems from the source, and realizing the pre-judgment and proactive control of R&D quality risks.
[0041] Furthermore, in one embodiment of this application, such as Figure 2 As shown, the cloud data processing platform 100 may also include a data service unit 105, which provides a variety of data service interfaces, wherein the data service interfaces are used to retrieve data from the cloud data processing platform.
[0042] Specifically, the data service function can build a standardized data service system based on the platform's unified data resource pool. Relying on a hierarchical permission control mechanism, it can open up multiple types of general data call interfaces and customized business data interfaces. Access permissions are strictly divided according to user identity, job function, and business level. Different operation permissions such as read-only query, data call, data export, and data modification are distinguished to achieve refined control of data access and strictly prevent unauthorized access and illegal leakage of core R&D data.
[0043] The aforementioned data service functions, within the scope of compliant authorization, can provide stable and reliable data support services for the AI bidirectional correlation analysis module 200, the collaborative quality management module 300, and various internal business subsystems. It supports the on-demand retrieval of various business data, such as design data, quality data, management data, statistical analysis results, and risk warning data. It not only meets the data interoperability and linkage needs between various functional modules, but also connects to external business systems to achieve data interconnection and interoperability. At the same time, it unifies and standardizes data retrieval formats and interaction standards to ensure efficient, smooth, and secure data retrieval, and fully supports the orderly operation of various business processes of quality management throughout the entire vehicle R&D process.
[0044] Furthermore, the AI bidirectional correlation analysis module 200 includes a feature extraction unit 201 and a correlation analysis unit 202. The feature extraction unit 201 is used to extract features from design data, quality data, and management data to generate vehicle feature data. The correlation analysis unit 202 is used to analyze the vehicle feature data to generate vehicle quality correlation data and send the quality correlation data to the cloud data processing platform.
[0045] In one embodiment of this application, the feature extraction unit 201 is specifically used to: construct a bidirectional correlation analysis model based on a deep learning framework; and extract features from design data, quality data, and management data through the bidirectional correlation analysis model to generate vehicle feature data, which may include design parameter thresholds, quality defect levels, and after-sales fault types.
[0046] Specifically, the AI bidirectional correlation analysis module 200 can build an intelligent analysis system based on a mature deep learning framework. It is specifically developed for data correlation analysis and judgment of the entire automotive R&D process, focusing on R&D data, quality data, and after-sales maintenance data to conduct in-depth data mining and causal relationship inference. This module can proactively and accurately extract the required R&D, quality, and after-sales data from the data storage area of the cloud data processing platform. After professional feature engineering processing by the internal feature extraction unit, such as standardization screening, noise reduction, and dimensional simplification of the raw data, it can efficiently extract core key features with business value, such as design parameter threshold ranges, component quality defect levels, market after-sales fault categories, fault occurrence frequency, and test and inspection deviation values.
[0047] Furthermore, in one embodiment of this application, the association analysis unit 202 is specifically used to: construct a forward association model and a reverse association model based on dual machine learning algorithms, wherein the forward association model and the reverse association model are interconnected; analyze the design parameter threshold, quality defect level, and after-sales fault type through the forward association model to obtain the problem impact weight; analyze the design parameter threshold, quality defect level, and after-sales fault type through the reverse association model to obtain the problem association weight; and generate quality association data based on the problem impact weight and the problem association weight, wherein the quality association data includes quality association nodes.
[0048] The AI-powered bidirectional correlation analysis module 200 can introduce a dual machine learning (DML) algorithm architecture to build two sets of interconnected independent learning sub-models: a forward correlation model and a reverse correlation model, forming a bidirectional closed-loop analysis logic. The forward correlation model focuses on the forward deduction of the transmission effect of source data from the R&D end, sorting out the complete influence transmission path of various R&D design parameters, structural schemes, process standards, and other R&D data on offline quality inspection data and end-market after-sales fault data. It quantifies and calculates the degree of influence corresponding to different R&D elements, outputs precise quantitative correlation influence weights, and clearly explains how problems such as design parameter deviations and unreasonable structural layouts gradually induce component inspection defects, ultimately evolving into end-vehicle after-sales fault problems. In short, the forward correlation model can be used to analyze the influence path of R&D data on quality data and after-sales data (such as design...). The model analyzes how parameter deviations lead to detection defects and subsequently after-sales failures, and outputs the impact weights. The reverse correlation model, on the other hand, uses reverse tracing analysis logic, taking abnormal data from on-site quality inspections and market after-sales failure feedback data as the starting point for tracing back to the potential loopholes and quality hazards in the corresponding R&D design stages. It also outputs reverse correlation matching weights, enabling rapid location of the root cause of front-end R&D design issues from terminal failure problems. In short, the reverse correlation model can be used to reverse trace the feedback correlation between after-sales data and quality data and R&D data (such as which design stages have quality hazards corresponding to high-frequency after-sales failures), and it also outputs correlation weights.
[0049] The two learning sub-models, forward and backward, share a unified feature space to carry out collaborative iterative learning. They can dynamically and autonomously optimize and correct the correlation weights between various types of data based on real-time new business data, and continuously iterate and update to form a visual dynamic data correlation map, which intuitively presents the intrinsic relationship between R&D, quality, and after-sales data.
[0050] When any type of business data shows numerical anomalies, indicator deviations, or abnormal data fluctuations, the module can conduct cross-verification through two sub-models to quickly pinpoint the business scope affected by the abnormal data, related data items, and corresponding business processes, thereby achieving precise location of the anomaly.
[0051] To illustrate with a real-world application scenario: When the number of complaints about brake system-related faults for a certain model in after-sales statistics increases sharply, the positive correlation model can quickly match and analyze the positive influence relationship between the material parameters, structural dimension design parameters of brake components in the R&D database and this type of fault. The reverse correlation model, on the other hand, combines after-sales fault characteristics with the error range of factory quality inspection to accurately pinpoint the abnormal interval where the brake-related design parameters deviate. Through cross-validation of the two models, the core nodes of the problem correlation are accurately determined, providing reliable data and decision support for subsequent design optimization, quality rectification, and solution iteration.
[0052] Furthermore, the collaborative quality management module 300 includes a collaborative management unit 301, which is used to generate a quality problem report for the vehicle based on quality-related data.
[0053] In one embodiment of this application, the collaborative management unit 301 is specifically used to: obtain a preset problem threshold and a preset urgency level, and generate a vehicle quality problem report based on quality-related data, the preset problem threshold, and the preset urgency level; and send the quality problem report to the cloud data processing platform so that the quality problem report can be sent to the target terminal through the data transmission unit.
[0054] Specifically, the collaborative management unit 301 includes cloud-based team collaboration and AI collaboration functions, enabling efficient cloud-based collaboration across regions and departments: Cloud-based team collaboration can establish cross-regional and cross-departmental team collaboration spaces, supporting real-time communication, file sharing, and task allocation. It ensures data security and operational standardization through a permission management mechanism, while recording operation process logs for easy subsequent traceability and management; AI collaboration can collaborate by calling the data service interface and data analysis prediction results of the cloud data processing platform, setting problem thresholds and urgency levels, monitoring quality data, and automatically creating quality problem tickets based on correlation results and urgency levels when design parameters or after-sales data are predicted to be abnormal. These tickets are then assigned to the quality management and design teams, tracking optimization progress until verification is passed, thus improving quality efficiency.
[0055] Furthermore, in one embodiment of this application, such as Figure 2 As shown, the collaborative quality management module 300 also includes a quality management unit 302. The quality management unit 302 has one or more of the following functions: quality problem management, design review management, recurrence prevention management, system audit problem management, zeroing-out management, and quality TFT (Task Force Team) management. For details, please refer to... Figure 3 As shown, this enables full lifecycle management of quality data.
[0056] Among them, quality issue management provides functions such as issue identification, issue analysis, measure formulation, measure implementation, implementation verification, issue closure, and experience summary; design review management provides functions such as review plan preparation, review execution minutes, review issue rectification, and recurrence prevention management provides functions such as task assignment, investigation and prevention, and preventive measures; system audit issue management provides functions such as non-conformity entry, non-conformity decomposition, correction and corrective measures, and verification closure; zeroing management provides functions such as zeroing instruction issuance, zeroing report writing, and zeroing report review; and quality TFT management provides functions such as TFT project initiation, progress reporting, TFT progress evaluation, and summary reports.
[0057] The following is a specific embodiment to describe the specific workflow of the cloud data processing platform proposed in this application, such as... Figure 4 As shown, the process is described below: 1. Market Quality Information Input: Each brand company manages after-sales issues through systems such as CMS (Customer Management System) and BQMS (Business Quality Management System) so that the cloud data processing platform can use the after-sales information for two-way processing.
[0058] 2. R&D Quality Information Input: R&D departments at all levels manage R&D design data through systems such as BPM (Business Process Management), experimental data system, and DFMEA (Design Failure Mode and Effects Analysis), so that the cloud data processing platform can use the R&D data for bidirectional processing.
[0059] 3. Cloud-based data processing platform with AI bidirectional correlation analysis: This platform is specifically designed for in-depth mining of R&D data, quality data, and after-sales data. It extracts key features such as design parameter thresholds, quality defect levels, and after-sales fault types. It also utilizes dual machine learning algorithms to construct two interconnected learning sub-models: a forward correlation model and a reverse correlation model. The platform outputs data in a targeted manner, and relevant functional modules are available for technical personnel to use.
[0060] 4. Positive Output: The positive correlation model analyzes the impact path of R&D data on quality and after-sales data (e.g., how design parameter deviations lead to detection defects, which in turn cause after-sales failures), and outputs the impact weights. It provides brand companies with maintenance suggestions, monitoring data, and fault warnings.
[0061] 5. Reverse Output: The reverse correlation model traces the feedback relationship between after-sales data and quality data and R&D data (e.g., which design stages have potential quality issues corresponding to high-frequency after-sales failures), and outputs the correlation weights. This provides design references and potential problem alerts for professional departments.
[0062] 6. Component design improvement: The cloud data processing platform serves as a tool for technical personnel to develop and design components, thereby driving improvements in component design.
[0063] The cloud-based automotive R&D quality management system proposed in this application can integrate scattered data through a cloud platform, solving the problem of difficult interoperability of multi-source data; it can replace manual analysis with an AI bidirectional correlation model to accurately and quickly mine data correlations, reducing manpower and time consumption; and it can achieve efficient cross-domain collaboration through cloud collaboration functions, automatically allocate tasks and manage closed loops, thereby effectively improving the efficiency of automotive R&D quality control, accelerating progress, reducing costs, and enhancing market competitiveness.
[0064] Furthermore, embodiments of this application may also provide an electronic device, which may include the cloud-based automotive R&D quality management system described in the above embodiments.
[0065] Specifically, this electronic device can serve as the hardware carrier of a cloud-based automotive R&D quality management system, enabling the collection, analysis, and collaborative management of quality data throughout the entire automotive R&D process. Its core feature is the integration of the aforementioned cloud-based automotive R&D quality management system. With hardware as support, it allows the innovative functions of the software system to be implemented. At the same time, through the collaborative optimization of hardware and software, it can solve the key problems of low efficiency, scattered data, poor reliability, and lagging management in traditional automotive R&D quality control.
[0066] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0067] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0068] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.
[0069] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0070] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0071] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
[0072] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0073] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.
Claims
1. A cloud-based automotive R&D quality management system, characterized in that, include: The system includes a cloud-based data processing platform, an AI bidirectional correlation analysis module, and a collaborative quality management module. The cloud-based data processing platform is connected to both the AI bidirectional correlation analysis module and the collaborative quality management module. The cloud-based data processing platform includes a data acquisition unit and a data transmission unit. The data acquisition unit is used to acquire vehicle design data, quality data, and management data. The data transmission unit is used to send the design data, quality data, and management data to the AI bidirectional correlation analysis module and the collaborative quality management module, respectively. The AI bidirectional correlation analysis module includes a feature extraction unit and a correlation analysis unit. The feature extraction unit is used to extract features from the design data, the quality data, and the management data to generate vehicle feature data. The correlation analysis unit is used to analyze the vehicle feature data to generate vehicle quality correlation data and send the quality correlation data to the cloud data processing platform. The collaborative quality management module includes a collaborative management unit, which is used to generate a vehicle quality problem report based on the quality correlation data.
2. The cloud-based automotive R&D quality management system according to claim 1, characterized in that, The data acquisition unit is also used for: The design data, quality data, and management data are preprocessed respectively, wherein the preprocessing includes one or more of the following: data cleaning, format conversion, deduplication, normalization, and annotation.
3. The cloud-based automotive R&D quality management system according to claim 1, characterized in that, The cloud-based data processing platform further includes a data storage unit, wherein the data storage unit is used for: The design data, quality data, and management data are classified separately to obtain structured data and unstructured data. A distributed storage architecture is used to store the structured data and the unstructured data.
4. The cloud-based automotive R&D quality management system according to claim 1, characterized in that, The cloud-based data processing platform further includes a data analysis unit, wherein the data analysis unit is used for: The quality correlation data is analyzed to obtain the analysis results; If the analysis result meets the preset quality problem occurrence conditions, an early warning message corresponding to the analysis result is generated and sent to the target terminal through the data transmission unit.
5. The cloud-based automotive R&D quality management system according to claim 1, characterized in that, The cloud-based data processing platform also includes a data service unit, which provides various data service interfaces, wherein the data service interfaces are used to retrieve data from the cloud-based data processing platform.
6. The cloud-based automotive R&D quality management system according to claim 1, characterized in that, The feature extraction unit is specifically used for: A bidirectional correlation analysis model was constructed based on a deep learning framework. The design data, quality data, and management data are used to extract features through the bidirectional correlation analysis model to generate the vehicle feature data.
7. The cloud-based automotive R&D quality management system according to claim 1, characterized in that, The vehicle feature data includes design parameter thresholds, quality defect levels, and after-sales fault types. The correlation analysis unit is specifically used for: Based on dual machine learning algorithms, a positive association model and a negative association model are constructed respectively, wherein the positive association model and the negative association model are mutually related; The design parameter thresholds, quality defect levels, and after-sales fault types are analyzed using the positive correlation model to obtain the problem impact weights. The design parameter thresholds, quality defect levels, and after-sales fault types are analyzed using the reverse correlation model to obtain the problem correlation weights. The quality association data is generated based on the impact weight of the problem and the association weight of the problem, wherein the quality association data includes quality association nodes.
8. The cloud-based automotive R&D quality management system according to claim 1, characterized in that, The collaborative quality management module also includes a quality management unit, which has one or more of the following functions: quality problem management, design review management, recurrence prevention management, system audit problem management, zeroing management, and quality TFT management.
9. The cloud-based automotive R&D quality management system according to claim 1, characterized in that, The collaborative management unit is specifically used for: Obtain a preset problem threshold and a preset urgency level, and generate a quality problem report for the vehicle based on the quality-related data, the preset problem threshold, and the preset urgency level; The quality issue report is sent to the cloud data processing platform, so that the quality issue report can be sent to the target terminal through the data transmission unit.
10. An electronic device, characterized in that, Including the cloud-based automotive R&D quality management system as described in any one of claims 1-9.