Automobile design change process data processing method and device, medium and electronic equipment

Abstract

The invention provides an automobile design change process data processing method and device, a medium and electronic equipment. The method comprises the steps of obtaining multi-source heterogeneous original design change information through a standardized interface in response to a design change process initiated by a management user for a target automobile change project; performing multi-level classification on the original design change information to obtain at least one category of intermediate design change information; extracting structured target design change information from the intermediate design change information through a pre-trained large language model; and creating a design change application ledger, and importing the target design change information and auditor information auditing the target design change information into the design change application ledger to trigger an approval program of the automobile design change. According to the invention, the efficiency of automobile design change process data processing can be improved.

Description

Technical Field

[0001] This application relates to the field of project management technology, and more specifically, to a method, apparatus, medium, and electronic device for processing data in the automotive design change process. Background Technology

[0002] In today's rapidly developing and increasingly competitive automotive industry, automotive R&D departments frequently make short-cycle changes to products, functions, components, and software / hardware to adapt to market demands, technological iterations, and enhance market competitiveness. Traditional design change processes largely rely on manual operations, such as handling numerous change requests, document writing, information extraction, communication coordination, and approval processes. This involves a significant amount of repetitive work and consumes substantial human resources. Therefore, improving the efficiency of data processing in automotive design change processes is a pressing technical challenge. Summary of the Invention

[0003] Embodiments of this application provide a method, apparatus, computer program product or computer program, computer-readable storage medium, or electronic device for processing automotive design change process data, which can at least to some extent improve the efficiency of automotive design change process data processing.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] According to one aspect of the embodiments of this application, a method for processing automotive design change process data is provided, characterized in that the method includes: responding to a design change process initiated by a management user for a target automotive change project, obtaining multi-source heterogeneous original design change information through a standardized interface; classifying the original design change information into multiple levels to obtain at least one category of intermediate design change information; extracting structured target design change information from the intermediate design change information using a pre-trained large language model; creating a design change application ledger, and importing the target design change information and the information of the reviewers who reviewed the target design change information into the design change application ledger to trigger the automotive design change approval process.

[0006] In some embodiments of this application, based on the foregoing scheme, the step of extracting structured target design change information from the intermediate design change information using a pre-trained large language model includes: obtaining pre-constructed target text processing prompts, which are used to prompt the large language model to understand the text processing task of the intermediate design change information; and extracting structured target design change information from the intermediate design change information using the large language model based on the target text processing prompts.

[0007] In some embodiments of this application, based on the foregoing scheme, obtaining pre-constructed target text processing prompts includes: obtaining a plurality of pre-constructed text processing prompts; and determining, from the plurality of text processing prompts, a target text processing prompt that matches the target category according to the target category to which the intermediate design change information belongs.

[0008] In some embodiments of this application, based on the foregoing scheme, the step of extracting structured target design change information from the intermediate design change information through the large language model based on the target text processing prompt words includes: inputting the target text processing prompt words and the intermediate design change information into the large language model; obtaining candidate design change information output by the large language model and displaying it on the user interaction interface; and determining the target design change information in response to the editing operation of the management user on the user interaction interface.

[0009] In some embodiments of this application, based on the foregoing scheme, the method further includes: acquiring multiple sets of historical design change record data, wherein each set of historical design change record data includes historical intermediate design change information and its corresponding target design change information; and training the large language model based on the multiple sets of historical design change record data.

[0010] In some embodiments of this application, based on the foregoing scheme, each set of historical design change record data further includes target text processing prompt words corresponding to the intermediate design change information in history, and the method further includes: optimizing the target text processing prompt words based on the multiple sets of historical design change record data through the large language model.

[0011] In some embodiments of this application, based on the foregoing scheme, importing the target design change information and the reviewer information of the target design change information into the design change application ledger includes: locating the information filling areas of the target design change information and the reviewer information in the design change application ledger using a positioning element; and writing the target design change information and the reviewer information into their respective information filling areas.

[0012] According to one aspect of the embodiments of this application, a data processing apparatus for automotive design change processes is provided, characterized in that the apparatus includes: an acquisition unit, configured to acquire multi-source heterogeneous original design change information through a standardized interface in response to a design change process initiated by a management user for a target automotive change project; a classification unit, configured to classify the original design change information at multiple levels to obtain at least one category of intermediate design change information; an extraction unit, configured to extract structured target design change information from the intermediate design change information using a pre-trained large language model; and an import unit, configured to create a design change application ledger and import the target design change information and the information of the reviewers who reviewed the target design change information into the design change application ledger to trigger the automotive design change approval process.

[0013] According to one aspect of the embodiments of this application, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods described in the above embodiments.

[0014] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the method described in the above embodiments.

[0015] According to one aspect of the embodiments of this application, an electronic device is provided, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to perform the method described in the above embodiments.

[0016] Based on the technical solution proposed in this application, firstly, obtaining multi-source heterogeneous original design change information through standardized interfaces simplifies the tedious process of manually collecting information from different systems and documents in traditional methods, reducing errors and omissions that may arise from manual operations, thereby improving the efficiency and accuracy of information collection. Secondly, by classifying the original information into multiple levels, the information becomes more organized, facilitating the adoption of appropriate processing methods for different categories of information, thus reducing processing errors and repetitive work caused by information chaos, and improving overall processing speed. Thirdly, utilizing a large language model to extract structured target design change information transforms unstructured text information into structured data that is easy for computers to process and for humans to understand, enabling the rapid identification of key information, reducing the time spent searching for information from large amounts of text, and thus improving approval efficiency.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0019] Figure 1 A flowchart of a data processing method for an automotive design change process according to an embodiment of this application is shown;

[0020] Figure 2 A block diagram of an automotive design change process data processing apparatus according to an embodiment of this application is shown;

[0021] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0022] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0023] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0024] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0025] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0026] It should be noted that "multiple" in this article refers to 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. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such uses of these terms can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described.

[0028] In today's rapidly developing and increasingly competitive automotive industry, automotive R&D departments frequently make short-cycle changes to products, functions, components, and software / hardware to adapt to market demands, technological iterations, and enhance market competitiveness. Traditional design change processes largely rely on manual operations, such as handling numerous change requests, document writing, information extraction, communication coordination, and approval processes. This involves a significant amount of repetitive work and consumes substantial human resources. Therefore, this application proposes a data processing method for automotive design change processes to improve the efficiency of data processing in these processes.

[0029] The implementation details of the technical solutions in the embodiments of this application are described below:

[0030] See Figure 1 The diagram illustrates a flowchart of a data processing method for an automotive design change process according to an embodiment of this application, the method being executed by a computing device.

[0031] like Figure 1 As shown, this automotive design change process data processing method includes at least steps 110 to 140, detailed below:

[0032] Step 110: In response to the design change process initiated by the management user for the target vehicle change project, obtain multi-source heterogeneous original design change information through a standardized interface.

[0033] Step 120: Classify the original design change information into multiple levels to obtain at least one category of intermediate design change information.

[0034] Step 130: Extract structured target design change information from the intermediate design change information using a pre-trained large language model.

[0035] Step 140: Create a design change application ledger and import the target design change information and the information of the reviewers who reviewed the target design change information into the design change application ledger to trigger the approval process for the vehicle design change.

[0036] In this application, the multi-source heterogeneous original design change information can be design change information in various formats from different departments. For example, it can be drawing change instructions from the design department, test reports and problem records from the R&D and testing department, or user feedback and market research reports from the customer service department. This application does not make any specific limitations on this.

[0037] In some specific embodiments of this application, the original design change information is classified into multiple levels. Specifically, the original design change information can be classified into six main sections: basic information, change content, change implementation time, involved parts, change impact, and joint approval. Basic information is further classified into two levels: change application basic information, related issues, related change requirements, and related change application forms. Change content is further classified into two levels: title, reason for change, feasibility of change, vehicle verification information, description of the original solution, description of the original solution, and scope of change. Change implementation time is further classified into two levels: vehicle model, derivative project, implementation node, node planned time, switching method, inventory parts handling method, trial assembly information, and remarks. Involved parts are further classified into two levels: part number identification before and after change, change status, imported vehicle model, part number, part procurement information, configuration description, supply status, supplier, tooling / mold cost impact, part status, mass production interchangeability, and after-sales interchangeability. The impact of changes is further categorized into two levels: performance impact, process impact, regulatory and patent impact, functional impact, vehicle safety impact, quality impact, electrical architecture impact, after-sales impact, weight change impact, after-sales inventory handling, tooling description, software and hardware compatibility assessment, change cycle, vehicle verification plan, vehicle cost impact, and other impact analysis. The co-signing and approval process is further categorized into two levels: departmental / professional review, procurement co-signing, cost co-signing, and the necessity of co-signing personnel.

[0038] In this application, the large language model may specifically be a large language model such as DeepSeek V3, GPT 4.1, or Claude4Sonnet, but this application does not make any specific limitation.

[0039] In this application, firstly, by obtaining multi-source heterogeneous original design change information through standardized interfaces, the tedious process of manually collecting information from different systems and documents in traditional methods can be simplified, reducing errors and omissions that may be caused by manual operation, thereby improving the efficiency and accuracy of information collection; secondly, by classifying the original information into multiple levels, the information can be made more organized, facilitating the adoption of appropriate processing methods for different categories of information, thereby reducing processing errors and repetitive work caused by information chaos, and improving the overall processing speed; thirdly, by using a large language model to extract structured target design change information, unstructured text information is transformed into structured data that is easy for computers to process and for people to understand, enabling the rapid identification of key information, reducing the time spent searching for information from a large amount of text, thereby improving approval efficiency.

[0040] In step 130 above, the extraction of structured target design change information from the intermediate design change information using a pre-trained large language model can be specifically performed according to steps 131 to 132 as follows:

[0041] Step 131: Obtain pre-constructed target text processing prompts, which are used to prompt the large language model to understand the text processing task of the intermediate design change information.

[0042] Step 132: Based on the target text processing prompt words, extract structured target design change information from the intermediate design change information using the large language model.

[0043] In this application, before extracting structured target design change information from intermediate design change information using a large language model, it is necessary to provide clear guidance to the large language model. Therefore, target text processing prompts can be pre-constructed to clearly convey the specific task requirements for text processing of intermediate design change information to the large language model. For example, the prompts can specify in detail which key elements need to be extracted from the intermediate design change information, such as the name of the changed component, the reason for the change, and a comparison of parameters before and after the change. They can also specify requirements for the format and structure of the information to ensure that the large language model can accurately understand the task objective.

[0044] In this application, the pre-constructed target text processing prompts can provide clear task guidance for the large language model, enabling it to quickly extract key information, thereby shortening the information reading time and improving the efficiency of data processing. By providing detailed descriptions of the task requirements for information extraction through the target text processing prompts, the large language model can more accurately identify and extract key information, reducing the occurrence of information extraction errors and incomplete extraction, thereby reducing the workload of manual correction and improving the accuracy and efficiency of data processing.

[0045] Furthermore, in step 131 above, the acquisition of pre-constructed target text processing prompts can be specifically performed according to steps 1311 to 1312 as follows:

[0046] Step 1311: Obtain multiple pre-built text processing prompts.

[0047] Step 1312: Based on the target category to which the intermediate design change information belongs, determine the target text processing prompt word that matches the target category from the plurality of text processing prompt words.

[0048] In this application, the pre-constructed multiple text processing prompts can be designed for various possible text processing tasks. Each prompt has its specific task orientation and scope of application. For example, prompts for changes in component structure may focus on extracting key information such as the size, shape, and material of the changed parts; while prompts for changes in electronic system software algorithms will focus on information extraction requirements such as the modification points and functional impact of the algorithm. By acquiring multiple text processing prompts, a basis can be provided for selecting appropriate prompts based on the category of intermediate design change information.

[0049] In this application, by pre-constructing multiple text processing prompts and quickly determining the matching target text processing prompts based on the category of intermediate design change information, the preparation time for information processing can be shortened, thereby accelerating the startup speed of the entire data processing process. Selecting the matching target text processing prompts based on the category of intermediate design change information ensures that the task requirements of the prompts are highly consistent with the characteristics of the information, enabling the large language model to extract key information more accurately, avoiding rework caused by prompt mismatch, and thus improving the efficiency and quality of data processing.

[0050] Furthermore, in step 132 above, the step of extracting structured target design change information from the intermediate design change information based on the target text processing prompt words and using the large language model can be specifically executed according to steps 1321 to 1323 as follows:

[0051] Step 1321: Input the target text processing prompt and the intermediate design change information into the large language model.

[0052] Step 1322: Obtain the candidate design change information output by the large language model and display it on the user interface.

[0053] Step 1323: In response to the editing operation of the management user on the user interface, determine the target design change information.

[0054] In this application, the target text processing prompt words can be used to guide the large language model to understand the text processing task of intermediate design change information. The intermediate design change information is the original text containing the specific content of the car design change, which may have problems such as non-standard expression and scattered information. Inputting the target text processing prompt words and intermediate design change information into the large language model can provide the large language model with key information for the processing task, enabling it to clarify the processing direction and content, and thus complete the analysis and processing of the intermediate design change information.

[0055] In this application, by inputting target text processing prompts and intermediate design change information into a large language model, the large language model can quickly analyze and process the intermediate design change information, generate candidate design change information, and complete the preliminary screening and organization of a large amount of information in a short time, thereby greatly saving data processing time and improving the efficiency of the entire information processing process.

[0056] In this application, the candidate design change information output by the large language model is displayed on the user interface, allowing management users to edit it. This enables management users to check and correct the information based on actual needs and professional knowledge, thereby enabling timely detection and correction of errors that occur during the extraction process of the large language model. This ensures the accuracy of the final target design change information, thus avoiding subsequent rework due to inaccurate information and improving the efficiency of data processing in the entire automotive design change process.

[0057] In this application, candidate design change information and the editing operations of management users are displayed through a user interface. This allows the system to record the entire information processing process and results for storage, retrieval, and traceability. This provides clear information for each stage of the automotive design change process, thereby strengthening communication and collaboration between departments and improving the overall efficiency of the process.

[0058] Based on the above, the method proposed in this application may further include the following steps 210 to 220:

[0059] Step 210: Obtain multiple sets of historical design change record data, wherein each set of historical design change record data includes information on intermediate design changes in history, as well as information on the corresponding target design changes.

[0060] Step 220: Train the large language model based on the multiple sets of historical design change record data.

[0061] Furthermore, each set of historical design change record data may also include target text processing prompts corresponding to the intermediate design change information in the history. The method proposed in this application may also include the following step 230:

[0062] Step 230: Based on the multiple sets of historical design change record data, optimize the target text processing prompt words through the large language model.

[0063] In this application, the multiple sets of historical design change record data can specifically include the names of the parts involved in the design change, the parameters before and after the design change, the scope of the impact of the design change, and the text processing prompts corresponding to each design change. By collecting multiple sets of historical design change record data, it can be ensured that the data is diverse and extensive, covering various types and scenarios of automotive design changes.

[0064] In this application, a large language model is trained using multiple sets of historical design change record data, enabling the model to learn the correspondence between rich language patterns and change information. This allows the model to more accurately understand the meaning of new intermediate design change information, extract the correct key information, and generate more accurate target design change information, thereby reducing the workload of manual correction and improving the efficiency and accuracy of information processing.

[0065] In this application, multiple sets of historical design change record data can cover various types and scenarios of automotive design changes. By using this data for training, the large language model can be exposed to a rich variety of change information representation methods, thereby enabling the model to learn the characteristics and patterns of different types of change information, enhancing its adaptability to different types of change information, and thus improving the efficiency and accuracy of information processing.

[0066] In this application, by using a large language model to optimize the target text processing prompt words based on multiple sets of historical design change record data, the prompt words can be made to better match the actual content and characteristics of intermediate design change information. This allows the optimized prompt words to more clearly indicate which key information the large language model should focus on, thereby improving the accuracy and completeness of information extraction.

[0067] In step 140 above, importing the target design change information and the information of the personnel reviewing the target design change information into the design change application ledger can be performed according to the following steps 141 to 142:

[0068] Step 141: Locate the information filling area for the target design change information and the reviewer information in the design change application ledger using the positioning element.

[0069] Step 142: Write the target design change information and the reviewer information into their respective information filling areas.

[0070] In one specific embodiment of this application, a Python script can be used to import the target design change information and the information of the reviewers who reviewed the target design change information into the design change application ledger.

[0071] In this application, the design change application ledger can be a document or system interface used to record and manage design change-related information. The positioning element can be a pre-defined specific identifier, such as a specific text label, table row and column number, or specific format features. Through these identifiers, the specific location of the information to be filled in can be quickly and accurately located in the ledger. For example, if the design change application ledger is presented in table form, the target design change information may correspond to a specific row area in a column of the table. The positioning element can be a column header or row index, etc.

[0072] In this application, the information of the reviewers may specifically include professional reviewers and countersigners, etc., and this application does not make specific limitations on this.

[0073] In this application, by utilizing positioning elements to quickly locate the information filling area, the tedious process of manually searching row by row and column by column can be reduced, thereby shortening the information search time and improving the efficiency of the entire data processing flow. In addition, by locating the information filling area and writing the target design change information and the reviewer information into their respective information filling areas, the information structure in the design change application ledger can be clear and complete, facilitating subsequent information integration and management, and further improving the efficiency of the entire data processing flow.

[0074] Based on the technical solutions proposed in this application, firstly, obtaining multi-source heterogeneous original design change information through standardized interfaces can simplify the tedious process of manually collecting information from different systems and documents in traditional methods, reduce errors and omissions that may be caused by manual operation, and thus improve the efficiency and accuracy of information collection; secondly, by classifying the original information into multiple levels, the information can be more organized, making it easier to adopt appropriate processing methods for different categories of information, thereby reducing processing errors and repetitive work caused by information chaos and improving the overall processing speed; thirdly, by using a large language model to extract structured target design change information, unstructured text information is transformed into structured data that is easy for computers to process and for people to understand, which can quickly identify key information, reduce the time spent searching for information from a large amount of text, and thus improve approval efficiency.

[0075] The following describes an embodiment of the apparatus described in this application, which can be used to execute the automotive design change process data processing method described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the automotive design change process data processing method described above in this application.

[0076] Figure 2 A block diagram of an automotive design change process data processing apparatus according to an embodiment of this application is shown.

[0077] Reference Figure 2 As shown, an automotive design change process data processing apparatus 200 according to an embodiment of this application includes an acquisition unit 201, a classification unit 202, an extraction unit 203, and an import unit 204.

[0078] The system includes: an acquisition unit 201, which responds to a design change process initiated by a management user for a target vehicle modification project and acquires multi-source heterogeneous original design change information through a standardized interface; a classification unit 202, which classifies the original design change information into multiple levels to obtain at least one category of intermediate design change information; an extraction unit 203, which extracts structured target design change information from the intermediate design change information using a pre-trained large language model; and an import unit 204, which creates a design change application ledger and imports the target design change information, along with the information of the reviewers who reviewed the target design change information, into the design change application ledger to trigger the vehicle design change approval process.

[0079] In some embodiments of this application, based on the foregoing scheme, the extraction unit 203 is configured to: obtain pre-constructed target text processing prompts, the target text processing prompts being used to prompt the large language model to understand the text processing task of the intermediate design change information; and extract structured target design change information from the intermediate design change information through the large language model based on the target text processing prompts.

[0080] In some embodiments of this application, based on the foregoing scheme, the extraction unit 203 is further configured to: acquire a plurality of pre-constructed text processing prompt words; and determine a target text processing prompt word that matches the target category from the plurality of text processing prompt words according to the target category to which the intermediate design change information belongs.

[0081] In some embodiments of this application, based on the foregoing scheme, the extraction unit 203 is further configured to: input the target text processing prompt word and the intermediate design change information into the large language model; obtain the candidate design change information output by the large language model and display it on the user interaction interface; and determine the target design change information in response to the editing operation of the management user on the user interaction interface.

[0082] In some embodiments of this application, based on the foregoing scheme, the device further includes a training unit, which is configured to: acquire multiple sets of historical design change record data, wherein each set of historical design change record data includes historical intermediate design change information and its corresponding target design change information; and retrain the large language model based on the multiple sets of historical design change record data.

[0083] In some embodiments of this application, based on the foregoing scheme, each set of historical design change record data also includes target text processing prompt words corresponding to the intermediate design change information in history, and the training unit is further configured to: optimize the target text processing prompt words through the large language model based on the multiple sets of historical design change record data.

[0084] In some embodiments of this application, based on the foregoing scheme, the import unit 204 is configured to: locate the information filling areas of the target design change information and the reviewer information in the design change application ledger using a positioning element; and write the target design change information and the reviewer information into their respective information filling areas.

[0085] As another embodiment of this application, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods described in the above embodiments.

[0086] As another embodiment of this application, a computer-readable storage medium is also provided. This computer-readable storage medium may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0087] Based on the same inventive concept, embodiments of this application also provide an electronic device. (Reference) Figure 3 The diagram illustrates a schematic of a computer system suitable for implementing an electronic device according to embodiments of this application. The electronic device includes one or more memories 304, one or more processors 302, and at least one computer program (program code) stored in the memories 304 and executable on the processors 302. When the processors 302 execute the computer program, they implement the methods described above.

[0088] Among them, Figure 3 In this document, a bus architecture (represented by bus 300) is used. Bus 300 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.

[0089] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0091] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium, including instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0093] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for processing data in the automotive design change process, characterized in that, The method includes: In response to user-initiated design change processes for target vehicle modification projects, the system obtains multi-source heterogeneous original design change information through standardized interfaces. The original design change information is classified into multiple levels to obtain at least one category of intermediate design change information; Structured target design change information is extracted from the intermediate design change information using a pre-trained large language model; Create a design change application ledger and import the target design change information and the information of the reviewers who will review the target design change information into the design change application ledger to trigger the approval process for the vehicle design change.

2. The method according to claim 1, characterized in that, The extraction of structured target design change information from the intermediate design change information using a pre-trained large language model includes: Obtain pre-constructed target text processing prompts, which are used to prompt the large language model to understand the text processing task of the intermediate design change information; Based on the target text processing prompts, structured target design change information is extracted from the intermediate design change information using the large language model.

3. The method according to claim 2, characterized in that, The process of obtaining pre-constructed target text processing prompts includes: Retrieve multiple pre-built text processing prompts; Based on the target category to which the intermediate design change information belongs, a target text processing prompt word that matches the target category is determined from the plurality of text processing prompt words.

4. The method according to claim 2, characterized in that, The step of extracting structured target design change information from the intermediate design change information based on the target text processing prompt words and using the large language model includes: The target text processing prompts and the intermediate design change information are input into the large language model; Obtain candidate design change information output from the large language model and display it on the user interface; In response to the editing operation performed by the management user on the user interface, the target design change information is determined.

5. The method according to claim 4, characterized in that, The method further includes: Acquire multiple sets of historical design change record data, where each set of historical design change record data includes information on intermediate design changes in history, as well as information on the corresponding target design change; The large language model is trained based on the multiple sets of historical design change records.

6. The method according to claim 5, characterized in that, Each set of historical design change record data also includes target text processing prompts corresponding to the intermediate design change information in the history, and the method further includes: Based on the multiple sets of historical design change record data, the target text processing prompt words are optimized using the large language model.

7. The method according to claim 1, characterized in that, The step of importing the target design change information and the reviewer information of the target design change information into the design change application ledger includes: The information filling area for the target design change information and the reviewer information is located in the design change application ledger by locating the positioning element; Write the target design change information and the reviewer information into their respective information filling areas.

8. A data processing device for automotive design change processes, characterized in that, The device includes: The acquisition unit is used to respond to the design change process initiated by the management user for the target vehicle change project and to acquire multi-source heterogeneous original design change information through a standardized interface. A classification unit is used to classify the original design change information at multiple levels to obtain at least one category of intermediate design change information. An extraction unit is used to extract structured target design change information from the intermediate design change information using a pre-trained large language model; The import unit is used to create a design change application ledger and import the target design change information and the information of the reviewers who review the target design change information into the design change application ledger to trigger the approval process for automotive design changes.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to perform the operations performed by the method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to implement the method as claimed in any one of claims 1 to 7.

Images