A software configuration compiling method and device based on a large language model

Abstract

This application provides a software configuration and compilation method and apparatus based on a large language model. The method includes: inputting software order information into a trained large language model to obtain data collection information output by the trained large language model; obtaining target data from corresponding external data sources through each target MCP service based on the data collection information; inputting each target data into the trained large language model to obtain a software compilation configuration table output by the trained large language model; and compiling the target software according to the software compilation configuration table. This application can combine multi-source heterogeneous information to generate an accurate and complete software compilation configuration table, and then compile correctly configured software based on the accurate and complete software compilation configuration table, reducing manual intervention and reliance on experience, lowering the software error rate, and improving customer experience.

Description

Technical Field

[0001] This application belongs to the field of software technology, and in particular relates to a software configuration and compilation method and apparatus based on a large language model. Background Technology

[0002] Currently, when customizing compilation software for clients, on-site application engineers manually obtain the information required for the compilation software, then manually verify the information to ensure its accuracy. Based on the verified information, they manually compile a configuration table, which is then submitted to the server. The server then executes the compilation.

[0003] However, the above methods rely too heavily on the engineer's experience, which can easily lead to omissions or configuration conflicts during the software compilation process, resulting in software compilation failures or problems in software usage. Summary of the Invention

[0004] This application provides a software configuration compilation method, apparatus, electronic device, readable storage medium, and computer program product based on a large language model, which can solve the problem that relying on the engineer's experience can easily lead to software compilation failure or problems in software use.

[0005] In a first aspect, embodiments of this application provide a software configuration and compilation method based on a large language model, including:

[0006] The software order information is input into the trained large language model to obtain the data collection information output by the trained large language model; Based on the data collection information, target data is obtained from the corresponding external data source through each target MCP service; Each of the target data is input into the trained large language model to obtain the software compilation configuration table output by the trained large language model; Compile the target software according to the software compilation configuration table.

[0007] In some embodiments, before compiling the target software according to the software compilation configuration table, the method further includes: Based on the feedback results, the correction information for the software order information is determined, and the feedback results are the error reason information for the software compilation configuration table; Based on the correction information, update the software order information to obtain the updated software order information; After obtaining the updated software order information, proceed to the following step: input the software order information into the trained large language model to obtain the data collection information output by the trained large language model.

[0008] In some embodiments, the trained large language model is used to perform semantic analysis on the software order information to determine data requirement information; based on the data requirement information and stored external data source information, it is determined whether to collect external information; if it is determined that external information should be collected, the data collection information is determined and output based on the data requirement information.

[0009] In some embodiments, obtaining target data from the corresponding external data source through each target MCP service based on the data acquisition information includes: Based on the target MCP service information of the data collection information, the corresponding target MCP service is determined; For each of the target MCP services, the service protocol of the target MCP service is used to communicate with the corresponding target external data source to obtain the target data corresponding to the data type being collected; The data acquisition information includes at least one type of data to be acquired and the corresponding target MCP service information.

[0010] In some embodiments, determining the correction information for the software order information based on the feedback result includes: Determine the semantic matching information between the feedback result and the software order information; The correction information is determined based on the semantic matching information.

[0011] In some embodiments, compiling the target software according to the software compilation configuration table includes: The software compilation configuration table is analyzed to generate a compilation task queue and determine the compilation toolchain; The target software is generated using the compilation toolchain based on the compilation task queue.

[0012] In some embodiments, the external data source includes order information data source, customer management information data source, email information data source, compilation configuration history information data source, product information data source, and software specification management information data source.

[0013] Secondly, embodiments of this application provide a software configuration compilation apparatus based on a large language model, comprising: The large language model module is used to input software order information into a trained large language model and obtain data collection information output by the trained large language model; It is also used to input each target data into the trained large language model to obtain the software compilation configuration table output by the trained large language model; The acquisition module is used to acquire target data from the corresponding external data source through each target MCP service based on the data acquisition information. The compilation module is used to compile the target software according to the software compilation configuration table.

[0014] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in any one of the first aspects above.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in any one of the first aspects above.

[0016] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to perform the method described in any one of the first aspects above.

[0017] The beneficial effects of the embodiments in this application compared with the prior art are: This application embodiment inputs software order information into a trained large language model to obtain data collection information output by the trained large language model, thereby achieving automated and accurate analysis of customer needs and determining the materials required for compilation. It obtains target data from corresponding external data sources through each target MCP service, ensuring the acquisition of required multi-source heterogeneous information from diverse heterogeneous data sources. The target data is then input into the trained large language model to obtain a software compilation configuration table output by the trained large language model. This table, combined with multi-source heterogeneous information, generates an accurate and complete software compilation configuration table. Based on this accurate and complete configuration table, the correctly configured software is compiled, reducing manual intervention and reliance on experience, lowering the software error rate, and improving the customer experience.

[0018] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the first flowchart of a software configuration compilation method based on a large language model provided in an embodiment of this application; Figure 2 This is a schematic diagram of the second process of a software configuration compilation method based on a large language model provided in an embodiment of this application; Figure 3 This is a schematic diagram of the first structure of a software configuration compilation device based on a large language model provided in an embodiment of this application; Figure 4 This is a schematic diagram of a second structure of a software configuration compilation device based on a large language model provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0021] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0022] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0023] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0025] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0026] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0027] Figure 1 This is a schematic diagram of the first flowchart of a software configuration and compilation method based on a large language model according to an embodiment of this application. The method is applied to electronic devices.

[0028] In some implementations, the method may be executed by a device that is compiled and configured based on a large language model, which may be implemented in software and / or hardware and may be configured in the aforementioned electronic device.

[0029] Figure 1 The method shown includes steps S11 to S14, which will be described in detail below.

[0030] S11: Input the software order information into the trained large language model and obtain the data collection information output by the trained large language model.

[0031] For example, software order information can be obtained by engineers describing customer customization needs in natural language, electronic devices analyzing the natural language description, generating structured prompts, and then obtaining the software order information.

[0032] In some implementations, a trained large language model is used to perform semantic analysis on software order information to determine data requirement information; based on the data requirement information and stored external data source information, it is determined whether to collect external information; if it is determined that external information should be collected, the data collection information is determined and output based on the data requirement information.

[0033] Before using the large language model for reasoning, the electronic device pre-trains the large language model. Training samples containing various customer-specific software customization information are acquired and used to train the large language model, enabling it to learn and recognize the data types required to meet the customer's customization information and generate a software compilation configuration table that satisfies the customer's customization information. Then, the electronic device uses the trained large language model to perform semantic analysis on the software order information, clarifying the customer's intent and thus determining the types of data required to compile the software, obtaining data requirement information. Based on stored external data sources, the source of the data types in the data requirement information is determined. If the required data is provided by an external data source, it is determined to be external information collection. When external information is collected, the data type to be collected and the corresponding target MCP service information are determined based on the data type in the data requirement information. If none of the required data is provided by an external data source, it is determined not to collect external information. When external information is not collected, the software compilation configuration table is determined and output based on the data requirement information.

[0034] In some implementations, the required MCP services are pre-registered with the trained large language model so that the trained large language model can identify available MCP services through the MCP service registration.

[0035] For example, external data sources include order information data sources, customer management information data sources, email information data sources, compilation configuration history information data sources, product information data sources, and software specification management information data sources. Correspondingly, the registered MCP service includes reading order information, reading customer information and historical emails, querying product specifications and software specification manuals, retrieving historical order configuration information, obtaining software compilation configuration history, obtaining product information, and obtaining software specification manuals.

[0036] The trained large language model performs semantic analysis based on software order information to clarify user intent: Company B needs to improve certain algorithms on its existing software, thus requiring customer information, order information, software specification information, and compilation configuration history information. Based on the stored data source, it is determined that the required data can be provided by an external data source. Therefore, based on the above data types, the data types to be collected are determined: customer information, order information, software specification information, compilation configuration history information, and corresponding target MCP service information.

[0037] In some implementations, when the software order information includes contextual session information and specific requirement descriptions, the contextual session information and specific requirement descriptions are concatenated to obtain joint information. This joint information is then input into a trained large language model to obtain the data collection information output by the trained large language model.

[0038] S12: Based on the data collection information, obtain target data from the corresponding external data source through the target MCP service.

[0039] In some implementations, the data acquisition information includes at least one type of data to be acquired and the corresponding target MCP service information. Correspondingly, step S12 includes: S121: Determine the corresponding target MCP service based on the target MCP service information of each target in the data collection information.

[0040] For example, the data collection information includes the following data types: customer information, order information, software specification information, and compilation configuration history information. The corresponding target MCP service information includes: calling to read customer information, calling to read order information, calling to obtain software compilation configuration history, and calling to obtain software specification manual.

[0041] The electronic device determines the corresponding target MCP service based on the target MCP service information: read customer information, read order information, obtain software compilation and configuration history, and obtain software specification manual.

[0042] S122: For each target MCP service, use the service protocol of the target MCP service to communicate with the corresponding target external data source to obtain the target data corresponding to the data type of the collected data.

[0043] The MCP (Model Context Protocol) service encapsulates the access logic to independent external data sources. The MCP service provides data access and manipulation capabilities through standardized interfaces, implementing access logic to enable access to external data sources within pre-defined authorized access limits.

[0044] For each target MCP service, the electronic device generates a request through the service protocol of the target MCP service and sends the request to the target external data source, thereby enabling communication between the target MCP service and the corresponding target external data source. The target external data source responds to the request and returns the target data.

[0045] For example, the target MCP service aims to read customer information. The electronic device sends a request to the target external data source: the Customer Management Information Data Source, through the MCP service. The Customer Management Information Data Source responds to the request by returning the target data: information about customer company B.

[0046] S13: Input each target data into the trained large language model to obtain the software compilation configuration table output by the trained large language model.

[0047] In some implementations, after acquiring the target data, the electronic device aggregates the target data to obtain summary data. This summary data is then input into a trained large language model, which performs comprehensive analysis to extract configuration parameters, driver options, resource paths, and other data that meet customer needs. Finally, based on these configuration parameters, driver options, and resource paths, a corresponding software compilation configuration table is generated.

[0048] In some implementations, after obtaining the software compilation configuration table, it is visualized so that engineers can view it.

[0049] S14: Compile the target software according to the software compilation configuration table.

[0050] In some implementations, step S14 includes: S141: Analyze the software compilation configuration table, generate a compilation task queue, and determine the compilation toolchain.

[0051] The electronic device performs field analysis on the software compilation configuration table, initializes the compilation environment for configuration parameters, driver options, resource paths, and other data, and generates multiple compilation tasks. Each compilation task includes a task representation, target artifact path, library file list, compilation commands, and status words. Then, the dependencies in the software compilation configuration table are analyzed, task priorities are set based on these dependencies, and a compilation task queue is obtained. The compilation toolchain to be invoked is determined based on the compilation tasks in the queue.

[0052] S142: Generate target software using the compiler toolchain based on the compiler task queue.

[0053] The compiler in the compilation toolchain is used to compile the compilation tasks in the compilation task queue to obtain object files, and the linker in the compilation toolchain is used to link the object files and library files into object software.

[0054] This application embodiment inputs software order information into a trained large language model to obtain data collection information output by the trained large language model, thereby achieving automated and accurate analysis of customer needs and determining the materials required for compilation. It obtains target data from corresponding external data sources through each target MCP service, ensuring the acquisition of required multi-source heterogeneous information from diverse heterogeneous data sources. The target data is then input into the trained large language model to obtain a software compilation configuration table output by the trained large language model. This table, combined with multi-source heterogeneous information, generates an accurate and complete software compilation configuration table. Based on this accurate and complete configuration table, the correctly configured software is compiled, reducing manual intervention and reliance on experience, lowering the software error rate, and improving the customer experience.

[0055] Understandably, utilizing the MCP service enables direct communication and interaction with external data sources within the authorized scope, eliminating the need for additional, pre-hard-coded details of each external data source's API interface. This reduces potential issues such as formatting errors, permission problems, and data parsing anomalies that may occur during hard-coding, thereby lowering operational risks. Furthermore, the ability to directly add MCP services based on the type of external data source enhances the flexibility and scalability of the method, thus resolving the problems of poor universality, high maintenance costs, and difficulty in expansion associated with API integration communication methods.

[0056] By directly communicating with external data sources through the MCP service, it obtains multi-source heterogeneous information. Combined with a trained large language model, it performs semantic understanding and logical verification of this information, automatically identifying and resolving conflicting configurations. This improves the accuracy and consistency of the software configuration table, ensuring correctly compiled and configured software. It achieves automated software compilation and secure, accurate access to and operation of external data sources, reducing manual intervention, shortening compilation preparation time, and improving the quality of software delivery. It is applicable to various scenarios, especially OEM software compilation and configuration. Furthermore, the large language model can be trained according to actual scenario requirements, dynamically adapting to different scenarios to output software configuration tables that meet specific needs.

[0057] In some embodiments, Figure 2 This is a schematic diagram of the second flowchart of a software configuration and compilation method based on a large language model provided in an embodiment of this application. As shown in the figure, before step S14, the method further includes: S21: Based on the feedback results, determine the correction information for the software order information.

[0058] The feedback result is the error reason information in the software compilation configuration table.

[0059] In some implementations, the configuration table can be compiled using visual software and then manually reviewed. If the review fails, the error message from the software compilation of the configuration table is manually entered.

[0060] In some implementations, error information in the software compilation configuration table can be obtained by performing operations such as syntax structure checking, path verification, compilation parameter verification, and logical consistency analysis on the software compilation configuration table.

[0061] In some implementations, step S21 includes: S211: Determine the semantic matching information between the feedback results and the software order information.

[0062] Calculate the semantic distance between the error cause information and the software order information to obtain the matching degree of each semantic term and obtain semantic matching information.

[0063] S212: Determine the correction information based on the semantic matching information.

[0064] Based on the matching degree of each semantic term, target semantic terms with a matching degree lower than a preset matching degree are obtained. Correction information is then determined based on the target semantic terms to make the updated software order information more closely resemble the user's intent.

[0065] S22: Update the software order information based on the correction information and obtain the updated software order information.

[0066] The software order information includes the customer's customization information for various aspects of the software. The customized information corresponding to the correction information is adjusted to obtain the updated software order information.

[0067] S23: After obtaining the updated software order information, proceed to step S11: Input the software order information into the trained large language model and obtain the data collection information output by the trained large language model.

[0068] This application embodiment determines the correction information for the software order information based on the feedback results, updates the software order information based on the correction information, obtains the updated software order information, and uses a trained large language model to output a new software compilation configuration table based on the updated software order information, thereby further improving the accuracy and consistency of the software compilation configuration table and further improving the software compilation success rate.

[0069] In some embodiments, after step S14, the method further includes: Store data acquisition information and compilation configuration tables.

[0070] This application embodiment forms a queryable and optimizable knowledge base by storing data acquisition information and compilation configuration tables, realizing the accumulation, querying and reuse of knowledge for intelligent software compilation, further improving the accuracy of software compilation and reducing the compilation error rate.

[0071] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. Furthermore, the data collection in the above embodiments is compliant, and its use or implementation does not involve any infringement upon public interests.

[0072] For ease of explanation, only the parts related to the embodiments of this application are shown in the methods described in the above embodiments.

[0073] In some embodiments, Figure 3 This is a schematic diagram of the first structure of a software configuration and compilation device based on a large language model provided in an embodiment of this application. For example... Figure 3 As shown, the device includes: The large language model module 10 is used to input software order information into the trained large language model and obtain the data collection information output by the trained large language model. It is also used to input various target data into a trained large language model to obtain the software compilation configuration table output by the trained large language model; The acquisition module 11 is used to acquire target data from the corresponding external data source through the target MCP service based on the data acquisition information. Compilation module 12 is used to compile the target software according to the software compilation configuration table.

[0074] In some embodiments, Figure 4 This is a schematic diagram of a second structure of a software configuration and compilation device based on a large language model provided in an embodiment of this application. For example... Figure 4 As shown, external data sources include order information data sources, customer management information data sources, email information data sources, compilation configuration history information data sources, product information data sources, and software specification management information data sources.

[0075] In some embodiments, the apparatus further includes a correction module.

[0076] The correction module is used to determine the correction information for the software order information based on the feedback results, which are the error cause information in the software compilation configuration table. Based on the correction information, the software order information is updated to obtain the updated software order information. After obtaining the updated software order information, the following steps are taken: inputting the software order information into the trained large language model to obtain the data collection information output by the trained large language model.

[0077] In some embodiments, the correction module is specifically used to determine semantic matching information between the feedback result and the software order information; and to determine correction information based on the semantic matching information.

[0078] In some embodiments, a trained large language model is used to perform semantic analysis on software order information to determine data requirement information; based on the data requirement information and stored external data source information, it is determined whether to collect external information; if it is determined that external information should be collected, the data collection information is determined and output based on the data requirement information.

[0079] In some embodiments, the acquisition module is specifically used to determine the corresponding target MCP service based on the target MCP service information of each target MCP service in the data acquisition information; for each target MCP service, it communicates with the corresponding target external data source using the service protocol of the target MCP service to obtain the target data corresponding to the data acquisition data type; wherein, the data acquisition information includes at least one data acquisition data type and the corresponding target MCP service information.

[0080] In some embodiments, the compilation module is specifically used to analyze the software compilation configuration table, generate a compilation task queue and determine the compilation toolchain; based on the compilation task queue, the compilation toolchain is used to generate the target software.

[0081] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device 2 of this embodiment includes: at least one processor 20 ( Figure 2 (Only one is shown in the diagram), memory 21, and computer program 22 stored in said memory 21 and executable on said at least one processor 20, wherein said processor 20 executes said computer program 22 to implement the steps in any of the above method embodiments.

[0082] The electronic device 2 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The electronic device 2 may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will understand that... Figure 2 This is merely an example of electronic device 2 and does not constitute a limitation on electronic device 2. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0083] The processor 20 can be a Central Processing Unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0084] In some embodiments, the memory 21 may be an internal storage unit of the electronic device 2, such as a hard disk or memory of the electronic device 2. In other embodiments, the memory 21 may be an external storage device of the electronic device 2, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 2. Furthermore, the memory 21 may include both internal and external storage units of the electronic device 2. The memory 21 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 21 can also be used to temporarily store data that has been output or will be output.

[0085] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0086] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0087] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps in the above-described method embodiments.

[0088] This application provides a computer program product that, when run on an electronic device, enables the electronic device to implement the steps described in the various method embodiments above.

[0089] 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, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some cases, the computer-readable medium cannot be an electrical carrier signal or a telecommunication signal.

[0090] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0091] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0092] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A software configuration compiling method based on a large language model, characterized in that, include: The software order information is input into the trained large language model to obtain the data collection information output by the trained large language model; Based on the data collection information, target data is obtained from the corresponding external data source through each target MCP service; Each of the target data is input into the trained large language model to obtain the software compilation configuration table output by the trained large language model; Compile the target software according to the software compilation configuration table.

2. The method of claim 1, wherein, Before compiling the target software according to the software compilation configuration table, the process also includes: Based on the feedback results, the correction information for the software order information is determined, and the feedback results are the error reason information for the software compilation configuration table; Based on the correction information, update the software order information to obtain the updated software order information; After obtaining the updated software order information, proceed to the following step: input the software order information into the trained large language model to obtain the data collection information output by the trained large language model.

3. The method of claim 1, wherein, The trained large language model is used to perform semantic analysis on the software order information to determine data requirement information; based on the data requirement information and the stored external data source information, it is determined whether to collect external information. If it is determined that external information needs to be collected, then the data collection information is determined and output based on the data requirement information.

4. The method of claim 1, wherein, The step of obtaining target data from the corresponding external data source through each target MCP service based on the data collection information includes: Based on the target MCP service information of the data collection information, the corresponding target MCP service is determined; For each of the target MCP services, the service protocol of the target MCP service is used to communicate with the corresponding target external data source to obtain the target data corresponding to the data type being collected; The data acquisition information includes at least one type of data to be acquired and the corresponding target MCP service information.

5. The method of claim 2, wherein, The step of determining the correction information for the software order information based on the feedback results includes: Determine the semantic matching information between the feedback result and the software order information; The correction information is determined based on the semantic matching information.

6. The method according to any one of claims 1 to 5, characterized in that, The step of compiling the target software according to the software compilation configuration table includes: The software compilation configuration table is analyzed to generate a compilation task queue and determine the compilation toolchain; The target software is generated using the compilation toolchain based on the compilation task queue.

7. The method of claim 5, wherein, The external data sources include order information data sources, customer management information data sources, email information data sources, compilation and configuration history information data sources, product information data sources, and software specification management information data sources. 8.A software configuration compiling apparatus based on a large language model, characterized in that, include: The large language model module is used to input software order information into a trained large language model and obtain data collection information output by the trained large language model; It is also used to input each target data into the trained large language model to obtain the software compilation configuration table output by the trained large language model; The acquisition module is used to acquire target data from the corresponding external data source through each target MCP service based on the data acquisition information. The compilation module is used to compile the target software according to the software compilation configuration table.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images