Large language model driven flexible manufacturing system modularization intelligent programming method and system

Abstract

The invention discloses a flexible manufacturing system modularization intelligent programming method driven by a large language model, equipment and a medium. The method comprises a task decomposition step, a manufacturing subtask single-step description generation step and a process generation step. Wherein in the task decomposition step, step-by-step tasks are generated by using a large model according to user task description input by a user; in the manufacturing sub-task single-step description generation step, manufacturing sub-task single-step description is generated for each manufacturing sub-task in the step-by-step task by using a large model; in the process generation step, a complete description of a manufacturing process is generated by using a large model according to single-step descriptions of a plurality of manufacturing sub-tasks. According to the method, the powerful natural language understanding and generating capacity of the large language model is utilized, and automatic planning of the whole manufacturing process can be completed through the large language model only by designing appropriate task prompts. According to the method, detailed steps of the manufacturing process can be rapidly generated, interactive iteration with engineers can be carried out, and the interpretability, flexibility and adaptability of the planning process are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of development process design, and in particular to a componentized intelligent programming method, device and medium for a flexible manufacturing system driven by a large language model. Background Art

[0002] In today's rapidly developing Industrial 5.0 era, the manufacturing industry is undergoing a profound transformation. The core of this transformation is the shift from the traditional standardized, large-scale production model to a more flexible and changeable personalized, small-batch production method. This transformation is not only a challenge to the existing manufacturing system, but also a major test of future manufacturing capabilities. In order to meet the growing personalized needs of consumers while maintaining the competitiveness of the company, manufacturers must build an intelligent manufacturing system that can quickly adjust the configuration of the production line and efficiently handle various customized orders.

[0003] In this context, automatic planning in the manufacturing process becomes crucial. It not only affects the delivery speed of the final product, but is also directly related to production efficiency, product quality, cost control and other aspects. An efficient automated planning system can significantly shorten the cycle time from product design to market, improve work efficiency by optimizing resource allocation, and ensure that every production link meets the highest standards, thereby providing customers with high-quality products and services. In addition, such a system can also help companies make more flexible cost management decisions when facing external factors such as fluctuations in raw material prices.

[0004] However, most manufacturing companies still rely mainly on the experience and expertise of human engineers to plan the manufacturing process. Although this method has played an important role in the past, its limitations are gradually emerging in the current unpredictable market environment: on the one hand, manual planning is time-consuming and inefficient; on the other hand, the error rate caused by human factors is relatively high, making it difficult to ensure a consistent level of quality. More importantly, when market demand changes dramatically, traditional manual planning methods often fail to respond in a timely manner, which undoubtedly poses a great challenge to companies. Therefore, the development and application of more intelligent and adaptive automated planning technologies has become the key to promoting the transformation and upgrading of the manufacturing industry. Summary of the invention

[0005] In view of this, the embodiment of the present invention provides a flexible manufacturing system component-based intelligent programming method, device and medium driven by a large language model.

[0006] The first aspect of the present invention provides a component-based intelligent programming method for a flexible manufacturing system driven by a large language model, comprising a task decomposition step, a manufacturing subtask single-step description generation step, and a process generation step;

[0007] The task decomposition step uses a large model to generate step-by-step tasks according to the user task description input by the user; the step-by-step tasks include multiple manufacturing subtasks;

[0008] The manufacturing subtask single-step description generating step uses the large model to generate a manufacturing subtask single-step description for each manufacturing subtask in the step-by-step task; the manufacturing subtask single-step description is used to explain the manufacturing function of the manufacturing subtask associated with the manufacturing subtask;

[0009] The process generation step uses the large model to generate a complete description of the manufacturing process based on the single-step descriptions of multiple manufacturing subtasks.

[0010] Furthermore, it is characterized in that the task decomposition step specifically includes the following steps:

[0011] Receiving a user task description input by a user, and establishing a manufacturing task order according to the user task description; the manufacturing task order includes all manufacturing functions that may be required by the task description;

[0012] Processing the user task description using a large language model to generate multiple manufacturing subtasks to form a step-by-step task; the manufacturing subtasks are used to describe the manufacturing functions included in the manufacturing task order and the manufacturing units that implement the manufacturing functions;

[0013] Receive a user's confirmation request for the step-by-step task; when the user accepts the step-by-step task, execute the step of generating a single-step description of the manufacturing subtask, and add the step-by-step task to the training data set of the large language model; when the user rejects the step-by-step task, return to the step of processing the user's task description using the large language model, and regenerate the step-by-step task.

[0014] Furthermore, each of the manufacturing units is associated with one or more manufacturing subtasks; and each of the manufacturing subtasks is associated with one or more manufacturing functions.

[0015] Furthermore, the manufacturing subtask single-step description generation step specifically includes the following steps:

[0016] Generate a single-step description of each manufacturing subtask using a large language model; each manufacturing subtask includes a manufacturing function in the manufacturing subtask corresponding to the manufacturing subtask, a dependency required by the manufacturing function, and an output content of the manufacturing function;

[0017] Receive a user's confirmation request for the single-step description of the manufacturing subtask; when the user accepts the single-step description of the manufacturing subtask, execute the process generation step, and add the single-step description of the manufacturing subtask to the training data set of the large language model; when the user rejects the single-step description of the manufacturing subtask, return to the step of generating the single-step description of the manufacturing subtask for each of the manufacturing subtasks using the large language model, and regenerate the step-by-step task.

[0018] Furthermore, the dependency required by the manufacturing function refers to the parameters of the manufacturing function associated with the manufacturing order and the output content associated with other manufacturing functions.

[0019] Furthermore, the process generation step specifically includes the following steps:

[0020] Using a large language model to establish an interface relationship and a content interaction relationship between manufacturing functions associated with multiple manufacturing subtasks according to the single-step description of the manufacturing subtask; the interface relationship is used to describe the interface for realizing data interaction between manufacturing functions; the content interaction relationship is used to describe the specific output content of data interaction between manufacturing functions;

[0021] Generate a complete description of the manufacturing process based on the interface relationship and content interaction relationship using a large language model;

[0022] Receive a user's request for confirmation of the complete description; when the user accepts the complete description, use the generated complete description as the manufacturing process, and add the complete description to the training data set of the large language model; when the user rejects the complete description, return to the step of using the large language model to generate a complete description of the manufacturing process according to the interface relationship and content interaction relationship, and regenerate the complete description.

[0023] Furthermore, before using the large language model to generate a complete description of the manufacturing process according to the interface relationship and the content interaction relationship, the following steps are also included:

[0024] The large language model is prompted with a preset manufacturing process template, so that the large language model generates a complete description of the manufacturing process according to the manufacturing process template.

[0025] Furthermore, the method further comprises the following steps:

[0026] Encapsulate a finite state machine in each manufacturing subtask;

[0027] When executing the complete description of the manufacturing process, the execution state of each manufacturing function is obtained through the finite state machine encapsulated in the manufacturing subtask;

[0028] Based on the execution state obtained from the finite state machine, determine whether there are any errors in the complete description of the current execution.

[0029] A second aspect of the present invention provides an electronic device, including a processor and a memory;

[0030] The memory is used to store programs;

[0031] The processor executes the program to implement the large language model-driven flexible manufacturing system component-based intelligent programming method.

[0032] A third aspect of the present invention provides a computer-readable storage medium storing a program, wherein the program is executed by a processor to implement the component-based intelligent programming method for a flexible manufacturing system driven by a large language model.

[0033] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0034] The embodiments of the present invention have the following beneficial effects: The embodiments of the present invention are a componentized intelligent programming method, device and medium for flexible manufacturing systems driven by a large language model. The large language model can automatically plan the entire manufacturing process by simply designing appropriate task prompts to solve the above-mentioned problems. The method of the present invention can quickly generate detailed steps of the manufacturing process, and can interactively iterate with engineers to improve the interpretability, flexibility and adaptability of the planning process, thereby realizing the automatic conversion from demand description to executable manufacturing process. The present invention is widely used in manufacturing process planning in the industry in the era of Industry 5.0.

[0035] Additional aspects and advantages of the present invention will be given in part in the following description, and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 It is a basic flow chart of a component-based intelligent programming method for a flexible manufacturing system driven by a large language model of the present invention.

[0038] Figure 2 It is a detailed flow chart of a component-based intelligent programming method for a flexible manufacturing system driven by a large language model of the present invention.

[0039] Figure 3 It is a schematic diagram of the relationship between manufacturing units, manufacturing subtasks and manufacturing functions in the task decomposition step of the present invention.

[0040] Figure 4 It is a schematic diagram of the specific execution relationship between the manufacturing subtasks of the present invention.

[0041] Figure 5 It is a schematic diagram of the functional code blocks generated in the single-step description generation step of the manufacturing subtask of the present invention.

[0042] Figure 6 It is a schematic diagram of a specific manufacturing subtask of a robot arm moving component, describing the functional code block in a single step.

[0043] Figure 7 It is a schematic diagram of errors that may be encountered in the job planning method of the present invention.

[0044] Figure 8 It is a structural schematic diagram of an electronic device of the present invention.

[0045] Fig. 9 It is a schematic diagram of the structure of a computer-readable storage medium of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] In today's rapidly developing Industry 5.0 era, intelligent manufacturing systems are facing a shift from standardized, mass production to personalized, small-batch production. This shift requires the manufacturing process to be highly flexible and adaptable in order to quickly respond to rapid changes in market demand. In this context, automatic planning of the manufacturing process becomes particularly important because it is directly related to production efficiency, product quality, and cost control. Currently, the planning of the manufacturing process mainly relies on the experience and knowledge of human engineers, which is inefficient, error-prone, and difficult to adapt to the rapid changes in market demand.

[0048] Although machine learning and artificial intelligence technologies have made some progress in manufacturing process planning in recent years, these methods usually require a large amount of training data and scenario-specific knowledge and have poor versatility. In addition, the manufacturing processes generated by existing methods usually lack interpretability, require manual post-processing, and are difficult to deal with complex multi-equipment collaborative planning problems. These problems have seriously restricted the widespread application of automatic manufacturing process planning technology in the industrial sector, and it is difficult to meet the requirements of the flexibility and adaptability of manufacturing processes in the Industrial 5.0 era.

[0049] To solve the above problems, the first embodiment of the present invention provides a component-based intelligent programming method for a flexible manufacturing system driven by a large language model. Figure 1 As shown, the method of the embodiment of the present invention mainly includes a task decomposition step, a manufacturing subtask single-step description generation step, and a process generation step.

[0050] The task decomposition step is used to generate step-by-step tasks according to the user task description input by the user. The manufacturing subtask single-step description generation step is used to generate a manufacturing subtask single-step description for each manufacturing subtask in the step-by-step task. The process generation step uses the large model to generate a complete description of the manufacturing process according to multiple manufacturing subtask single-step descriptions.

[0051] The detailed process of the embodiment of the present invention is as follows Figure 2 The method proposed in the embodiment of the present invention can automatically parse the manufacturing task workflow generation framework of the user's manufacturing order requirements through a large language model, and through the framework, heterogeneous industrial instances can be simultaneously called and integrated into the workflow.

[0052] The implementation process of each step of the present invention is described in detail below.

[0053] Task decomposition step: The task decomposition step in the embodiment of the present invention specifically includes the following steps:

[0054] S101. Receive a user task description input by a user, and create a manufacturing task order according to the user task description.

[0055] The task description expressed in natural language input by the user cannot be used directly as a manufacturing process, so the user input needs to be understood by a large language model. The large language model used in the embodiment of the present invention refers to a type of large model in the field of natural language processing (Natural Language Processing, NLP), which is usually used to process text data and understand natural language. The main feature of this type of large language model is that they are trained on a large-scale corpus to learn various grammatical, semantic and contextual rules of natural language. Specific large language models include GPT series (OpenAI), Bard (Google), Wenxin Yiyan (Baidu), etc.

[0056] In some embodiments, the task requirements input by the user may have a specific format, which is the same as the training set format for training the large language model, so that the large language model can more easily understand the user task requirements.

[0057] While understanding the task description, the large language model extracts keywords of the manufacturing function based on the keywords in the task description and generates a manufacturing task order. The manufacturing task order contains descriptions of various manufacturing functions to match the manufacturing units provided by the manufacturing service provider. In order to complete the task requirements, the embodiment of the present invention will set up a manufacturing unit library provided by the manufacturing service provider, which includes manufacturing units that realize various manufacturing functions, and use the manufacturing unit as the basic tool for processing task requirements.

[0058] S102. Use a large language model to process the user task description and generate multiple manufacturing subtasks to form a step-by-step task.

[0059] In the embodiment of the present invention, the specific relationship diagram of the manufacturing unit, the manufacturing subtask and the manufacturing unit is as follows: Figure 3 In the embodiment of the present invention, each manufacturing unit is associated with one or more manufacturing subtasks; each manufacturing subtask is associated with one or more manufacturing functions.

[0060] Specifically, for each manufacturing subtask t in the entire step-by-step task T i , whose properties are defined by the following formula:

[0061] t i ={desc,paratrans}

[0062] Among them, desc describes the manufacturing function to be completed by the manufacturing subtask by defining the single-step description of the manufacturing subtask, and paratrans represents the parameters received from the adjacent manufacturing subtask and the parameters transmitted to other subtasks after being processed by the internal algorithm. i and its adjacent subtask t i+1 ,t i-1 In the process, the subtasks are interconnected through executable parameters in paratrans. Since a manufacturing subtask consists of multiple manufacturing functions, for example, the subtask of robot object grasping requires a combination of servo motor and gripper control, etc., and the manufacturing unit is capable of performing various subtasks. Therefore, in the embodiment of the present invention, a consumer product manufacturing order needs to arrange and combine multiple subtasks to generate a task workflow that can complete the order. The manufacturing service provider must coordinate the execution logic of the manufacturing functions to derive a complete step-by-step task sequence.

[0063] since Figure 3It can be found that, since each manufacturing subtask in the embodiment of the present invention is associated with only one manufacturing unit, each manufacturing subtask will only call one manufacturing unit for manufacturing during execution, thus avoiding the situation where multiple manufacturing units interfere with each other and cause the manufacturing subtask to fail to execute. The specific granularity of the manufacturing subtask division is determined according to the detail level of the task steps stored in the preset knowledge base. By providing manufacturing subtasks with the same granularity to train the large language model during the training phase of the large language model, the detail level of the manufacturing subtasks output by the large language model can be maintained at the same level.

[0064] For example, when a user inputs a task description such as "Use a depth camera and a robotic arm to perform an object grabbing process," the following manufacturing subtasks can be obtained through the task decomposition steps: "Step 1: In order to facilitate object identification, a depth camera is required to locate the object. Step 2: ..." It can be seen that the task decomposition steps of the embodiment of the present invention will extrapolate the user's concise input into task steps with the same level of detail as the steps in the knowledge base, generate multiple manufacturing subtasks, and thus facilitate the execution of subsequent steps.

[0065] S103. Receive a user's confirmation request for the step-by-step task; when the user accepts the step-by-step task, execute the step of generating a single-step description of the manufacturing subtask, and add the step-by-step task to the training data set of the large language model; when the user rejects the step-by-step task, return to the step of processing the user's task description using the large language model, and regenerate the step-by-step task.

[0066] After the large language model outputs the step-by-step tasks, the embodiment of the present invention can display the step-by-step tasks generated by the model to the user. If the user believes that the manufacturing function implemented by the task is incomplete or there is a conflict, the distributed task output by the large language model can be rejected. The large language model will establish multiple rounds of dialogue with the user, gradually complete the decomposition of the task process and generate manufacturing subtasks, and finally obtain the step-by-step task output accepted by the user. At the same time, for the step-by-step task output accepted by the user, it is added to the training data set of the large language model for the model to optimize the subsequent task description decomposition and step-by-step task generation work.

[0067] The step of generating a single-step description of a manufacturing subtask: The step of generating a single-step description of a manufacturing subtask in the embodiment of the present invention specifically includes the following steps:

[0068] S201. Generate a single-step description of each manufacturing subtask using a large language model.

[0069] In the embodiment of the present invention, the manufacturing subtasks generated by the large language model have specific execution relationships. Figure 4As shown in the figure, the execution relationship between manufacturing subtasks includes sequential execution, conditional execution and parallel execution. Sequential execution means starting from the first manufacturing subtask at the beginning, executing each manufacturing subtask in sequence until the end, without conditional execution and parallel execution process in between. Conditional execution means starting from the first manufacturing subtask at the beginning, executing a single or multiple branch tasks according to the conditional judgment results until the end. Parallel tasks mean starting from the first manufacturing subtask at the beginning, executing in order to the manufacturing subtasks related to the parallel judgment, and executing the sequel of all parallel branches synchronously. After all parallel branches are completed, the task ends.

[0070] since Figure 3 It can be found that the execution of each manufacturing function also depends on external dependencies, which may come from the results of the execution of other functions, or may be based on the internal parameter injection of the consumer manufacturing order, etc. Therefore, after receiving the step-by-step tasks of the previous step, the embodiment of the present invention formally describes the parameter transmission of each step through a large language model. These parameter transmissions encapsulate the dependencies required for the manufacturing functions to execute the subtasks, as well as the outputs generated by executing these tasks, and finally obtain a Figure 5 The functional code block shown.

[0071] Specifically, the function code block includes the content of the dependent parameters involved in the manufacturing subtask and the internal algorithm function responsible for its implementation. For example, calling the robot arm movement function requires the input of the six-dimensional coordinate data of the specified movement to a certain position. And the function of the robot arm movement function needs to be executed in sequence.

[0072] In the embodiment of the present invention, the generated function code block Paratrans is composed of an API and a DATA interface. The API interface is a way to call a certain function of the function code block, and the DATA interface is used for data transmission between function code blocks. For example, for a task that requires a robotic arm to perform, the moveline linear movement function API of the robotic arm function code block is used, and the 6DoF coordinates are passed in to move the robotic arm end effector to the specified position. The key aspect of this stage is to effectively process the input parameters and generate the parameters required by other function code blocks after internal operations. The specific example of the robotic arm function code block is as follows: Figure 6 shown.

[0073] S202. Receive a user's confirmation request for the single-step description of the manufacturing subtask; when the user accepts the single-step description of the manufacturing subtask, execute the process generation step, and add the single-step description of the manufacturing subtask to the training data set of the large language model; when the user rejects the single-step description of the manufacturing subtask, return to the step of generating the single-step description of the manufacturing subtask for each of the manufacturing subtasks using the large language model, and regenerate the step-by-step task.

[0074] After the large language model outputs a single-step description of a manufacturing subtask, the embodiment of the present invention can display the single-step description of the manufacturing subtask generated by the model to the user. If the user believes that the manufacturing function implemented by the single-step description is incomplete or there is a conflict, the single-step description output by the large language model can be rejected. The large language model will establish multiple rounds of dialogue with the user, and the user will manually adjust the model-generated code block to finally obtain the single-step description output of the manufacturing subtask accepted by the user. At the same time, for the single-step description output of the manufacturing subtask accepted by the user, it is added to the training data set of the large language model for the model to optimize the subsequent single-step description generation work of the manufacturing subtask.

[0075] Process generation step: In the embodiment of the present invention, the process generation step specifically includes the following steps:

[0076] S301. Use a large language model to establish interface relationships and content interaction relationships between manufacturing functions associated with multiple manufacturing subtasks based on single-step descriptions of manufacturing subtasks.

[0077] The focus of the process generation step in the embodiment of the present invention is to ensure the information interaction between the current function code block and other function code blocks in each subtask step. Paratrans is divided into two parts: [API, Data]; the interface relationship API is used to describe the interface for realizing data interaction between manufacturing functions; the content interaction relationship DATA is used to describe the specific output content of data interaction between manufacturing functions. By establishing seamless parameter interaction between manufacturing subtasks and other manufacturing subtasks, it is ensured that the entire task is executed smoothly and without errors under the assumption that it has been divided into subtasks. In the workflow generation stage, the large language model should not only consider the parameter transfer between subtasks, but also understand the specific requirements in the task description in order to establish parameter transfer relationships between all subtasks. This involves API interaction and DATA interaction between adjacent function code blocks to ensure that task execution meets the expected results.

[0078] S302. Generate a complete description of the manufacturing process based on the interface relationship and the content interaction relationship using a large language model.

[0079] After the relationship between manufacturing subtasks is established, the execution results of each functional code block will be transmitted to the API interface of the subsequent code block through the API interface. After each code block obtains the task execution result from the previous manufacturing subtask, it uses the necessary function encapsulated in the code block to process and obtain further execution results. The large language model can generate a complete description of the manufacturing process based on the interface relationship between each manufacturing subtask for use by front-line manufacturing personnel.

[0080] In some embodiments, before the large language model generates a complete description of the manufacturing process, a preset manufacturing process template can be first imported so that the large language model generates a complete description of the manufacturing process according to the manufacturing process template. The manufacturing process template is a manufacturing process description format determined by the manufacturer, which is easy for the manufacturer to understand and interpret. This step can effectively utilize existing knowledge and experience to generate a coherent and practical task workflow, thereby improving the efficiency and accuracy of task execution.

[0081] S303. Receive the user's confirmation request for the complete description; when the user accepts the complete description, use the generated complete description as the manufacturing process, and add the complete description to the training data set of the large language model; when the user rejects the complete description, return to the step of using the large language model to generate a complete description of the manufacturing process based on the interface relationship and content interaction relationship, and regenerate the complete description.

[0082] After the large language model outputs a complete description of the manufacturing process, the embodiment of the present invention can show the user the complete description generated by the model. If the user believes that the manufacturing function implemented by the complete description is incomplete or there is a conflict, the complete description output by the large language model can be rejected. The large language model will establish multiple rounds of dialogue with the user and adjust the output of a new complete description based on user feedback, and finally obtain a complete description output accepted by the user. At the same time, the complete description output accepted by the user is added to the training data set of the large language model for the model to optimize the subsequent complete description generation work.

[0083] In actual operation, it is found that the step-by-step tasks, single-step descriptions, and complete descriptions generated by large language models are not always executable, and there may be various errors. Most of the errors can be summarized as follows: Figure 7 Types shown:

[0084] Type (1) error: Deadlock may occur in the complete description. After the executable loop condition of the manufacturing subtask is met, the current manufacturing subtask execution loop needs to be exited. However, the erroneous process will continue to iterate the current cycle until a timeout occurs, instead of continuing to execute subsequent processes.

[0085] Type (2) errors: Data transfer anomalies manifest themselves in the execution sequence, where discrepancies are observed in the information exchanged between functions. These errors include incorrect data input identifiers and misaligned compatibility of data formats. For example, a robotic arm designed to manipulate six-dimensional coordinate data may be fed image data from a camera that cannot interpret the data.

[0086] Class (3) error: Encountering incorrect generation of sequence API input and output, especially in conditional and parallel processes. The corresponding sequence API for conditional steps and parallel processing must be called to execute the corresponding process. It is not feasible to directly transition from standard functions to conditional or parallel processes, which will cause disruption of the expected process flow.

[0087] Type (4) Error: Failure to perform a step in the executable sequence results in incomplete execution of the process. This omission may result in truncation of the workflow, compromising the overall integrity and functionality of the system.

[0088] In this regard, the embodiment of the present invention uses a finite state machine to monitor the execution process of each manufacturing subtask, which specifically includes the following steps:

[0089] S401. Encapsulate the finite state machine in each manufacturing subtask;

[0090] S402. When executing the complete description of the manufacturing process, the execution status of each manufacturing function is obtained through the finite state machine encapsulated in the manufacturing subtask;

[0091] S403. Determine whether there is an error in the complete description of the current execution according to the execution status obtained from the finite state machine.

[0092] For a step-by-step task T = {t1, t2, ... t n}, the embodiment of the present invention injects the finite state machine into the functional code block corresponding to each manufacturing subtask. In the state of each finite state machine, 0 indicates that the current functional code block has not been executed, and 1 indicates that the current functional code block has been executed. By deploying finite state machines in manufacturing subtasks, the embodiment of the present invention only needs to maintain a state machine controller, which can execute the corresponding finite state machine according to the step-by-step task process. When the controller executes a certain finite state machine, the state transfer condition is triggered, S∶0→1. When the manufacturing subtask is completed, S:1→0. At the same time, the executed finite state machines are listed to record the executed finite state machines and the number of executions of each finite state machine.

[0093] In summary, the embodiments of the present invention achieve the transformation of manufacturing process planning from manual experience to automation and intelligence, thereby improving planning efficiency; enhancing the flexibility and adaptability of manufacturing process planning, enabling it to quickly respond to rapid changes in market demand; reducing errors that may occur in manually designed manufacturing process steps, thereby improving the quality of manufacturing process planning. In addition, the embodiments of the present invention also enhance the user's ability to participate in manufacturing process planning and enhance user satisfaction through interactive design; reducing the dependence of manufacturing process planning on professional knowledge and skills, thereby lowering the technical threshold. Finally, the embodiments of the present invention achieve rapid response to market demand, enhance the market competitiveness of enterprises, and are widely used in the manufacturing process design of enterprises.

[0094] Figure 8 : is a schematic diagram of the structure of the electronic device proposed in the second embodiment of the present invention. In this embodiment, the memory stores program instructions for implementing the large language model-driven flexible manufacturing system component-based intelligent programming method of any of the above embodiments. The processor is used to execute the program instructions stored in the memory to perform large language model-driven flexible manufacturing system component-based intelligent programming. Among them, the processor can also be called CPU (Central Processing Unit). The processor may be an integrated circuit chip with signal processing capabilities. The processor can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0095] The contents of the method in the first embodiment of the present invention are all applicable to the electronic device embodiment. The functions specifically implemented by the electronic device embodiment are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method.

[0096] Fig. 9 The schematic diagram of the structure of the computer-readable storage medium of the third embodiment of the present invention. The computer-readable storage medium of the fourth embodiment of the present invention stores program instructions that can implement the above-mentioned large language model-driven flexible manufacturing system componentized intelligent programming method, wherein the program instructions can be stored in the above-mentioned storage medium in the form of a software product, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment of the present invention. The aforementioned computer-readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes, or terminal devices such as computers, servers, mobile phones, tablets, etc.

[0097] The contents of the method in the first embodiment of the present invention are all applicable to the computer-readable storage medium embodiment. The functions specifically implemented by the computer-readable storage medium embodiment are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method.

[0098] This embodiment also provides a computer program product. When the computer program product runs on a computer, it enables the computer to execute the above-mentioned related steps to implement the large language model-driven flexible manufacturing system component-based intelligent programming method provided in the above embodiment.

[0099] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0100] Those skilled in the art will appreciate that the modules in the devices in the embodiments of the present invention may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments of the present invention may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including corresponding claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including corresponding claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0101] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0102] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0103] In addition, each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. In particular, for embodiments such as devices and equipment, since they are basically similar to method embodiments, the relevant parts can refer to the partial description of the method embodiments. The embodiments of the devices and equipment described above are merely schematic, wherein the modules, units, etc. described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed in multiple places, such as nodes of a system network. Specifically, some or all of the modules and units may be selected according to actual needs to achieve the purpose of the above-mentioned embodiment scheme. Those skilled in the art can understand and implement it without paying creative labor.

[0104] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0105] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0106] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the present embodiment. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of the features. In the description of the present invention, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.

[0107] In the embodiments of the present invention, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present invention may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context in the specific embodiment.

[0108] Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and cannot be construed as limitations of the present invention, and those of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention. Those skilled in the art will readily come to think of other embodiments of the present invention after considering the specification and practicing the present invention. This application is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art that are not disclosed in the present invention. The specification and embodiments are intended to be exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

Claims

1. A component-based intelligent programming method for flexible manufacturing systems driven by a large language model, characterized in that: It includes the steps of task decomposition, single-step description generation of manufacturing subtasks and process generation; The task decomposition step uses a large model to generate step-by-step tasks according to the user task description input by the user; the step-by-step tasks include multiple manufacturing subtasks; The manufacturing subtask single-step description generating step uses the large model to generate a manufacturing subtask single-step description for each manufacturing subtask in the step-by-step task; the manufacturing subtask single-step description is used to explain the manufacturing function associated with the manufacturing subtask; The process generation step uses the large model to generate a complete description of the manufacturing process based on the single-step descriptions of multiple manufacturing subtasks.

2. According to claim 1, a large language model driven flexible manufacturing system component-based intelligent programming method is characterized in that: The task decomposition step specifically includes the following steps: Receiving a user task description input by a user, and establishing a manufacturing task order according to the user task description; the manufacturing task order includes all manufacturing functions that may be required by the task description; Processing the user task description using a large language model to generate multiple manufacturing subtasks to form a step-by-step task; the manufacturing subtasks are used to describe the manufacturing functions included in the manufacturing task order and the manufacturing units that implement the manufacturing functions; Receive a user's confirmation request for the step-by-step task; when the user accepts the step-by-step task, execute the step of generating a single-step description of the manufacturing subtask, and add the step-by-step task to the training data set of the large language model; when the user rejects the step-by-step task, return to the step of processing the user's task description using the large language model, and regenerate the step-by-step task.

3. The component-based intelligent programming method for flexible manufacturing systems driven by a large language model according to claim 2 is characterized in that: Each of the manufacturing units is associated with one or more manufacturing subtasks; each of the manufacturing subtasks is associated with one or more manufacturing functions.

4. The component-based intelligent programming method for flexible manufacturing systems driven by a large language model according to claim 1 is characterized in that: The manufacturing subtask single-step description generation steps specifically include the following steps: Generate a single-step description of each manufacturing subtask using a large language model; each manufacturing subtask includes a manufacturing function in the manufacturing subtask corresponding to the manufacturing subtask, a dependency required by the manufacturing function, and an output content of the manufacturing function; Receive a user's confirmation request for the single-step description of the manufacturing subtask; when the user accepts the single-step description of the manufacturing subtask, execute the process generation step, and add the single-step description of the manufacturing subtask to the training data set of the large language model; when the user rejects the single-step description of the manufacturing subtask, return to the step of generating the single-step description of the manufacturing subtask for each of the manufacturing subtasks using the large language model, and regenerate the step-by-step task.

5. The method for component-based intelligent programming of a flexible manufacturing system driven by a large language model according to claim 4 is characterized in that: The dependency required by the manufacturing function refers to the parameters of the manufacturing function associated with the manufacturing order and the output content associated with other manufacturing functions.

6. The component-based intelligent programming method for flexible manufacturing systems driven by a large language model according to claim 1 is characterized in that: The process generation step specifically includes the following steps: Using a large language model to establish an interface relationship and a content interaction relationship between manufacturing functions associated with multiple manufacturing subtasks according to the single-step description of the manufacturing subtask; the interface relationship is used to describe the interface for realizing data interaction between manufacturing functions; the content interaction relationship is used to describe the specific output content of data interaction between manufacturing functions; Generate a complete description of the manufacturing process based on the interface relationship and content interaction relationship using a large language model; Receive a user's request for confirmation of the complete description; when the user accepts the complete description, use the generated complete description as the manufacturing process, and add the complete description to the training data set of the large language model; when the user rejects the complete description, return to the step of using the large language model to generate a complete description of the manufacturing process according to the interface relationship and content interaction relationship, and regenerate the complete description.

7. The method for component-based intelligent programming of a flexible manufacturing system driven by a large language model according to claim 6, characterized in that: Before using the large language model to generate a complete description of the manufacturing process according to the interface relationship and the content interaction relationship, the following steps are also included: The large language model is prompted with a preset manufacturing process template, so that the large language model generates a complete description of the manufacturing process according to the manufacturing process template.

8. The method for component-based intelligent programming of a flexible manufacturing system driven by a large language model according to claim 1, characterized in that: The following steps are also included: Encapsulate a finite state machine in each manufacturing subtask; When executing the complete description of the manufacturing process, the execution state of each manufacturing function is obtained through the finite state machine encapsulated in the manufacturing subtask; Based on the execution state obtained from the finite state machine, determine whether there are errors in the complete description of the current execution.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement a large language model-driven flexible manufacturing system component-based intelligent programming method as described in any one of claims 1-8.

Images