Method and device for flexible construction of industrial production flows

Abstract

Embodiments of the present disclosure provide a flexible construction method and device for an industrial production process. The method is applied to the field of artificial intelligence and industrial software technology, and comprises the following steps: obtaining an industrial production process requirement; inputting the industrial production requirement description into a pre-trained construction model to obtain a corresponding industrial production process description; wherein the industrial production process description comprises micro-processes in the form of Token, and connection relationships and timing configurations between the micro-processes; and constructing a flexible industrial production management software according to the industrial production process description. In this way, the optimization construction of the industrial production process can be automatically completed according to the natural language prompts of the user and other environmental constraints and prerequisites, the flexible industrial production management software is constructed according to the production process, and an industrial software version suitable for the current production requirement and production environment is obtained.

Description

Technical Field

[0001] This disclosure relates to the fields of artificial intelligence and industrial software, and in particular to methods and apparatus for flexibly constructing industrial production processes. Background Technology

[0002] Traditional industrial software encompasses numerous categories, each with its own focus. PLM (Product Lifecycle Management) includes components, Bill of Materials (BOM), products, and projects; ERP (Enterprise Resource Planning) includes order management, materials management, process management, and work order management; and MES (Manufacturing Execution System) includes process control, defect tracking, material tracking, and manpower tracking. These types of industrial software are widely used in all aspects of industrial production, significantly contributing to increased efficiency and reduced costs in modern industry.

[0003] However, existing industrial software suffers from two fatal problems that severely hinder the development and progress of the industrial software industry. Regardless of the specific category, the core of traditional industrial software lies in the selection and combination of various "micro-processes" (or "microservices") modules and the overall system optimization strategy. Due to historical reasons, traditional industrial software is diverse, with significant conflicting objectives and overlapping functions. Therefore, the selection and combination methods and optimization strategies for these "micro-processes" (or "microservices") modules are difficult to obtain due to technological protection; furthermore, because these modules are not tailored to actual production environments, they struggle to meet users' actual needs.

[0004] For example, suppose a factory receives an order to produce 100 units of product A. Traditional industrial software requires the activation of multiple systems to process this order. PLM (Product Lifecycle Management) includes information on components, Bill of Materials (BOM), products, and projects; ERP (Enterprise Resource Planning) includes order management, material management, process management, and work order management; and MES (Manufacturing Execution System) includes process control, defect tracking, material tracking, and manpower tracking. The number of "micro-processes" involved is enormous, with overlapping functions and complex interfaces between different industrial software systems. Furthermore, the flexibility in process selection is limited, resulting in a low degree of alignment with actual needs and making it difficult to meet the demands of modern flexible industrial production.

[0005] In addition, modern industrial enterprises use a large number of advanced information technology methods to enhance production efficiency, including (but not limited to) IoT, CAD, CAE, vision, AR, etc. How to integrate these technologies with traditional industrial software is also a difficult problem that users need to solve. Summary of the Invention

[0006] This disclosure provides a flexible construction method, apparatus, equipment, and storage medium for industrial production processes, solving the problems of traditional industrial software being cumbersome, with significant target conflicts and functional overlaps. Therefore, the selection and combination methods and optimization strategies for "micro-process" modules are difficult to obtain due to technical protection limitations, and also because these modules are not tailored to actual production environments, making it difficult to adapt to users' actual needs.

[0007] According to a first aspect of this disclosure, a flexible construction method for industrial production processes is provided. The method includes: acquiring industrial production process requirements; inputting the industrial production requirement description into a pre-trained construction model to obtain a corresponding industrial production process description; wherein the industrial production process description includes micro-processes in token form, as well as the connection relationships and timing configurations between the micro-processes; and constructing flexible industrial production management software according to the industrial production process description.

[0008] According to a second aspect of this disclosure, a flexible construction device for industrial production processes is provided. The device includes: a demand acquisition module for acquiring industrial production process demands; an industrial production process description generation module for inputting the industrial production demand description into a pre-trained construction model to obtain a corresponding industrial production process description; wherein the industrial production process description includes micro-processes in the form of tokens, and the connection relationships and timing configurations between the micro-processes; and a software construction module for constructing flexible industrial production management software according to the industrial production process description.

[0009] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0010] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the methods according to the first and / or second aspects of this disclosure.

[0011] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 A flowchart illustrating a flexible construction method for an industrial production process according to an embodiment of the present disclosure is shown; Figure 2 A flowchart illustrating a training method for constructing a model of an industrial production process according to an embodiment of the present disclosure is shown. Figure 3 A block diagram of a flexible construction apparatus for an industrial production process according to an embodiment of the present disclosure is shown; Figure 4 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0014] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0015] Figure 1 A flowchart of a flexible construction method 100 for an industrial production process according to an embodiment of the present disclosure is shown.

[0016] In box 102, obtain the industrial production process requirements; In some embodiments, the industrial production process requirements are in natural language form.

[0017] In box 104, the industrial production demand description is input into the pre-trained construction model to obtain the corresponding industrial production process description; wherein, the industrial production process description includes micro-processes in the form of tokens, as well as the connection relationship and timing configuration between each micro-process.

[0018] In box 106, flexible industrial production management software is constructed according to the industrial production process description.

[0019] In some embodiments, the model is trained through the following steps: In box 202, obtain the industrial production microprocess code; In some embodiments, the initial code for each “microprocess” of different industrial software is obtained.

[0020] The industrial software can be PLM (Product Lifecycle Management), ERP (Enterprise Resource Planning), or MES (Manufacturing Execution System) software; the "micro-processes" can be micro-processes such as "parts information," "BOM information," "product information," and "project information" included in PLM (Product Lifecycle Management), micro-processes such as "order management," "material management," "process management," and "work order management" included in ERP (Enterprise Resource Planning), and micro-processes such as "process control," "defect tracking," "material tracking," and "human resource tracking" included in MES (Manufacturing Execution System).

[0021] In some embodiments, the industrial production process is refined to its individual steps (i.e., the process steps listed on the process card in traditional factory production). These process steps are generally divided into two parts: one part is converted into robot control instructions to control the robot to complete the production task, realizing the physical part of industrial production; the other part is converted into API calls provided by industrial software (or self-developed) to realize the digital part of industrial production.

[0022] In box 204, the industrial production microprocess code is converted into a code vector in token form; In some embodiments, the initial encoding of the "microprocess" is used as the input to the token generation network model, and the embedding encoding of the "microprocess" in the internal space of the token generation network model is used as the output.

[0023] In some embodiments, the token generation network model is an Encoder-Decoder architecture neural network model, which includes an input layer, a projection layer, and an output layer. The token generation network model is trained based on massive amounts of process data accumulated in industrial production sites, using either CBOW or Skip-Gram training methods.

[0024] The dimension of the input layer of the Token generation network model is consistent with the number of "micro-processes" obtained, and the initial encoding of the input "micro-processes" can be expressed using a simple encoding method (such as One-Hot encoding).

[0025] The initial encoding of the input "micro-process" is mapped to the projection layer of the token generation network model through a projection transformation. This layer is the "latent space" of the token generation network model, with a lower dimension compared to the input layer, achieving information compression and compact representation. The parameters of the projection transformation are determined through training. The information from the projection layer is then decoded and transformed to reach the output layer of the token generation network model.

[0026] The output layer of the token generation network model is about the same size as the input layer, and the output layer uses Softmax to perform encoding expression calculations for each "micro-process".

[0027] Ultimately, the token generation network model generates an encoded vector, or token, for each "micro-process" with a dimension equal to the total number of "micro-processes." These tokens are used for further model training. Here, the token is analogous to a "vocabulary" in a large language model. Encoding the tokens constitutes word embedding in the large language model, which involves embedding the tokens into a high-dimensional space and establishing connections between tokens within that space.

[0028] In box 206, industrial production process data is converted into the connection relationships and time sequence configurations between micro-processes in the form of tokens, and the corresponding industrial production requirements are extracted to generate training samples. In some embodiments, the corresponding industrial production demand is expressed in natural language. User needs are extracted from existing industrial process data and described as "questions" in natural language. Known processes in the industrial production process data are set as "answers." The known processes are the connection relationships and timing configurations between micro-processes in the form of tokens.

[0029] In box 208, the large language model is trained based on the training samples.

[0030] The large language model is a Transformer model, and the model training includes two stages: pre-training and post-training.

[0031] The purpose of the pre-training is to familiarize the large language model with the basic components of industrial production processes. Pre-training is based on industrial production process data and employs unsupervised methods, primarily using two strategies: Mask and NSP. Mask uses context to predict a specific step ("micro-process") within the process; NSP predicts stage transitions and time-series nodes. The pre-trained large language model can then understand the basic components and structure of industrial production processes.

[0032] The purpose of post-training is to enable large language models to generate and optimize industrial production processes through "input alignment" techniques. The generation of industrial production processes utilizes a Question / Answer training model and the Supervised FineTuning (SFT) method. This involves extracting industrial production data from existing industrial process data, describing it as a "question" in natural language, and setting known processes in the data as "answers." This process guides the training of a large model, gradually enabling it to automatically generate corresponding industrial production processes based on natural language instructions. The known processes are represented by the connection relationships and timing configurations between micro-processes in the form of tokens.

[0033] The optimization of industrial production processes utilizes a Question / Rational / Answer training model and Reinforcement Learning (RL) methods. This provides a large model with prompts, requiring it to optimize and configure the timing of existing industrial production processes. By setting appropriate reward and punishment mechanisms, the large model is guided through training, gradually acquiring the ability to replace steps in the existing process and adjust its basic direction.

[0034] According to the embodiments of this disclosure, the following technical effects are achieved: Based on the user's natural language prompts and other environmental constraints and prerequisites, it can fully leverage the powerful capabilities of large language models in storage, computation, and reasoning to automatically complete the optimized construction of industrial production processes and output them to the user.

[0035] Users who obtain industrial production process data can leverage mature "modular" or "component-based" strategies to build flexible industrial production management software according to the production process, resulting in an industrial software version suitable for current production needs and environment, which can then be applied in actual production.

[0036] According to one embodiment of this disclosure, the method for flexibly constructing the industrial production process is further described.

[0037] Users only need to input "I need to produce 100 units of product A, please provide a process description" into the large model. The trained large model can then provide the following process description based on the knowledge and experience gained from training on existing data: Project Information — Product Information — ITEM / BOM Information — Material Management (IoT) — Work Order Management — CAD — CAE — Process Control (Vision) — Defect Handling (AR) — Warehousing Information.

[0038] This process breaks away from the disadvantages of traditional industrial software, which is characterized by numerous categories and fragmented operations. It enables global management and scheduling of various "micro-processes," reduces functional overlap, simplifies interface design, and highlights the integrity of the industrial process. On the other hand, it is more closely aligned with user needs and offers greater flexibility.

[0039] If a user discovers that the same product has been manufactured before and there are existing drawings, eliminating the need for a CAD step, then the user only needs to input "We already have drawings, no design is needed, please optimize the process." into the large model, and the large model will then provide the following optimized process description; Project Information — Product Information — ITEM / BOM Information — Material Management (IoT) — Work Order Management — Recipe / Drawing Management — CAE — Process Control (Vision) — Defect Handling (AR) — Warehousing Information.

[0040] Replacing CAD with existing recipe / drawing management "micro-processes" can significantly improve efficiency.

[0041] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0042] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0043] Figure 3 A block diagram of a flexible fabrication apparatus 300 for an industrial production process according to an embodiment of the present disclosure is shown. Figure 3 As shown, the device 300 includes: The requirement acquisition module 302 is used to acquire industrial production process requirements; The industrial production process description generation module 304 is used to input the industrial production demand description into a pre-trained construction model to obtain the corresponding industrial production process description; wherein, the industrial production process description includes micro-processes in the form of tokens, as well as the connection relationships and timing configurations between each micro-process. Software building module 306 is used to build flexible industrial production management software according to the industrial production process description.

[0044] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0045] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0046] Figure 4 A schematic block diagram of an electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0047] Electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in ROM 402 or a computer program loaded into RAM 403 from storage unit 408. RAM 403 can also store various programs and data required for the operation of electronic device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O interface 405 is also connected to bus 404.

[0048] Multiple components in electronic device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of displays, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows electronic device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0049] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as method 100 and method 200. For example, in some embodiments, method 100 and method 200 may be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of method 100 and method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute method 100 or method 200 by any other suitable means (e.g., by means of firmware).

[0050] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0051] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0052] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0053] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including voice input, speech input, or tactile input).

[0054] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0055] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0056] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0057] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for flexibly constructing an industrial production process, comprising: Obtain industrial production process requirements; The industrial production demand description is input into the pre-trained construction model to obtain the corresponding industrial production process description; wherein, the industrial production process description includes micro-processes in the form of tokens, as well as the connection relationship and timing configuration between each micro-process. Develop flexible industrial production management software based on the described industrial production process.

2. The method according to claim 1, wherein, The constructed model is obtained through the following steps: Industrial production process data is converted into the connection relationships and time sequence configurations between micro-processes in the form of tokens, and the corresponding industrial production requirements are extracted to generate training samples. The large language model is trained based on the training samples.

3. The method according to claim 2, wherein, The microprocess in token form is obtained through the following steps: Obtain the microprocess code for industrial production; The industrial production microprocess code is converted into a token-form code vector.

4. The method according to claim 3, wherein, Converting the industrial production microprocess code into a token-form encoding vector includes: The initial encoding of the microprocess is used as the input to the token generation network model, and the embedding encoding of the microprocess in the internal space of the token generation network model is used as the output. The token generation network model is an Encoder-Decoder architecture neural network model.

5. The method according to claim 2, wherein, The large language model is a Transformer model, and the model training includes pre-training and post-training.

6. The method according to claim 5, wherein, The post-training includes the generation and optimization of industrial production processes.

7. The method according to claim 6, wherein, The generation process uses the Question / Answer training mode; the optimization process uses the Question / Rational / Answer training mode.

8. An apparatus for a flexible construction method of an industrial production process, comprising: The requirement acquisition module is used to acquire industrial production process requirements; An industrial production process description generation module is used to input the industrial production demand description into a pre-trained construction model to obtain the corresponding industrial production process description; wherein, the industrial production process description includes micro-processes in the form of tokens, as well as the connection relationships and timing configurations between each micro-process. The software building module is used to build flexible industrial production management software according to the industrial production process description.

9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 7.

Images