Multi-factory collaborative production management method, device and equipment and storage medium

Abstract

The invention provides a multi-factory collaborative production management method, and the method comprises the steps: obtaining market demand information, and real-time equipment operation state data, real-time material inventory information, historical sales parameters, production demand data and production process evaluation information of each factory; an industrial knowledge graph is constructed for the production demand data and the production process evaluation information based on a large language model, the market demand information and the historical sales data are analyzed to obtain production configuration data, and a dynamic production demand model is generated; according to the real-time equipment operation state data and the real-time material inventory information, a basic capacity allocation scheme is determined and corrected, and a collaborative production scheduling instruction set is obtained for collaborative production management; according to the method, the unified industrial knowledge graph is constructed through the large language model, the data utilization rate is improved, the production scheduling scheme is generated based on the real-time dynamic production demand model, the order delivery punctuality rate is improved, the traceability relation chain fully covered in the production process is constructed, the comprehensive utilization of equipment is improved, and the logistics scheduling cost is reduced.

Description

Technical Field

[0001] This application relates to the field of production management, and particularly to a multi-factory collaborative production management method, device, equipment, and storage medium. Background Art

[0002] With the rapid development of industrial Internet and intelligent manufacturing technologies, discrete manufacturing enterprises are gradually transforming towards a multi-factory collaborative production mode. Traditional production management systems are usually designed based on a single factory scenario and are difficult to adapt to the dynamic demand changes under a multi-supply chain layout. Existing production planning mostly relies on manual experience and historical experience to formulate a multi-factory collaborative production plan across factories.

[0003] In existing production scheduling technologies, there is a lack of real-time fusion ability for multi-source heterogeneous data, resulting in low efficiency of cross-factory resource collaboration, low degree of data fusion among factories, inability to achieve wide coverage of collaborative allocation, and traditional production scheduling relying on historical experience is prone to mismatch between production capacity allocation and actual demand. Moreover, the manual adjustment process of the production plan takes a long time and is difficult to comprehensively consider complex constraints such as equipment compatibility and logistics timeliness, which is prone to resource idleness and delivery delays. Especially in the context of increasing market demand fluctuations and rising product customization levels, traditional methods have many deficiencies in response speed, resource allocation accuracy, and exception handling capabilities. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a multi-factory collaborative production management method, device, equipment, and storage medium to solve the above technical problems.

[0005] The present invention provides a multi-factory collaborative production management method, and the multi-factory collaborative production management method includes: obtaining market demand information, as well as real-time equipment operation status data, real-time material inventory information, historical sales parameters, production demand data, and production process evaluation information of each factory; extracting entity features and association relationships from the production demand data and production process evaluation information through a large language model to obtain a material attribute network, an equipment capacity matrix, and process constraint relationships; constructing an industrial knowledge graph containing the material attribute network, the equipment capacity matrix, and the process constraint relationships, and parsing the market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data, and generating a dynamic production demand model according to the production configuration data; determining a basic production capacity allocation plan for each factory according to the dynamic production demand model, real-time equipment operation status data, and real-time material inventory information, and calling a large language model to correct the basic production capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set.

[0006] In an embodiment of the present invention, the production demand data includes equipment parameter data, process standard data, and quality case data, and the production process evaluation information includes work order record text information and inspection report document information. Extracting entity features and association relationships from the production demand data and production process evaluation information through a large language model includes: establishing an equipment capacity matrix based on the equipment parameter data, where the dimensions of the equipment capacity matrix include maximum processing accuracy, production capacity per unit time, and energy consumption efficiency coefficient; constructing a process constraint relationship based on the process standard data and quality case data, where the process constraint relationship includes temperature threshold interlock control and processing accuracy cumulative error compensation relationship; parsing the work order record text information and inspection report document information through the large language model, the equipment capacity evaluation matrix, and the process constraint relationship network to obtain process compatibility rules, and determining the equipment capacity evaluation matrix as an entity feature, and determining the process constraint relationship network and the process compatibility rules as association relationships.

[0007] In an embodiment of the present invention, the generation of the dynamic production demand model includes: performing quarterly decomposition on historical sales parameters to obtain historical sales component data for characterizing periodic fluctuation characteristics and long-term trend changes; performing semantic analysis on market demand information based on a large language model to generate market demand trend parameters for characterizing changes in market demand intensity; calculating the production capacity elasticity coefficient of each factory based on an industrial knowledge graph; deploying a reinforcement learning model, with the optimal balance of order delivery on-time rate and equipment utilization rate as the goal, and real-time outputting the optimal combination weight ratio of historical sales component data, market demand trend parameters, and production capacity elasticity coefficient; weighting and adding the historical sales component data, market demand trend parameters, and production capacity elasticity coefficient according to the optimal combination weight ratio to obtain a dynamic production demand model.

[0008] In an embodiment of the present invention, the generation process of the collaborative production scheduling instruction set includes: obtaining an equipment maintenance plan and special process requirements; calculating a basic production capacity allocation plan based on the dynamic production demand model, real-time equipment operation status data, and real-time material inventory information based on a preset mixed integer programming algorithm, and determining a production scheduling cycle according to the basic production capacity allocation plan; calling a large language model to parse the conflict between the equipment maintenance plan and the production scheduling cycle to generate a buffer time window adjustment plan; calling a large language model to identify the matching differences between special process requirements and the equipment capacity matrix of each factory and generate an alternative process route; correcting the basic production capacity allocation plan based on the buffer time window adjustment plan and the alternative process route to obtain a corrected production capacity allocation plan, and generating a collaborative production scheduling instruction set based on the corrected production capacity allocation plan.

[0009] In an embodiment of the present invention, after performing multi-factory collaborative production management according to the collaborative production scheduling instruction set, the multi-factory collaborative production management method further includes: monitoring and obtaining the equipment utilization rate, order completion progress, and material consumption rate data of each factory; calculating the progress deviation degree according to the equipment utilization rate, order completion progress, and material consumption rate data of each factory and the corrected production capacity allocation plan; if the progress deviation degree of any factory is greater than or equal to the preset progress deviation degree threshold, freezing the in-process work orders and triggering a dynamic rescheduling process.

[0010] In an embodiment of the present invention, the dynamic rescheduling process includes: obtaining the abnormal state of the factory with a progress deviation degree greater than or equal to the preset progress deviation degree threshold, and predicting the abnormal state of the factory through a pre-constructed impact propagation model to obtain abnormal impact prediction information; matching at least two remedial strategies with the highest correlation in the historical processing association information library based on the abnormal impact prediction information; selecting an adjustment plan with the minimum comprehensive loss from at least two remedial strategies with the highest correlation based on a multi-objective optimization algorithm to obtain a compensation adjustment plan, and generating a compensation work order instruction according to the compensation adjustment plan, based on the compensation work order instruction.

[0011] An embodiment of the present invention further provides a multi-factory collaborative production management device, which includes: a management data acquisition module, configured to acquire market demand information, as well as the real-time equipment operation status data, real-time material inventory information, historical sales parameters, production demand data, and production process evaluation information of each factory; a demand model construction module, configured to extract entity features and association relationships from the production demand data and production process evaluation information through a large language model to obtain a material attribute network, an equipment capacity matrix, and process constraint relationships; constructing an industrial knowledge graph including the material attribute network, the equipment capacity matrix, and the process constraint relationships, and parsing the market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data, and generating a dynamic production demand model according to the production configuration data; a collaborative production execution module, configured to determine the basic production capacity allocation plan of each factory according to the dynamic production demand model, the real-time equipment operation status data, and the real-time material inventory information, and call a large language model to correct the basic production capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set.

[0012] In an embodiment of the present invention, the multi-factory collaborative production management device further includes: a collaborative production monitoring module, configured to monitor and obtain data on the equipment utilization rate, order completion progress, and material consumption rate of each factory; a progress deviation compensation module, configured to calculate the progress deviation degree based on the equipment utilization rate, order completion progress, and material consumption rate data of each factory and the corrected production capacity allocation plan; if the progress deviation degree of any factory is greater than or equal to the preset progress deviation degree threshold, freeze the in-process work orders and trigger a dynamic rescheduling process.

[0013] An embodiment of the present invention also provides an electronic device, including: one or more processors; a storage device, configured to store one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the multi-factory collaborative production management method as described in any one of the above embodiments.

[0014] An embodiment of the present invention also provides a computer-readable storage medium, on which computer-readable instructions are stored, which, when executed by a processor of a computer, cause the computer to execute the multi-factory collaborative production management method as described in any one of the above embodiments.

[0015] A multi-factory collaborative production management method provided by the present invention, by obtaining market demand information, as well as the real-time equipment operation status data, real-time material inventory information, historical sales parameters, production demand data, and production process evaluation information of each factory, extracting entity features and association relationships from the production demand data and production process evaluation information through a large language model, obtaining a material attribute network, an equipment capacity matrix, and a process constraint relationship, constructing an industrial knowledge graph including the material attribute network, the equipment capacity matrix, and the process constraint relationship, and parsing the market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data, and generating a dynamic production demand model according to the production configuration data, determining the basic production capacity allocation plan of each factory according to the dynamic production demand model, real-time equipment operation status data, and real-time material inventory information, and invoking the large language model to correct the basic production capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set; this application parses unstructured production data through a large language model, fuses it with structured data such as equipment sensors, constructs a unified industrial knowledge graph, improves data utilization rate, generates a production scheduling plan based on a dynamic production demand model of real-time equipment status and material inventory, improves the on-time delivery rate of orders and shortens the response time for emergency order insertion, constructs a traceability relationship chain covering the entire production process, improves the defect root cause location efficiency, improves equipment comprehensive utilization, and reduces logistics scheduling costs.

[0016] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and cannot limit this application. Brief Description of the Drawings

[0017] The drawings herein are incorporated into and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings: Figure 1 is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application; Figure 2 is a flowchart of a multi-factory collaborative production management method shown in an exemplary embodiment of the present application; Figure 3 is a schematic diagram of a multi-factory collaborative production management device shown in an exemplary embodiment of the present application; Figure 4 is a schematic diagram of the structure of a computer system of an electronic device shown in an exemplary embodiment of the present application. Detailed Embodiments

[0018] The following will describe the embodiments of the present invention with reference to the drawings and specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention, rather than for limiting the protection scope of the present invention.

[0019] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention schematically. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0020] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0021] As used in this application, the "and / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0022] Figure 1 It is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of this application.

[0023] Refer to Figure 1 As shown, the system architecture may include a factory system database 110 and a computer device 120. Among them, the computer device 120 obtains market demand information, as well as real-time device operation status data, real-time material inventory information, historical sales parameters, production demand data, and production process evaluation information of each factory through the factory system database 110. It extracts entity features and association relationships from the production demand data and production process evaluation information through a large language model to obtain a material attribute network, a device capability matrix, and process constraint relationships, constructs an industrial knowledge graph containing the material attribute network, the device capability matrix, and the process constraint relationships, and analyzes the market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data, and generates a dynamic production demand model according to the production configuration data. It determines the basic production capacity allocation plan for each factory based on the dynamic production demand model, real-time device operation status data, and real-time material inventory information, and calls the large language model to correct the basic production capacity allocation plan to obtain a collaborative production scheduling instruction set for multi-factory collaborative production management according to the collaborative production scheduling instruction set. The above computer device 120 refers to a program implementation environment for carrying out the multi-factory collaborative production management method, including but not limited to a microcomputer, an embedded computer, an industrial control computer, and a cloud virtual machine, etc.; the above factory system database 110 at least includes a communication device for collecting data related to each factory and data for storing the data. In addition, it also includes a cloud server, a display terminal, a large language model interface, etc.

[0024] Schematically, the computer device 120 obtains market demand information, as well as real-time device operation status data, real-time material inventory information, historical sales parameters, production demand data, and production process evaluation information of each factory through the factory system database 110. It extracts entity features and association relationships from the production demand data and production process evaluation information through a large language model to obtain a material attribute network, a device capacity matrix, and process constraint relationships, constructs an industrial knowledge graph containing the material attribute network, the device capacity matrix, and the process constraint relationships, and analyzes the market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data. Then, it generates a dynamic production demand model based on the production configuration data, determines the basic production capacity allocation plan for each factory according to the dynamic production demand model, real-time device operation status data, and real-time material inventory information, and calls the large language model to correct the basic production capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set. In this application, unstructured production data is analyzed through a large language model and integrated with structured data such as device sensors to construct a unified industrial knowledge graph, improving data utilization rate. A production scheduling plan is generated based on the dynamic production demand model of real-time device status and material inventory, improving the on-time delivery rate of orders and shortening the response time for emergency order insertion. A traceability relationship chain covering the entire production process is constructed, improving the efficiency of defect root cause location, increasing the comprehensive utilization of equipment, and reducing logistics scheduling costs.

[0025] Figure 2 is a flowchart of a multi-factory collaborative production management method shown in an exemplary embodiment of this application. This multi-factory collaborative production management method can be executed in Figure 1 the implementation environment of, and can also be implemented in other implementation environments. The above implementation environment is not specifically limited herein. Referring to Figure 2 as shown, the flowchart of this multi-factory collaborative production management method at least includes steps S210 to S240, which are introduced in detail as follows: In step S210, market demand information, as well as real-time device operation status data, real-time material inventory information, historical sales parameters, production demand data, and production process evaluation information of each factory are obtained.

[0026] In an embodiment of this application, the above production demand data includes device parameter data, process standard data, and quality case data, and the above production process evaluation information includes work order record text information and inspection report document information.

[0027] In one embodiment of the present application, the market demand information includes structured data such as customer order databases and market forecast reports, as well as unstructured data such as customer demand texts and industry trend analyses. It obtains specific information by docking with enterprise CRM systems, e-commerce platform order systems, etc. through API interfaces; the real-time device operation status data includes, but is not limited to, device basic parameters, operation indicators, sensor data, working status, utilization rate, maintenance records, last maintenance time, cumulative working hours, pending fault codes, etc., which can be collected in real time from the device PLC / SCADA system through an industrial Internet of Things gateway; the real-time material inventory information includes, but is not limited to, in-stock materials, raw materials, semi-finished products, finished products, materials in transit, expected arrival time and quantity in purchase orders, and the logistics transportation status of cross-factory transferred materials. The acquisition methods include, but are not limited to, accessing the inventory management module of the ERP system or the logistics tracking system providing the status of materials in transit; the historical sales parameters include time series data, regional sales distribution, customer behavior data, large customer order cycle rules, sales volume fluctuation characteristics during promotional activities, product correlation data, etc., and the acquisition methods include retrieving from the enterprise data warehouse; the production demand data includes, but is not limited to, order demands, implicit demand forecasts, process requirements, special processing requirements for products, environmental control parameters, etc., and the acquisition methods include, but are not limited to, parsing the technical specifications in the attachments of customer orders or extracting the key requirement clauses in emails / contracts; the production process evaluation information includes, but is not limited to, efficiency indicators, production line balance rate, quality data, SPC control chart data of key quality characteristics, abnormal records, etc., and the acquisition methods include production reporting data of the manufacturing execution system or inspection result records of the quality management system, etc.

[0028] In step S220, the large language model is used to extract entity features and association relationships from the production demand data and the production process evaluation information, obtaining a material attribute network, a device capacity matrix, and process constraint relationships.

[0029] In one embodiment of the present application, a device capacity matrix is established based on device parameter data. The dimensions of the device capacity matrix include maximum processing accuracy, unit time production capacity, and energy consumption efficiency coefficient; process constraint relationships are constructed based on process standard data and quality case data. The process constraint relationships include temperature threshold interlock control and cumulative error compensation relationships for processing accuracy; the work order record text information and inspection report document information are parsed through the large language model, the device capacity evaluation matrix, and the process constraint relationship network to obtain process compatibility rules, and the device capacity evaluation matrix is determined as the entity feature, and the process constraint relationship network and the process compatibility rules are determined as the association relationships.

[0030] In one embodiment of the present application, the equipment capability matrix is a structured data model for quantitatively evaluating the comprehensive performance of factory equipment. Its core dimensions include, but are not limited to, the maximum processing accuracy for characterizing the highest processing accuracy level that the equipment can achieve under the best conditions, the unit-time production capacity for characterizing the theoretical output per hour / shift under standard working conditions, and the energy consumption efficiency coefficient for characterizing the energy consumption level per unit output of the equipment. Among them, the calculation formula for the unit-time production capacity can be expressed as unit-time production capacity = (equipment theoretical production capacity × utilization rate) × (1 - planned downtime rate). The construction process includes analyzing the stability of processing accuracy of continuous equipment using the Six Sigma method based on the equipment parameter data and the historical work order completion data extracted from the MES system, and calculating the theoretical cycle time of discrete equipment through motion time analysis.

[0031] In one embodiment of the present application, in the construction of process constraint relationships, the core constraint types include temperature threshold interlock control and cumulative error compensation relationship of processing accuracy. The temperature threshold interlock control is used to define the temperature conduction relationship between processes. The cumulative error compensation of processing accuracy is used to establish a transfer model for multi-process processing errors. For example, if the processing error of the previous process is +0.02mm, the subsequent process needs to automatically adjust and compensate by 0.015mm. When the cumulative error of 3 consecutive processes in the same direction exceeds 0.05mm, a full inspection instruction is triggered.

[0032] In one embodiment of the present application, the generation of process compatibility rules is to perform semantic parsing on the work order record text and the inspection report document, and perform entity recognition and relationship extraction by the large language model, and perform logical verification on the extracted rules with the equipment capability matrix and the process constraint network. If the verification is correct, the process compatibility rules are obtained.

[0033] In step S230, an industrial knowledge graph including the material attribute network, the equipment capability matrix, and the process constraint relationship is constructed, and the market demand information and historical sales data are analyzed based on the industrial knowledge graph to obtain production configuration data, and a dynamic production demand model is generated according to the production configuration data.

[0034] In one embodiment of the present application, the historical sales parameters are decomposed quarterly to obtain historical sales component data for characterizing periodic fluctuation characteristics and long-term trend changes; the semantic analysis of market demand information is performed based on the large language model to generate market demand trend parameters for characterizing the change of market demand intensity; the production capacity elasticity coefficient of each factory is calculated based on the industrial knowledge graph.

[0035] In one embodiment of the present application, a reinforcement learning model is deployed with the goal of achieving the optimal balance between order delivery on-time rate and equipment utilization rate, and the optimal combined weight ratio of historical sales component data, market demand trend parameters, and production capacity elasticity coefficient is output in real time. Then, the historical sales component data, market demand trend parameters, and production capacity elasticity coefficient are weighted and added according to the optimal combined weight ratio to obtain a dynamic production demand model.

[0036] In one embodiment of the present application, the core optimization goal is to establish a dynamic balance between the order delivery on-time rate and the equipment utilization rate, avoiding systematic imbalance caused by the optimization of a single indicator. Among them, the order delivery on-time rate is the number of orders delivered on time / the total number of orders, and the equipment utilization rate is the actual production time of the equipment / the available time of the equipment. Specifically, the model training process includes constructing a simulation environment using historical production data, randomly exploring weight combinations by the initial policy network, updating network parameters through the proximal policy optimization algorithm, and fine-tuning the model by collecting the latest production data in real time. A dual-network architecture is adopted to ensure stability, and a safety boundary weight parameter is set to prevent extreme allocation.

[0037] In step S240, based on the dynamic production demand model, real-time equipment operation status data, and real-time material inventory information, the basic production capacity allocation plan for each factory is determined, and a large language model is called to correct the basic production capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set.

[0038] In one embodiment of the present application, the generation of the collaborative production scheduling instruction set includes obtaining the equipment maintenance plan and special process requirements; calculating the basic production capacity allocation plan based on the dynamic production demand model, real-time equipment operation status data, and real-time material inventory information using a preset mixed-integer programming algorithm, and determining the production scheduling cycle according to the basic production capacity allocation plan; calling a large language model to analyze the conflict between the equipment maintenance plan and the production scheduling cycle, and generating a buffer time window adjustment plan; calling a large language model to identify the matching differences between the special process requirements and the equipment capacity matrix of each factory, and generating an alternative process route; correcting the basic production capacity allocation plan based on the buffer time window adjustment plan and the alternative process route to obtain a corrected production capacity allocation plan, and generating a collaborative production scheduling instruction set based on the corrected production capacity allocation plan.

[0039] In one embodiment of the present application, it also includes monitoring and obtaining the equipment utilization rate, work order completion progress, and material consumption rate data of each factory; calculating the progress deviation degree according to the equipment utilization rate, work order completion progress, and material consumption rate data of each factory and the corrected production capacity allocation plan; if the progress deviation degree of any factory is greater than or equal to the preset progress deviation degree threshold, the in-process work orders are frozen, and a dynamic rescheduling process is triggered.

[0040] In one embodiment of the present application, the dynamic rescheduling process includes obtaining a factory abnormal state with a progress deviation degree greater than or equal to a preset progress deviation degree threshold, predicting the factory abnormal state through a pre-constructed impact propagation model to obtain abnormal impact prediction information; matching at least two remedial strategies with the highest correlation in the historical processing association information library based on the abnormal impact prediction information; selecting an adjustment plan with the minimum comprehensive loss from at least two remedial strategies with the highest correlation based on a multi-objective optimization algorithm to obtain a compensation adjustment plan, and generating a compensation work order instruction based on the compensation adjustment plan, so as to be based on the compensation work order instruction.

[0041] A multi-factory collaborative production management method, device, equipment and storage medium provided by the present invention, by obtaining market demand information, as well as real-time equipment operation status data, real-time material inventory information, historical sales parameters, production demand data and production process evaluation information of each factory, extracting entity features and association relationships from the production demand data and production process evaluation information through a large language model to obtain a material attribute network, an equipment capacity matrix and a process constraint relationship, constructing an industrial knowledge graph including the material attribute network, the equipment capacity matrix and the process constraint relationship, and parsing the market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data, generating a dynamic production demand model according to the production configuration data, determining a basic production capacity allocation plan for each factory according to the dynamic production demand model, real-time equipment operation status data and real-time material inventory information, and calling a large language model to correct the basic production capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set; this application parses unstructured production data through a large language model, fuses it with structured data such as equipment sensors, constructs a unified industrial knowledge graph, improves data utilization rate, generates a production scheduling plan based on a dynamic production demand model of real-time equipment status and material inventory, improves the on-time delivery rate of orders and shortens the response time for emergency order insertion, constructs a traceability relationship chain covering the entire production process, improves the defect root cause location efficiency, improves the comprehensive utilization of equipment and reduces the logistics scheduling cost.

[0042] The following introduces the device embodiments of the present application, which can be used to execute the multi-factory collaborative production management method in the above embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the embodiments of the multi-factory collaborative production management method above of the present application.

[0043] Figure 3 is a schematic diagram of a multi-factory collaborative production management device shown in an exemplary embodiment of the present application. This device can be applied to Figure 2 the method implementation process shown, and this device can be based on Figure 1It can be executed in the implementation environment shown, and can also be applied to other exemplary implementation environments and be specifically configured in other devices. This embodiment does not limit the implementation environment applicable to the device.

[0044] As Figure 3 shown, the exemplary multi-factory collaborative production management device includes: a management data acquisition module 301, a demand model construction module 302, and a collaborative production execution module 303.

[0045] Among them, the management data acquisition module 301 is used to acquire market demand information, as well as the real-time device operation status data, real-time material inventory information, historical sales parameters, production demand data, and production process evaluation information of each factory; the demand model construction module 302 is used to extract entity features and association relationships from the production demand data and production process evaluation information through a large language model to obtain a material attribute network, a device capacity matrix, and process constraint relationships; construct an industrial knowledge graph containing the material attribute network, the device capacity matrix, and the process constraint relationships, and parse the market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data, and generate a dynamic production demand model according to the production configuration data; the collaborative production execution module 303 is used to determine the basic production capacity allocation plan for each factory according to the dynamic production demand model, the real-time device operation status data, and the real-time material inventory information, and call the large language model to correct the basic production capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set.

[0046] Among them, the exemplary multi-factory collaborative production management device further includes: a collaborative production monitoring module and a progress deviation compensation module. The above-mentioned collaborative production monitoring module is used to monitor and acquire the equipment utilization rate, work order completion progress, and material consumption rate data of each factory; the above-mentioned progress deviation compensation module is used to calculate the progress deviation degree according to the equipment utilization rate, work order completion progress, and material consumption rate data of each factory and the corrected production capacity allocation plan; if the progress deviation degree of any factory is greater than or equal to the preset progress deviation degree threshold, freeze the in-process work order and trigger a dynamic rescheduling process.

[0047] An embodiment of the present application also provides an electronic device, including: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the multi-factory collaborative production management method provided in each of the above embodiments.

[0048] Figure 4 is a schematic structural diagram of a computer system of an electronic device shown in an exemplary embodiment of the present application. It should be noted that Figure 4The computer system 400 of the illustrated electronic device is merely an example and shall not impose any limitation on the functions and scope of use of the embodiments of the present application.

[0049] As Figure 4 shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage section into the random access memory (RAM) 403, such as executing the method in the above embodiments. In the RAM 403, various programs and data required for system operation are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus. The I / O interface 405 is also connected to the bus 404, where the I / O interface 405 refers to the input / output interface.

[0050] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that the computer program read from it can be installed into the storage section 408 as needed.

[0051] Specifically, according to the embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the system of the present application are executed.

[0052] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0053] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0054] In the corresponding drawings of the above embodiments, connection lines may represent the connection relationships between various components, to represent more constituent signal paths and / or one or more ends of some lines have arrows to represent the main information flow direction. As a kind of identification, the connection lines are not a limitation on the solution itself, but using these lines in combination with one or more exemplary embodiments helps to more easily connect circuits or logic units. Any represented signal (determined by design requirements or preferences) may actually include one or more signals that can be transmitted in any one direction and can be implemented in any appropriate type of signal scheme.

[0055] The units involved in the embodiments described in this application can be implemented in software or in hardware, and the described units can also be set in a processor. Among them, the names of these units do not constitute a limitation on the units themselves in some cases.

[0056] Another aspect of this application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method as described above is implemented. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist separately without being assembled into the electronic device.

[0057] The embodiments of this application also provide a computer program product, including a computer program. When the computer program is executed by a processor, the multi-factory collaborative production management method in any one of the above embodiments is implemented.

[0058] It should be noted that although several modules or units of the devices for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0059] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described here can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (such as a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of this application.

[0060] Note that the present application can be used in numerous general-purpose or special-purpose computing system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on.

[0061] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include known common general knowledge or conventional technical means in the technical field not disclosed in the present application.

[0062] It should be understood that the above content of the present application is only a preferred exemplary embodiment of the present application and is not used to limit the implementation of the present application. Those of ordinary skill in the art can easily make corresponding adaptations or modifications according to the main concept and spirit of the present application. Therefore, the protection scope of the present application should be the protection scope required by the claims.

Claims

1. A multi-factory collaborative production management method, characterized in that: The multi-factory collaborative production management method comprises: Obtain market demand information, as well as real-time equipment operation status data, real-time material inventory information, historical sales parameters, production demand data and production process evaluation information of each factory; Extract entity features and association relationships from the production demand data and production process evaluation information through a large language model to obtain a material attribute network, an equipment capability matrix, and a process constraint relationship; Construct an industrial knowledge graph including a material attribute network, an equipment capability matrix, and process constraint relationships, and analyze market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data, and generate a dynamic production demand model based on the production configuration data; The basic capacity allocation plan for each factory is determined according to the dynamic production demand model, real-time equipment operation status data and real-time material inventory information, and the large language model is called to correct the basic capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set.

2. The multi-factory collaborative production management method according to claim 1, characterized in that: The production demand data includes equipment parameter data, process standard data and quality case data, and the production process evaluation information includes work order record text information and test report document information. The entity features and association relationships extracted from the production demand data and production process evaluation information by the large language model include: Establishing an equipment capability matrix according to the equipment parameter data, wherein the dimensions of the equipment capability matrix include maximum processing accuracy, unit time capacity, and energy efficiency coefficient; Constructing a process constraint relationship according to the process standard data and the quality case data, wherein the process constraint relationship includes a temperature threshold linkage control and a machining accuracy cumulative error compensation relationship; The work order record text information and the inspection report document information are parsed through a large language model, an equipment capability evaluation matrix, and a process constraint relationship network to obtain process compatibility rules, and the equipment capability evaluation matrix is ​​determined as an entity feature, and the process constraint relationship network and the process compatibility rules are determined as association relationships.

3. The multi-factory collaborative production management method according to claim 1, characterized in that: The generation of the dynamic production demand model includes: Decompose historical sales parameters quarterly to obtain historical sales component data used to characterize cyclical fluctuation characteristics and long-term trend changes; Perform semantic analysis on market demand information based on a large language model to generate market demand trend parameters used to characterize changes in market demand intensity; Calculate the production capacity elasticity coefficient of each factory based on the industrial knowledge graph; Deploy a reinforcement learning model to achieve the optimal balance between on-time order delivery and equipment utilization, and output the optimal combination weight ratio of historical sales component data, market demand trend parameters, and capacity elasticity coefficient in real time; The historical sales component data, market demand trend parameters and production capacity elasticity coefficient are weighted and added according to the optimal combination weight ratio to obtain a dynamic production demand model.

4. The multi-factory collaborative production management method according to claim 1, characterized in that: The generation process of the collaborative production scheduling instruction set includes: Obtain equipment maintenance plans and special process requirements; Calculate a basic capacity allocation plan based on a preset mixed integer programming algorithm according to the dynamic production demand model, real-time equipment operation status data, and real-time material inventory information, and determine a production scheduling cycle according to the basic capacity allocation plan; Calling a large language model to analyze the conflict between the equipment maintenance plan and the production scheduling cycle, and generating a buffer time window adjustment plan; Calling the large language model to identify the matching differences between special process requirements and the equipment capability matrix of each factory, and generating alternative process routes; The basic capacity allocation plan is corrected based on the buffer time window adjustment plan and the alternative process route to obtain a corrected capacity allocation plan, and a collaborative scheduling instruction set is generated based on the corrected capacity allocation plan.

5. The multi-factory collaborative production management method according to claim 4, characterized in that: After performing multi-factory collaborative production management according to the collaborative production scheduling instruction set, the multi-factory collaborative production management method further includes: Monitor and obtain data on equipment utilization rate, work order completion progress, and material consumption rate of each factory; Calculate the progress deviation based on the equipment utilization rate, work order completion progress, material consumption rate data and the corrected capacity allocation plan of each factory; If the progress deviation of any factory is greater than or equal to the preset progress deviation threshold, the work-in-process work order will be frozen and the dynamic rescheduling process will be triggered.

6. The multi-factory collaborative production management method according to claim 5, characterized in that: The dynamic rescheduling process includes: Obtaining abnormal plant states with a progress deviation greater than or equal to a preset progress deviation threshold, and predicting the abnormal plant states through a pre-built impact propagation model to obtain abnormal impact prediction information; Matching at least two remediation strategies with the highest correlation in a historical processing correlation information base based on the abnormal impact prediction information; Based on the multi-objective optimization algorithm, an adjustment plan with the smallest comprehensive loss is selected from at least two remedial strategies with the highest correlation to obtain a compensation adjustment plan, and a compensation work order instruction is generated according to the compensation adjustment plan to obtain a compensation work order instruction based on the compensation work order instruction.

7. A multi-factory collaborative production management device, characterized in that: The multi-factory collaborative production management device comprises: Management data acquisition module, used to obtain market demand information, as well as real-time equipment operation status data of each factory, real-time material inventory information, historical sales parameters, production demand data and production process evaluation information; A demand model building module is used to extract entity features and associations from the production demand data and production process evaluation information through a large language model to obtain a material attribute network, an equipment capability matrix, and a process constraint relationship; to build an industrial knowledge graph including the material attribute network, the equipment capability matrix, and the process constraint relationship, and to parse the market demand information and historical sales data based on the industrial knowledge graph to obtain production configuration data, and to generate a dynamic production demand model based on the production configuration data; The collaborative production execution module is used to determine the basic capacity allocation plan of each factory based on the dynamic production demand model, real-time equipment operation status data and real-time material inventory information, and call the large language model to correct the basic capacity allocation plan to obtain a collaborative production scheduling instruction set, so as to perform multi-factory collaborative production management according to the collaborative production scheduling instruction set.

8. The multi-factory collaborative production management device according to claim 7, characterized in that: The multi-factory collaborative production management device also includes: Collaborative production monitoring module, used to monitor and obtain data on equipment utilization rate, work order completion progress, and material consumption rate of each factory; The progress deviation compensation module is used to calculate the progress deviation based on the equipment utilization rate, work order completion progress, material consumption rate data and the corrected capacity allocation plan of each factory; if the progress deviation of any factory is greater than or equal to the preset progress deviation threshold, the work-in-process work order is frozen and the dynamic rescheduling process is triggered.

9. An electronic device, characterized in that: It comprises a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute the computer program stored in the memory to implement the multi-factory collaborative production management method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is used to enable a computer to execute the multi-factory collaborative production management method as described in any one of claims 1-6.

Images