252 results about "Manufacturing execution system" patented technology

The present invention relates to a method for constructing a digital twin system for an additive manufacturing process with lifecycle data management. The digital twin system for an additive manufacturing process constructed by the method includes a data acquisition and supervisory control system, a data management and storage system, a manufacturing executing system, a configuration model, a simulation system, and a multi-physics simulation system. The present invention can fully and accurately characterize the molding quality of parts, thereby saving a lot of time required for offline data processing, and achieving real-time acquisition and updating of data.

An AI-driven, cloud-based system (100) for real-time biomedical and pharmaceutical compliance and risk management, including: (a) a compliance knowledge module configured to ingest, interpret and structure regulatory data using natural language processing (NLP) and generate machine-readable compliance rules; (b) a real-time monitoring and event recording module configured to collect and normalise operational data from distributed biomedical and pharmaceutical systems, including laboratory information management systems (LIMS), manufacturing execution systems (MES) and IoT-enabled devices; (c) an intelligent risk assessment and prediction module configured to correlate operational data with compliance rules, calculate dynamic risk scores and predict potential compliance violations using machine learning models; (d) an automated policy and workflow enforcement module configured to initiate remedial actions, assign tasks and log activities based on predefined standard operating procedures (SOPs); (e) an audit readiness and reporting module configured to generate compliance logs, audit trails and standardised regulatory reports in real time; and (f) an adaptive learning and feedback optimization module configured to refine rule sets and predictive models based on feedback, historical data and regulatory updates; g) the modules are integrated into a cloud infrastructure to enable real-time, scalable and predictive compliance and risk management across biomedical and pharmaceutical processes.

The invention relates to the technical field of computers, and discloses a chip mounter material tracing management method and system based on a knowledge graph. The method comprises the following steps: constructing a dynamic knowledge graph covering the whole process of a patch; injecting multi-source data in real time to drive dynamic updating of the atlas; when the materials are abnormal, reverse tracing and forward influence double-path reasoning are started; isolation, rework and reset instructions are automatically generated and pushed to a manufacturing execution system; and synchronously updating the atlas state to form an auditable record. The system comprises a dynamic knowledge graph construction module, a real-time data injection module, a bidirectional inference engine module, an automatic processing instruction generation module and a graph state synchronization module. According to the scheme, millisecond-level error positioning and closed-loop processing are realized, and the tracing efficiency and the quality guarantee capability are improved.

The invention discloses a process parameter switching method and device for multi-variety production, and a server side method comprises the steps: receiving a process parameter switching request sent by a manufacturing execution system used for monitoring a product production state, wherein the process parameter switching request carries production demand description information and a product batch model; according to the production demand description information, corresponding target process parameters are automatically obtained, the target process parameters are determined by adopting a preset comparison function, and the preset comparison function comprises a basic comparison term expression and a physical comparison term expression; pre-checking the target process parameters to obtain a checking result; and under the condition that the verification result indicates that the verification of the target process parameter is passed, binding the target process parameter to a product batch model, and issuing the product batch model to an equipment control layer. Therefore, by adopting the embodiment of the invention, the time required for searching and inputting the process parameters is avoided, so that the equipment can be switched to a new production task more quickly, and the production efficiency and the product quality are remarkably improved.

The invention provides an industrial manufacturing industry-oriented carbon asset full life cycle management method and system, and the method comprises the steps: carrying out the cross-link feature fusion processing through obtaining an original carbon activity data set of an industrial manufacturing whole process, and generating carbon footprint feature data; and calling a pre-trained deep learning model to perform carbon asset state evolution analysis on the carbon footprint feature data, predicting a carbon asset evolution path, generating a carbon asset optimization strategy set based on a prediction result, including equipment energy efficiency regulation and control and a production plan recombination strategy, and pushing the carbon asset optimization strategy set to an industrial manufacturing execution system. And triggering an automatic control instruction reconstruction operation to realize automation and intelligence of carbon asset management, thereby comprehensively and accurately mastering a carbon asset state and an evolution rule, formulating a scientific and effective optimization strategy, reducing carbon emission, improving energy utilization efficiency, and improving green production capacity of an enterprise.

The invention discloses a steelmaking MES manufacturing execution system based on data analysis, and relates to the technical field of monitoring analysis, and the system comprises a data collection module which is used for collecting multivariate heterogeneous data of a steelmaking whole process, and constructing a steelmaking dynamic feature vector; the optimization scheme generation module is used for generating an inter-process parameter coupling relation graph and performing key process parameter optimization generation on the inter-process parameter coupling relation graph to obtain a parameter optimization configuration scheme; the instruction generation module is used for establishing a production execution deviation quantitative index, performing process parameter dynamic compensation calculation according to the production execution deviation quantitative index, and generating a real-time process adjustment instruction set; the simulation verification module is used for carrying out dynamic priority ranking on the parameter optimization configuration scheme and generating an execution strategy optimization scheme; and the manufacturing execution control module is used for executing manufacturing based on the execution strategy optimization scheme and carrying out risk prediction and efficiency evaluation based on an execution manufacturing result. The device has the effect of improving the production efficiency.

The invention provides a production process configuration method and device for a manufacturing execution system in the technical field of industrial manufacturing informatization. The method comprises the steps that S1, customized information is extracted from order data to generate a production task instruction; s2, matching resource requirements based on the production task instruction to generate a resource allocation list; s3, generating a flow configuration file based on the resource allocation list and the production task instruction, and issuing the flow configuration file to a corresponding production execution unit to execute production operation; s4, collecting production data from each production execution unit in real time, recording production logs in real time, and carrying out standardized processing and unified storage on the production logs; and S5, carrying out real-time monitoring on a production task state, a production resource state, a system operation state and a change condition of order data, and dynamically reconstructing a process configuration file. The method has the advantages that the flexibility, the automation level and the response efficiency of production process configuration are greatly improved.

The invention discloses a production line test construction system based on an MES system, and relates to the technical field of intelligent manufacturing and production line testing, and the production line test construction system comprises a test configuration module, a test execution module, a data integration module, a visual interface module and an authority management module. The test configuration module is used for automatically obtaining a test process template from the MES system according to the product model information and completing process customization in a graphical mode; the test execution module identifies a to-be-tested product and calls a process file, and controls the test equipment to execute a test and perform data acquisition and judgment; the data integration module binds the test result with the unique identifier of the product, and uploads the test result to the MES system to realize full-process tracing; the visual interface module is used for displaying a process state and a test result; the authority management module is used for performing hierarchical control and version conflict detection on the operation authority; according to the system, the construction efficiency and execution reliability of the test process are improved, and closed-loop and intelligent management of data in the test process is realized.

The invention provides a precision machining and 3D printing mixed manufacturing execution system, and relates to the technical field of data processing, and the system is used for dividing a three-dimensional model into a configuration area and a finishing area, generating a layer-by-layer closed contour path, obtaining configuration path data, extracting a boundary segment close to the finishing area, and obtaining a configuration path data set; calculating a space projection vector on a finishing target surface to obtain primary finishing path data; calculating a boundary torsion value; superposing interference offset in a historical sample path to a primary finishing path; calculating an interference amplitude index; the fitting path data and the configuration path data are subjected to path connection and unified processing according to the manufacturing sequence, and a mixed execution path instruction is obtained. Precise machining and 3D printing are integrated, and path overlapping, empty cutting or unnecessary machining is avoided.

The invention discloses a multi-branch industrial ventilation intelligent regulation and control system and method based on a PLC. According to the system, a closed-loop control network is formed by an infrared sensor, a wind speed sensor, a PLC (Programmable Logic Controller), an air door control cabinet, an electric valve, a frequency converter, a frequency conversion fan and an upper computer. The infrared sensor is responsible for monitoring the running state of each production line in real time. The wind speed sensor is used for detecting the wind speed in the wind pipe and verifying wind quantity balance. The PLC processes all sensor data and outputs a control instruction. On one hand, the opening degree of the electric valve is adjusted through the air door control cabinet, and on the other hand, the rotating speed of the fan is adjusted in real time through the frequency converter. The upper computer is used for system parameter monitoring, threshold setting and data interaction with the manufacturing execution system. According to the system, on-demand adjustment of multi-branch ventilation is achieved through intelligent closed-loop control, the problem of response lag of a traditional control mode is effectively solved, the dust removal efficiency and the energy utilization rate are remarkably improved, and safe and efficient operation of the industrial environment is guaranteed.

The invention discloses a combined machining system with five-axis linkage control and four-spindle independent control functions. The combined machining system integrates high-precision combined CNC machining equipment, an AGV (automatic guided vehicle) logistics device and an MES (manufacturing execution system). According to the system, four high-speed main shaft units are arranged in parallel in the X-axis direction, an inclinable workbench is independently installed in front of each main shaft unit, and the system has the functions of inclining by + / -110 degrees and rotating by 360 degrees. Each workbench is provided with a center pressing type circular quick-change clamp adapter, and a 3D identification mark is embedded into each workbench so that the AGV logistics device can automatically identify and replace the center pressing type circular quick-change clamp adapter. According to the system, an MES instructs the AGV to enter a standby state in advance through an M330 forecast signal output by the CNC, then after automatic cleaning and door body opening operation are sequentially executed, the AGV enters equipment to complete clamp replacement, real-time communication among the MES, the CNC and the AGV is achieved on the basis of an OPC-UA protocol in the whole process, and the MES issues a Cycle Start signal only when all working conditions are met, so that the high-speed unmanned continuous machining process is ensured.

The invention relates to the technical field of manufacturing execution systems, in particular to an intelligent scheduling method integrating demand prediction and supply matching, which comprises the following steps of: acquiring to-be-scheduled order information and a workshop real-time resource state in a manufacturing execution system, constructing an order demand feature vector, the method comprises the following steps: acquiring an equipment precision retentivity value, a current load rate value, an energy consumption level value and an operator skill proficiency value, and constructing a resource supply capability vector; according to the method, when an urgent order insertion instruction is received, a clear decision basis is provided, a rigid scheduling locking block which must be kept unchanged and an adjustable liquid adjustable scheduling block which can be adjusted can be distinguished, only the latter is subjected to accurate splitting and backward moving operation, and the target-clear local adjustment mode is adopted, so that the operation efficiency is greatly improved. The huge calculation overhead and the violent fluctuation of the production plan caused by the traditional global rescheduling are avoided, and the agility of the manufacturing system to deal with the market change is enhanced.

The invention relates to a defect analysis and process optimization method based on artificial intelligence multi-mode fusion, and the method comprises the steps: respectively inputting virtual data of a chip or device design layout, an expected process flow and parameters, and an expected electrical performance curve into an image encoder, a process encoder, and an electrical encoder, extracting a corresponding feature vector; performing cross-modal information interaction on the corresponding feature vectors according to a cross attention fusion mechanism; determining a representation image, a defect category, a root cause category and a process parameter correction suggestion; and based on a manufacturing execution system (MES), an electronic design automation (EDA) tool or an equipment interface, process parameters are corrected, and a closed-loop control result from defect analysis to process optimization is obtained. Therefore, the problems of single data dimension, mutual coupling of various defects, influence of background noise, limited machine identification accuracy, overlarge workload of artificial expert judgment and low efficiency are solved.

The invention discloses an environment monitoring management system and method for a precision workshop, and relates to the technical field of environment monitoring and control, and the method comprises the steps: synchronously collecting multi-dimensional environment parameters through a distributed sensor network, accessing a manufacturing execution system in real time, analyzing the requirements of a process window, and carrying out the real-time monitoring of the environment parameters; and performing fusion and abnormality diagnosis on the data under a unified space-time reference, generating a closed-loop regulation and control instruction, and coordinating and controlling an execution mechanism. The system comprises a multi-mode environment perception unit, a process semantic analysis unit, a space-time fusion and abnormality diagnosis engine, an intelligent regulation and control decision unit and an execution mechanism cooperative control unit. According to the invention, deep understanding of environment disturbance and production process relevance can be realized, compound environment abnormity can be accurately identified, production task requirements can be adapted in real time, environment parameters are ensured to be always in an optimal process tolerance band, the product yield and the process repeatability are obviously improved, and millisecond-level response and cooperative linkage control are realized.

The invention discloses a data management method, system and device for a semiconductor manufacturing execution system and a medium, and the method comprises the steps: creating or obtaining a unique identifier for connecting an upper layer component and a lower layer component in a component tree, and enabling each layer component of the component tree to achieve the isolation of component states at a hierarchical boundary through mapping state data corresponding to different action ranges; confirming a mixing mode of context data between the upper-layer component and the lower-layer component; mixing the state data of the upper-layer component and the context data of the lower-layer component based on the mixing mode and the unique identifier to form current action domain data corresponding to the lower-layer component; and the lower-layer component obtains the business data provided for the upper-layer component through the action domain component based on the unique identifier in the current action domain data, so that the business data can be used by the business. According to the method, a dynamic state isolation mechanism is realized, a state management tool can well realize component-level state isolation, and extraction and reuse of complex services are realized; and the data combination form among the components is more flexible.

The invention relates to the technical field of medical instrument quality management, in particular to a medical instrument monitoring method and system, and the method comprises the steps: firstly generating design gene data containing a model code, a physical unclonable fingerprint and a quantum public key at a design freezing node, and writing the design gene data into a Twindow-DNA chip; in the manufacturing stage, process parameters and scattering optical data are synchronously collected, an optical domain super-vector is constructed and spliced with process embedding to form manufacturing embedding characteristic data, and the manufacturing embedding characteristic data are encrypted and then sent to a digital twinborn body; performing twin calculation on a normalized residual error, generating a residual error vector through vector holographic convolution and multi-stage diffusion denoising when the normalized residual error exceeds a threshold value, inputting the residual error vector into a super-vector converter to obtain defect semantic data, and writing the defect semantic data into a three-division hypergraph account book which takes a quantum public key as an index by using zero knowledge commitment; and calling the hypergraph neural network and the neural relationship inference model according to a fixed time interval, outputting correction-prevention data, writing the correction-prevention data back to a manufacturing execution system, and meanwhile, performing hash chain writing on the correction-prevention data to form a quality closed loop and support operation decision and regulation delivery.

The invention discloses an online detection system and method for optical indexes of a hollow-core optical fiber, and relates to the technical field of optical performance detection of optical fibers, and the system comprises an optical fiber connection module, an optical performance detection module, a production linkage module and a data interaction module. The method comprises the following steps: welding the inner end of a production optical fiber with a system at one time; the industrial personal computer reads PLC production data and generates a test trigger condition; when the conditions are met, controlling the OTDR to test the optical indexes of the optical fiber; carrying out segment processing on the OTDR curve by using an improved Viterbi algorithm so as to identify fault features; performing automatic environment compensation based on an attenuation reference model established by the LSTM neural network; and finally, uploading the analysis data to a manufacturing execution system. According to the invention, on-line, real-time and accurate detection of the optical indexes of the hollow-core fiber is realized, traditional multi-time welding is replaced by one-time welding, the detection efficiency is greatly improved, and the problems of poor sealing performance, low efficiency and low data reliability in the prior art are solved.

The invention discloses a task scheduling method based on MES system collaboration, and belongs to the technical field of task scheduling. The invention relates to a task scheduling method based on MES (Manufacturing Execution System) system collaboration, which is characterized by comprising the following steps of: S1, carrying out production data acquisition and standardization processing; s2, sensing and predicting a production resource state; s3, performing task scheduling constraint modeling; s4, cooperative scheduling calculation; s5, carrying out visualization and explanation generation on the scheduling scheme; s6, task issuing and execution feedback; and S7, historical data accumulation and scheduling strategy optimization. According to the method, the production resource state is predicted through a time sequence prediction model, a Bayesian model and a skill matching model based on the equipment sensor data, the material state and the personnel scheduling information which are acquired in real time.

The invention provides an MES (Manufacturing Execution System)-oriented arc-shaped battery manufacturing process data acquisition method and system, and relates to the technical field of manufacturing execution system data acquisition. The method comprises the following steps: firstly, constructing a hierarchical model of a production line, a workshop section, a station, equipment, an acquisition channel and a data field, enabling the hierarchical model to correspond to a manufacturing execution system object, establishing a global unique identifier and time and space marks, forming a unified data item description table, and implementing field acquisition, unified time service and standardized preprocessing; bending features are extracted, mapping entries are generated with process states and quality results, the mapping entries are uploaded to a manufacturing execution system and a data platform, abnormal supplementary transmission and monomer-level tracing are supported, and the data consistency and tracing capability of the arc battery manufacturing process are improved.

The invention belongs to the technical field of automobile flexible manufacturing, and particularly discloses a method and system for analyzing and issuing technological parameters in real time in automobile flexible manufacturing, and the method comprises the following steps: a customer submits required configuration orders of appearance, interior decoration and functions through an Internet of Things customization platform; the Internet of Things customization platform converts the customer order information into a standardized data format and sends the data format to a manufacturing execution system MES; and the MES system presets process basic data required by each vehicle type and configuration rules of the corresponding vehicle type, analyzes production process information of the vehicle required by a client, issues the information to the production equipment through the IOT platform, and executes the steps of collecting the state and production data of the production equipment, judging whether the production equipment works normally or not and judging whether the product quality reaches the standard or not. By adopting the technical scheme, based on a two-way communication mechanism between the MES and the IOT platform, rapid customization, accurate issuing and real-time adjustment of the process data are realized, so that the efficient production requirement of flexible manufacturing of automobiles is met.

The invention discloses an AGV scheduling system and scheduling method, relates to the technical field of flexible workshop job scheduling, and solves the problems that local optimization damages global circulation efficiency, characterization defects and invalid actions frequently occur and robustness is poor in the prior art. The system comprises a manufacturing execution system, a data acquisition module, a decision-making system and an environment interaction module, the manufacturing execution system decomposes a production plan into discrete manufacturing tasks and stores the discrete manufacturing tasks in a dynamically updated task pool, a workshop environment generates state information in real time, the state information comprises environment dynamics and AGV instant observation data, and the AGV real-time observation data is transmitted to the manufacturing execution system. The decision-making system adopts a neural network model based on multi-agent reinforcement learning, multiple groups of candidate scheduling strategies are generated by processing real-time observation data, the environment interaction module is responsible for verifying feasibility verification and performance evaluation of actions, iterative updating of the system state is achieved by generating observation values, and the decision-making system is in real-time scheduling. The modular design ensures the real-time performance and adaptability of the scheduling decision.

The invention discloses a production process real-time optimization and quality tracing method and system based on multi-source equipment data fusion, and relates to the technical field of intelligent manufacturing and quality control. Real-time standardized fusion of multi-source heterogeneous data is realized through edge calculation, quality risks are accurately evaluated by using a process-level digital twin model and a multi-layer graph neural network, real-time adjustment and optimization of a production process are realized by using a multi-objective optimization algorithm, a complete and credible quality tracing system is constructed in combination with a causal graph model and a block chain technology, and the quality tracing efficiency is improved. The problems of data islands, optimization lag and tracing fracture existing in a traditional manufacturing execution system are fundamentally solved, and transparency, intelligent real-time optimization and full-chain credible quality tracing of the production process are achieved.

The invention relates to an intelligent digital management method for friction plate production, which belongs to the technical field of friction plate processing and comprises the following operation steps of: 1, performing intelligent production scheduling; and 2, processing the core plate, counting and summarizing, and performing formula digitization and mistake proofing according to classification requirements. And a third step of carrying out equipment data acquisition and health management on the equipment based on IIOT and SCADA equipment and data interconnection. And 4, performing appearance defect detection and performance prediction on the friction plate based on intelligent quality control of machine vision and AI. And 5, finally summarizing the number of the types of friction plates required by the order, and meanwhile, displaying the number of semi-finished products in the operation process of each production line and each device in real time. Through fusion of advanced technologies such as industrial Internet of Things, artificial intelligence, big data analysis and a manufacturing execution system, the problems of difficult production scheduling, unstable quality, information isolated island, difficult tracing and the like in traditional friction plate production are solved, so that transparency, automation, intelligence and lean production process are realized.

The invention relates to a wafer-level film stress regulation and control method, module and device. The method comprises the following steps: constructing a stress regulation and control module according to set parameters and a structure, and integrating the constructed stress regulation and control module at a set position of a semiconductor device; wherein the stress regulation and control module comprises a stress regulation and control layer, and the stress regulation and control layer adopts a metal / medium composite laminated structure; in the wafer manufacturing process, a target net stress value needed by a current wafer is obtained through a manufacturing execution system, the optimal thickness proportion needed by a stress regulation and control layer for achieving the target net stress value is calculated through an internal stress prediction model, and the manufacturing execution system generates a technological formula according to the optimal thickness proportion; and the deposition equipment is driven to deposit the stress regulation and control layer under the optimal thickness ratio. By designing the independent stress regulation and control module, it can be ensured that the crystallization quality, the stoichiometric ratio and the electrical / piezoelectric performance of the functional film are not sacrificed, and linear, accurate and predictable stress control over the wafer is achieved.

This disclosure relates to a method, apparatus, electronic device, and storage medium for controlling the transfer of a wound yarn package. [Solution] The method includes, when each of the multiple second controllers is determined to be a target controller, and the communication link from the target controller to the first controller is determined to be in a normal state, receiving target business data transmitted by the target controller, transmitting the target business data to the manufacturing execution system, receiving target transfer instructions transmitted by the manufacturing execution system, and transmitting the target transfer instructions to the target controller. The manufacturing execution system is for acquiring target transfer instructions based on the target business data and transmitting the target transfer instructions to the first controller. The target controller performs transfer control operations on the wound yarn package product passing through the target work station corresponding to the target controller based on the target transfer instructions.

The invention relates to the technical field of antenna detection, in particular to an antenna detection device based on an MES (Manufacturing Execution System) combined with a vector network analyzer, which comprises the MES, the vector network analyzer (VNA), an automatic test platform and an industrial personal computer, the manufacturing execution system (MES) is configured to generate and issue a structured electronic work order including a product model, test parameter configuration information and a performance qualification limit value; the vector network analyzer (VNA) is an automatic test platform used for executing radio frequency performance parameter measurement on a tested antenna, and comprises a turntable used for fixing and driving the tested antenna to perform azimuth or pitching rotation, and a radio frequency switch matrix used for switching test signal paths among a plurality of tested antenna ports or a plurality of antennas; and the industrial personal computer is in communication connection with the MES, the VNA and the automatic test platform.

A system and method include dividing, by a processor of a manufacturing execution system (MES), a time axis associated with a time window into a plurality of time slots, assigning an integer value to an integer variable indexed by a slot identifier, a machine identifier, and a wafer lot identifier, specifying one or more constraints based on the integer variable, wherein the one or more constraints comprise a wafer quantity constraint and a Q-time constraint, executing an optimization solver under the one or more constraints to determine a time and a quantity of wafer lots to be provided to each machine associated with the time window, and issuing a request to a controller to cause provision of the quantity of wafer lots to each machine associated with each step in the time window.

The application provides a flexible scheduling group and a scheduling method. The scheduling group comprises a manufacturing execution system, a logistics execution system, an intelligent group control system, a logistics intelligent trolley scheduling system and a process intelligent trolley scheduling system. The intelligent group control system receives a production plan issued by the manufacturing execution system, receives inventory material information of the logistics execution system, receives vehicle position information of the logistics intelligent trolley scheduling system and the process intelligent trolley scheduling system respectively, and formulates scheduling tasks of the process intelligent trolley and the logistics intelligent trolley in real time. Through deep cooperation of the intelligent group control system with the manufacturing execution system, the logistics execution system and other systems, overall management of the whole production process is realized. Through real-time sensing of data of environmental changes and / or data of demand fluctuations by the intelligent group control system, and through on-demand pulling, the coordination and stability of line operation are improved through cooperation with multiple systems.

The invention provides a method and system for collecting working state data of a manufacturing execution system, and the method comprises the steps: obtaining an equipment working data set, a personnel working video set and a workpiece information set, and respectively extracting a corresponding equipment working feature sequence set and a corresponding workpiece feature sequence set, performing illumination compensation, foreground segmentation and time window splitting on the personnel operation video set, and performing multi-dimensional attitude decoupling, action semantic recognition and production rhythm modeling on the personnel operation video set after the time window splitting to obtain a personnel action feature sequence set; performing dynamic time warping, beat alignment and feature binding based on the production task order to obtain a multi-modal production feature sequence set, and performing collaborative feature enhancement and dimension reduction compression to obtain a multi-modal working time sequence feature sequence set; and by taking the production task order as an edge index, constructing a dynamic hypergraph model of the multi-modal working time sequence feature sequence set, and carrying out man-machine collaborative analysis on the dynamic hypergraph model to obtain a working state data sequence.

The invention discloses a question and answer model obtaining method and device based on a manufacturing execution system, and relates to the field of production manufacturing and artificial intelligence large models.The method comprises the steps that different service links are obtained according to multiple service files of the manufacturing execution system; obtaining a reasoning sample set according to the logic relationship of each service action in the service link; the reasoning sample comprises a problem, a reasoning path and a result; and inputting the reasoning sample into the general big language model, so as to obtain the trained question and answer model based on the manufacturing execution system according to the general big language model. According to the technical scheme provided by the embodiment of the invention, the training sample of the question and answer model based on the manufacturing execution system is automatically acquired, so that the labor cost and the time cost consumed in a sample labeling process are avoided, the acquisition efficiency of the question and answer model is improved, the phenomena of wrong labeling and missing labeling existing in manual labeling are avoided, and the accuracy of labeling is improved. And the accuracy of the question-answer model feedback result is improved.