Automatic operation management and control method, equipment, medium and program product

Abstract

The invention discloses an automatic operation management and control method and device, a medium and a program product, and relates to the technical field of industrial automation. The automatic operation management and control method comprises the steps of generating an initial structured knowledge graph based on a standardized operation program document, a target equipment manual and a target process standard document; updating the initial structured knowledge graph based on the current planned work order to obtain a to-be-mapped knowledge graph; based on the to-be-mapped knowledge graph and the work order execution process nodes, establishing process knowledge integration data; and according to the operation state change data and the process knowledge integration data, generating a target automatic operation decision instruction. According to the technical scheme of the embodiment of the invention, the business execution system can fuse operation knowledge, automatic operation is realized, and manpower is greatly liberated.

Description

Technical Field

[0001] This invention relates to the field of industrial automation technology, and in particular to an automated operation control method, equipment, medium, and program product. Background Technology

[0002] The core operational knowledge in industrial manufacturing sites often exists in the form of unstructured static documents, which fail to be deeply integrated with the business execution system. As a result, the core operational knowledge cannot be directly understood and invoked by the business execution system, relying on manual transmission and interpretation. This leads to low knowledge utilization and heavy dependence on the experience and conscientiousness of operators, making it difficult to ensure the standardization and consistency of execution. Summary of the Invention

[0003] This invention provides an automated operation management method, equipment, medium, and program product to solve the problem that existing industrial manufacturing processes rely too heavily on manual labor and that operational knowledge cannot be fully utilized by the business execution system.

[0004] According to one aspect of the present invention, an automated operation control method is provided, comprising: An initial structured knowledge graph is generated based on standardized operating procedure documents, target equipment manuals, and target process standard documents. The initial structured knowledge graph is updated based on the current planned work order to obtain the knowledge graph to be mapped; Based on the knowledge graph to be mapped and the work order execution process nodes, establish process knowledge integration data; Based on the data on changes in job status and the integration of process knowledge, the system generates decision instructions for the target automated job.

[0005] According to another aspect of the present invention, an automated operation control device is provided, comprising: The first knowledge graph generation module is used to generate an initial structured knowledge graph based on standardized operating procedure documents, target equipment manuals, and target process standard documents. The second knowledge graph generation module is used to update the initial structured knowledge graph based on the current planned work order to obtain the knowledge graph to be mapped. The knowledge integration module is used to establish process knowledge integration data based on the knowledge graph to be mapped and the work order execution process nodes. The job instruction generation module is used to generate target automated job decision instructions based on job status change data and process knowledge integration data.

[0006] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the automated operation control method according to any embodiment of the present invention.

[0007] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the automated job control method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the automated operation control method described in any embodiment of the present invention.

[0009] The technical solution of this invention generates an initial structured knowledge graph based on standardized work procedure documents, target equipment manuals, and target process standard documents. This initial structured knowledge graph is then updated based on the current planned work order to obtain a knowledge graph to be mapped. Furthermore, based on the knowledge graph to be mapped and the work order execution process nodes, process knowledge integration data is established. Finally, based on work status change data and process knowledge integration data, target automated work decision instructions are generated. This solution integrates multi-dimensional core work knowledge from the business execution system to generate an initial structured knowledge graph. The initial structured knowledge graph is adjusted based on the current planned work order to better suit the current work task. The association between the knowledge graph and the work order execution process nodes ensures that the target automated work decision instructions accurately match the execution process, making the entire production process more standardized. This significantly reduces manual intervention during normal operation, solving the problem of excessive reliance on manual labor in existing industrial manufacturing processes and the inability of the business execution system to fully utilize work knowledge. It enables the business execution system to integrate work knowledge, achieve automated operations, and greatly liberate manpower.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1A flowchart of an automated operation control method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of an automated operation control method provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of an automated operation control system; Figure 4 A schematic diagram illustrating the key steps of an automated operation control method; Figure 5 This is a schematic diagram of an automated operation control device provided in Embodiment 4 of the present invention; Figure 6 A schematic diagram of an electronic device that can be used to implement embodiments of the present invention is shown. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "initial," "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] Example 1 Figure 1 This is a flowchart illustrating an automated operation control method according to Embodiment 1 of the present invention. This embodiment is applicable to intelligent control of industrial automated operations. The method can be executed by an automated operation control device, which can be implemented in hardware and / or software and can be configured in an electronic device. This electronic device may include, but is not limited to, a computer or server. Figure 1 As shown, the method includes: Step 110: Generate an initial structured knowledge graph based on standardized operating procedure documents, target equipment manuals, and target process standard documents.

[0016] The standardized operating procedure (SOP) document can be the SOP document of the business execution system. The target equipment manual can be a systematic document guiding the operation, maintenance, and management of the equipment in the business execution system. The target process standard document can be a technical document that standardizes the production process of the business execution system and ensures quality control. The business execution system can be an industrial production system with automated operation management requirements. For example, the business execution system can include, but is not limited to, a cigarette production system. The initial structured knowledge graph can be a knowledge graph created based on the standardized operating procedure document, the target equipment manual, and the target process standard document.

[0017] In this embodiment of the invention, standardized operating procedure documents, target equipment manuals, and target process standard documents can be obtained first. Then, based on the entities and entity relationships extracted from the standardized operating procedure documents, target equipment manuals, and target process standard documents, a structured initial structured knowledge graph with semantic associations can be constructed.

[0018] Step 120: Update the initial structured knowledge graph based on the current planned work order to obtain the knowledge graph to be mapped.

[0019] Here, the current planned work order can be a work order currently scheduled for execution. The knowledge graph to be mapped can be a knowledge graph obtained by updating the initial structured knowledge graph based on the current planned work order.

[0020] In this embodiment of the invention, the current planned work order can be retrieved from the business execution system before the production task begins. Based on the current planned work order, the entities and corresponding attributes of the initial structured knowledge graph can be updated to obtain the knowledge graph to be mapped.

[0021] Optionally, while updating the entities and corresponding attributes of the initial structured knowledge graph based on the current planned work order, the association between the corresponding generated tasks of the current planned work order and the process standard entities in the knowledge graph to be mapped can also be established to ensure the synchronization of production and knowledge in the knowledge graph.

[0022] Step 130: Based on the knowledge graph to be mapped and the work order execution process nodes, establish process knowledge integration data.

[0023] The integrated process knowledge data can be used to describe the relationship between entities in the knowledge graph to be mapped and work order execution process nodes. Work order execution process nodes can be process nodes in the production task execution process corresponding to the current planned work order. For example, assuming the current planned work order is a cigarette factory tobacco processing line slicing and rehydration work order, the work order execution process nodes can include, but are not limited to, unpacking and pretreatment, vacuum rehydration, slicing / shredding, and loosening and rehydration.

[0024] In this embodiment of the invention, a mapping relationship can be established between entities in the knowledge graph to be mapped and work order execution process nodes, so as to deeply integrate the static knowledge in the knowledge graph to be mapped with the dynamic process. When a certain work order execution process node is executed, the corresponding knowledge in the knowledge graph to be mapped can be activated and associated, namely the entities involved, entity attributes and relationships between entities.

[0025] Step 140: Generate target automated operation decision instructions based on job status change data and process knowledge integration data.

[0026] The job status change data can be used to indicate the flow of work order execution nodes. The target automated job decision instruction can be the operation instruction for the automated execution of the corresponding production task of the current planned work order.

[0027] In this embodiment of the invention, the work status change data can be determined based on the work order execution process node completed in the previous work order, and then the target automated work decision instruction for executing the corresponding task can be determined based on the work status change data and process knowledge integration data.

[0028] Optionally, the target automated job decision instruction for executing the corresponding task at the current work order execution process node can be determined based on job status change data and process knowledge integration data, using orchestration tools, pre-configured database matching, or deep learning models.

[0029] For example, a deep learning model can be pre-trained based on historical job status change data and historical process knowledge integration data to obtain a model that can infer the corresponding job decision instructions for the work order execution process node. The job status change data and process knowledge integration data are then input into the trained model to obtain the target automated job decision instructions, so that the business execution system can execute the target automated job decision instructions in the execution order to realize the automated operation of the work order execution process node tasks.

[0030] The technical solution of this invention generates an initial structured knowledge graph based on standardized work procedure documents, target equipment manuals, and target process standard documents. This initial structured knowledge graph is then updated based on the current planned work order to obtain a knowledge graph to be mapped. Furthermore, based on the knowledge graph to be mapped and the work order execution process nodes, process knowledge integration data is established. Finally, based on work status change data and process knowledge integration data, target automated work decision instructions are generated. This solution integrates multi-dimensional core work knowledge from the business execution system to generate an initial structured knowledge graph. The initial structured knowledge graph is adjusted based on the current planned work order to better suit the current work task. The association between the knowledge graph and the work order execution process nodes ensures that the target automated work decision instructions accurately match the execution process, making the entire production process more standardized. This significantly reduces manual intervention during normal operation, solving the problem of excessive reliance on manual labor in existing industrial manufacturing processes and the inability of the business execution system to fully utilize work knowledge. It enables the business execution system to integrate work knowledge, achieve automated operations, and greatly liberate manpower.

[0031] Example 2 Figure 2 This is a flowchart of an automated operation control method provided in Embodiment 2 of the present invention. This embodiment is a specific embodiment based on the above embodiment, and provides specific optional implementation methods for generating an initial structured knowledge graph based on standardized operation procedure documents, target equipment manuals, and target process standard documents. Figure 2 As shown, the method includes: Step 210: Extract entities and entity relationships from the standardized operating procedure documents, target equipment manuals, and target process standard documents to obtain target entities and their basic relationships.

[0032] The target entity can be an entity extracted from standardized operating procedure documents, target equipment manuals, and target process standard documents. The basic relationships between target entities can be semantic relationships between entities extracted from standardized operating procedure documents, target equipment manuals, and target process standard documents.

[0033] For example, target entities may include, but are not limited to, process activities (such as no-load operation during pre-production inspection, production process control, and production end-of-production processing), work steps (such as system login and authentication, slowly opening the main steam valve, and confirming equipment readiness item by item according to the checklist), equipment (such as a slicer and a loose rehumidifier), standard process parameters (such as standard slice thickness and standard moisture content at the rehumidification outlet), production tasks (specific grades and batches generated by the manufacturing execution system work order), and status conditions (such as safety doors being closed, work orders being issued, equipment being preheated, and equipment being ready). The basic relationships between target entities may include inclusion relationships (pre-production inspection includes system login and authentication, confirming equipment readiness item by item according to the inspection steps, and equipment being preheated), parameter constraint relationships (slice thickness of the slicer), and compliance relationships (standard moisture content at the rehumidification outlet and standard rehumidification hot air temperature).

[0034] In this embodiment of the invention, entities can be extracted from standardized operating procedure documents, target equipment manuals, and target process standard documents to obtain target entities, and semantic relationships of entities in standardized operating procedure documents, target equipment manuals, and target process standard documents can be extracted to obtain basic relationships of target entities.

[0035] Step 220: Obtain state-sensitive operations and sequence-sensitive operations, and determine the execution attributes of job steps in the target entity based on state-sensitive operations and sequence-sensitive operations.

[0036] State-sensitive operations are those whose execution order is variable within a workflow, provided that the execution result meets the prerequisite states required for subsequent steps; these can be simply referred to as flexible steps. Sequence-sensitive operations, on the other hand, are those that must be executed strictly in a predetermined order within a workflow; changing the execution order will lead to safety risks, quality defects, or workflow failure; these can be simply referred to as rigid steps. The execution attributes of a work step can include either flexible or rigid steps.

[0037] In this embodiment of the invention, state-sensitive operations and sequence-sensitive operations can be defined based on standardized work procedure documents. Then, based on state-sensitive operations and sequence-sensitive operations, the execution attributes of work steps in the target entity can be determined, that is, whether the work steps in the target entity are rigid steps or flexible steps.

[0038] Step 230: Determine the initial structured knowledge graph based on the target entity, the basic relationships between the target entities, and the execution attributes of the operation steps in the target entity.

[0039] In this embodiment of the invention, the execution attributes of the work steps in the target entity can also be used as entity relations, thereby creating an initial structured knowledge graph based on the target entity and the entity relations between target entities (the basic relations of the target entity and the execution attributes of the work steps in the target entity).

[0040] Step 240: Update the initial structured knowledge graph based on the current planned work order to obtain the knowledge graph to be mapped.

[0041] In an optional embodiment of the present invention, updating the initial structured knowledge graph based on the current planned work order to obtain the knowledge graph to be mapped may include: parsing the current planned work order to obtain the work order production task entity and the work order process standard entity; updating the initial structured knowledge graph according to the work order production task entity and the work order process standard entity to obtain the knowledge graph to be mapped.

[0042] The work order production task entity can be a production task extracted from the current planned work order. The work order process standard entity can be a process standard extracted from the current planned work order.

[0043] In this embodiment of the invention, the current planned work order can be parsed to obtain the work order production task entity and the work order process standard entity. Then, based on the work order production task entity and the work order process standard entity, the initial structured knowledge graph can be dynamically created or updated to obtain the knowledge graph to be mapped.

[0044] Step 250: Based on the knowledge graph to be mapped and the work order execution process nodes, establish process knowledge integration data.

[0045] In an optional embodiment of the present invention, establishing process knowledge integration data based on the knowledge graph to be mapped and the work order execution process nodes may include: establishing a process knowledge mapping relationship between the target entity in the knowledge graph to be mapped and the work order execution process nodes according to the standardized work procedure document; and using the process knowledge mapping relationship as process knowledge integration data.

[0046] Among them, the process knowledge mapping relationship can be the association mapping relationship between the target entity in the knowledge graph to be mapped and the work order execution process node.

[0047] In this embodiment of the invention, the association between the target entity in the knowledge graph to be mapped and the work order execution process node can be determined based on the standardized work procedure document. The association between the two is used as the process knowledge mapping relationship to establish the mapping between the target entity in the knowledge graph to be mapped and the work order execution process node. Furthermore, the process knowledge mapping relationship is used as process knowledge integration data to assist the business execution system in realizing automated operations.

[0048] Step 260: Generate target automated operation decision instructions based on job status change data and process knowledge integration data.

[0049] In an optional embodiment of the present invention, generating a target automated operation decision instruction based on operation status change data and process knowledge integration data may include: retrieving the operation status decision database based on the operation status change data and process knowledge integration data to obtain the target automated operation decision instruction; wherein, the target automated operation decision instruction may include control equipment reverse control instructions and / or manual guided operation instructions.

[0050] The job status decision database can be a database consisting of historical execution task instances from the business execution system and their corresponding decision instructions. Control equipment reverse control instructions can be control instructions to the underlying control system within the target automated job decision instructions. Manually guided operation instructions can be guided operation instructions within the target automated job decision instructions that require manual completion.

[0051] In this embodiment of the invention, the job status change data and process knowledge integration data can be matched with the job flow of historical execution task instances in the job status decision database. The decision instruction corresponding to the historical execution task instance with the highest similarity is selected according to the job status change data of the current planned work order. The target automated job decision instruction is selected, that is, the job decision instruction required for the execution of the task node of the work order to be started.

[0052] For example, the control equipment's reverse control command is first sent to the reverse control execution unit (such as a PLC, manufacturing execution system, etc.). The reverse control execution unit automatically reads the equipment's status data, performs equipment readiness diagnostics, and compares the current equipment parameters with the work order standards. After completing the manual guidance work completion assessment, equipment diagnostics, and parameter presets, if everything is normal, the reverse control execution unit automatically unlocks the equipment and starts the equipment. Manually guided operation commands are sent to the process-driven guidance unit (such as a human-interactive screen). This unit generates dynamic pre-production inspection steps on the operator's smart terminal. The process-driven guidance unit guides the operator to perform inspections through text, images, voice, etc. The system only unlocks the next inspection task after the operator completes each item and confirms it by scanning a code, taking a photo, etc.

[0053] In an optional embodiment of the present invention, after generating the target automated operation decision instruction based on the operation status change data and process knowledge integration data, the method may further include: collecting the status of the work order operation equipment and real-time material process parameters; performing attribute verification on the work order operation equipment status, real-time material process parameters and operation steps based on the knowledge graph to be mapped, and generating abnormal warning data when there is a verification anomaly.

[0054] The work order equipment status can be the real-time collected operating status of the corresponding equipment in the current planned work order. Real-time material process parameters can be the real-time collected process parameters of the materials during the current planned work order operation. Anomaly warning data can be warning data generated when production anomalies occur during the execution of the target automated operation decision instruction. Anomaly warning data may include, but is not limited to, verification failure items, the time when the verification failure items occurred, and the duration of the anomaly.

[0055] In this embodiment of the invention, industrial IoT data sensing sensors can collect the status of work order equipment and real-time material and process parameters according to a data acquisition cycle. Then, based on the knowledge graph to be mapped, the status of work order equipment, real-time material and process parameters, and execution attributes of work steps are verified. If the verification passes, it indicates that the task execution of the work order execution process node is successful and no manual intervention is required. If the verification fails, it indicates that the task execution of the work order execution process node is abnormal, and thus, based on the relevant data of the verification failure item, abnormal warning data is generated.

[0056] In an optional embodiment of the present invention, after generating an initial structured knowledge graph based on standardized work procedure documents, target equipment manuals, and target process standard documents, the method may further include: obtaining automated work decision data generated by a digital twin model constructed from historical work order execution data; determining the confidence level of optimized process parameters and the execution order of work steps based on the automated work decision data; and updating the initial structured knowledge graph according to the confidence level of optimized process parameters and the execution order of work steps.

[0057] Among these, historical work order execution data can be relevant operational data from when the business execution system executes historical work orders. Automated operation decision data can be decision instructions generated by a digital twin model based on historical work order execution data. Optimized process parameters can be process parameters optimized based on automated operation decision data. The confidence level of the execution sequence of operation steps can be the confidence level of the execution attributes of the operation steps determined based on automated operation decision data.

[0058] In this embodiment of the invention, a digital twin model for automated operation management can be constructed based on historical work order execution data. Automated operation decision data is then generated using this digital twin model, and machine learning algorithms are used to optimize this data, obtaining optimized process parameters and confidence levels for the execution order of operation steps. The latest optimized process parameters and confidence levels for the execution order of operation steps are then updated to the initial structured knowledge graph. By continuously acquiring new knowledge through the digital twin model to constantly update the initial structured knowledge graph, the accuracy of the generated target automated operation decision instructions is improved. This approach enables continuous self-evolution and decision optimization based on data feedback, enhancing the continuous improvement and intelligence level of the manufacturing process. It overcomes the shortcomings of standardized work procedure documents, which rely on periodic manual revisions for optimization and updates, resulting in slow response times and difficulty in adapting to dynamic changes in the production environment (such as equipment performance degradation, raw material fluctuations, and the introduction of new products).

[0059] For example, by analyzing automated operation decision data, the optimal control range of process parameters can be discovered and parameter optimization suggestions can be proposed. At the same time, by statistically analyzing the success rate of different operation sequences, the confidence of the relationship between steps in the knowledge graph to be mapped can be dynamically adjusted, so that the decision and guidance strategy can continuously evolve and become more accurate over time.

[0060] The technical solution of this invention involves extracting entities and entity relationships from standardized work procedure documents, target equipment manuals, and target process standard documents to obtain target entities and their basic relationships. This process yields state-sensitive and sequence-sensitive operations. Based on these operations, the execution attributes of work steps within the target entities are determined. Subsequently, an initial structured knowledge graph is established based on the target entities, their basic relationships, and the execution attributes of the work steps. This initial structured knowledge graph is then updated based on the current planned work order to obtain a knowledge graph to be mapped. Based on this knowledge graph and the work order execution process nodes, process knowledge integration data is established. Finally, based on work status change data and the process knowledge integration data, target automated work decision instructions are generated. This solution integrates multi-dimensional core operational knowledge from the business execution system with the execution attributes of operational steps to generate an initial structured knowledge graph carrying these attributes. The initial structured knowledge graph is then adjusted based on the current work order to better suit the current task. The association between the knowledge graph and the work order execution process nodes ensures that the target automated operation decision instructions accurately align with the execution process, making the entire production process more standardized. It allows for flexible execution of operational steps with different execution attributes, breaking away from rigid sequential matching logic. This solves the problem of existing industrial manufacturing processes over-relying on manual labor and the inability of the business execution system to fully utilize operational knowledge. It enables the business execution system to integrate operational knowledge, achieving automated operations and significantly freeing up manpower.

[0061] Example 3 Embodiment 3 of the present invention provides an optional embodiment of an automated operation control system and an automated operation control method, the specific implementation of which can be found in the following embodiments. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0062] like Figure 3 As shown, the automated operation control system comprises a knowledge graph construction layer, a process knowledge integration layer, an intelligent decision-making and execution layer, and an adaptive optimization layer. The business execution system includes a manufacturing execution system (MAS), a PLC (Programmable Logic Controller), and an IoT platform. The automated operation control system establishes communication connections with field devices such as the MAS, PLC, and industrial IoT sensors through the workshop network. By constructing a knowledge graph to be mapped and deeply integrating it with the manufacturing process, the automated operation control system enables knowledge to empower the entire manufacturing process with contextual awareness, intelligent decision-making, precise execution, real-time verification, and continuous optimization.

[0063] The knowledge graph construction layer transforms standardized operating procedure documents, target equipment manuals, and target process standard documents into a structured, semantically related initial structured knowledge graph through entity extraction and relation definition. This initial structured knowledge graph includes core entities such as process activities, work steps, equipment, process parameters, and exception types, as well as semantic relationships such as inclusion, constraint, and triggering between them.

[0064] The knowledge graph construction layer is also used to retrieve the latest current planned work order before the production task begins through a predefined application programming interface, then parse the current planned work order, and dynamically update the production task entities and their related attributes (such as production grade, batch, and quantity) in the initial structured knowledge graph. At the same time, it establishes the association between the task and the existing process standard entities in the initial structured knowledge graph to ensure the real-time synchronization of production plan and execution knowledge.

[0065] The process knowledge integration layer is used to pre-establish mapping relationships between entities such as work steps in standardized work procedure documents and nodes in the business execution process, thereby obtaining a knowledge graph to be mapped and achieving deep integration of static knowledge and dynamic processes. When the process executes to a specific node, it can automatically activate and associate all relevant knowledge in the knowledge graph, providing a data foundation for context-aware decision-making.

[0066] The intelligent decision-making and execution layer responds to changes in the manufacturing process state by reasoning based on the knowledge graph to be mapped, generating target automated operation decision instructions. These target automated operation decisions include control equipment feedback instructions and manually guided operation instructions, achieving intelligent collaboration between automation and manual operation.

[0067] The intelligent decision-making and execution layer is also used to intelligently select the execution mode based on the task characteristics of the target automated operation decision. For example, for tasks that are standardized and have automated interfaces, it executes control equipment reverse control commands. For tasks that require manual judgment and operation, it executes control equipment reverse control commands and provides operators with guidance information in the form of graphics, text, and voice through intelligent human-machine interfaces such as augmented reality devices and mobile terminals to ensure the standardization and compliance of operations.

[0068] Optionally, the automated operation management system also includes a multi-dimensional intelligent verification module, which collects the status of field equipment and process parameters in real time through IoT data sensing sensors, and automatically compares the collected data with predefined standard values ​​in the knowledge graph to be mapped, so as to realize real-time compliance monitoring of equipment status and process parameters.

[0069] The multidimensional intelligent verification module introduces state verification logic based on step hierarchy, which distinguishes work steps into rigid steps and flexible steps by execution attributes, ensuring the correctness of the results while giving necessary flexibility to the on-site operation.

[0070] The multi-dimensional intelligent verification module achieves a leap from rigid sequential matching to intelligent state-condition verification. For rigid steps, their strong sequential dependencies are clearly defined. For example, the prerequisite for starting the equipment is the completion of closing the safety door, and the safety door status is "closed". For flexible steps, the target state they need to contribute is defined. For example, the production end process includes steps C1 (equipment cleaning), C2 (site cleaning), and C3 (record completion). Their common goal is to achieve the final state S (site deliverable), which requires three sub-states: equipment clean = true, site tidy = true, and record complete = true, to be true simultaneously. The correspondence between steps C1, C2, C3 and these sub-states is defined in the knowledge graph to be mapped.

[0071] In the rigid step comparison, when the operation intention is recognized, the multi-dimensional intelligent verification module does not check whether the previous step in the operation log was closing the safety door. Instead, it queries the knowledge graph to be mapped in real time to see if the preconditions for starting the equipment are met. That is, it directly checks whether the safety door status signal read from the PLC is closed. If the condition is not met, even if the operation record seems continuous, it will determine that the sequence is violated and prevent the start-up, fundamentally eliminating safety hazards. Taking the production end processing as an example, the flexible step comparison allows the operator to flexibly arrange the order of C1, C2, and C3. The multi-dimensional intelligent verification module does not interfere with the order during the process. The verification content is not the order of steps, but rather checks whether the three status flags of equipment cleanliness, site tidiness, and record completeness are all set. As long as the status conditions are met, the sequence is determined to be executed correctly.

[0072] The multi-dimensional intelligent verification module generates precise warnings when comparisons fail. For violations of rigid steps, it indicates that the operation is prohibited, such as failure to meet prerequisites [specific condition name]. For failure to achieve the final state of flexible steps, it indicates that the stage is incomplete, such as the non-compliant item being listed in the [specific state list]. During production, IoT data sensing sensors collect process parameters such as slice thickness and moisture content at the rehydration outlet in real time. The real-time collected data is automatically and continuously compared with predefined standard ranges in the knowledge graph to be mapped. Once parameter exceedances or abnormal trends are detected, the system immediately triggers multi-level warnings and pushes the abnormal warning data to relevant positions, enabling early detection and handling of quality issues.

[0073] The adaptive optimization layer is used to build a manufacturing digital twin model based on historical work order execution data, and to continuously evaluate the decision-making effect of the automated operation decision data generated by the digital twin model using machine learning algorithms. This includes setting judgment logic thresholds (such as optimization process parameter alarm thresholds) and the confidence of relationships between entities in the knowledge graph to be mapped (such as the confidence of the effectiveness of optimization anomaly handling schemes). This enables the knowledge graph and decision-making strategy to evolve collaboratively, giving the system the vitality for continuous improvement.

[0074] For example, taking the slicing and rehydration process as an example, such as Figure 4As shown, the key steps of the automated operation control method are as follows: Standardized operation procedure documents, target equipment manuals, and target process standard documents are used as data sources to extract entities and relationships, constructing an initial structured knowledge graph. The initial structured knowledge graph is updated based on the current planned work order to obtain a knowledge graph to be mapped. This knowledge graph is then deeply mapped to the work order execution process nodes, resulting in integrated process knowledge data. Further, based on the operation status change data and the integrated process knowledge data, target automated operation decision instructions are generated. While executing the target automated operation decision instructions, the status of the work order's equipment and real-time material and process parameters can be collected in real time. The collected data is compared with the knowledge graph to be mapped to complete multi-dimensional process verification. After the target automated operation decision instructions are executed, adaptive optimization is performed based on the execution effect. The optimization results are applied to new operation tasks, forming a closed loop of perception, decision-making, execution, and optimization.

[0075] Before the daily planned production time, the system automatically retrieves work order data for the day's slicing and rehydration process from the Manufacturing Execution System (MES), parses the work orders, dynamically creates or updates production task entities in the knowledge graph to be mapped, and associates and binds them with existing process standard entities in the graph to ensure real-time synchronization between production instructions and knowledge standards. When the system time reaches the pre-planned start time (e.g., 10 minutes), the intelligent decision layer is triggered. Based on the activation of pre-production inspection process nodes, it queries the knowledge graph to be mapped and generates target automated operation decision instructions.

[0076] This solution achieves deep integration and dynamic activation of knowledge and processes, transforming static SOP documents into directly accessible structured knowledge. Through automatic linkage with the Manufacturing Execution System (MES) plan, it ensures real-time consistency between knowledge and production tasks, fundamentally solving the problem of knowledge-application disconnect. It enables context-aware intelligent decision-making; through deep mapping of knowledge graphs and process nodes, it can activate relevant knowledge based on real-time context, enabling hybrid decision-making. This reduces reliance on human experience, improves the scientific rigor and consistency of decision-making, enhances the intelligence level of human-machine collaboration, and achieves seamless collaboration between automation and manual operation, significantly improving execution efficiency and accuracy. By introducing verification of operational steps with different execution attributes, it overcomes the rigidity of traditional sequential verification, ensuring strict execution of critical steps while providing reasonable operational flexibility for non-critical steps. This improves system usability and user experience, endowing the system with continuous self-optimization capabilities. Furthermore, based on digital twin and machine learning technologies, it can autonomously learn and optimize decision-making strategies and knowledge content from operational data, with adaptive capabilities that continuously improve over time, effectively responding to dynamic changes in the manufacturing environment.

[0077] Example 4 Figure 5 This is a schematic diagram of an automated operation control device provided in Embodiment 4 of the present invention. Figure 5 As shown, the device includes: The first knowledge graph generation module 310 is used to generate an initial structured knowledge graph based on standardized operating procedure documents, target equipment manuals, and target process standard documents. The second knowledge graph generation module 320 is used to update the initial structured knowledge graph based on the current planned work order to obtain the knowledge graph to be mapped. Knowledge integration module 330 is used to establish process knowledge integration data based on the knowledge graph to be mapped and the work order execution process nodes; The job instruction generation module 340 is used to generate target automated job decision instructions based on job status change data and process knowledge integration data.

[0078] The technical solution of this invention generates an initial structured knowledge graph based on standardized work procedure documents, target equipment manuals, and target process standard documents. This initial structured knowledge graph is then updated based on the current planned work order to obtain a knowledge graph to be mapped. Furthermore, based on the knowledge graph to be mapped and the work order execution process nodes, process knowledge integration data is established. Finally, based on work status change data and process knowledge integration data, target automated work decision instructions are generated. This solution integrates multi-dimensional core work knowledge from the business execution system to generate an initial structured knowledge graph. The initial structured knowledge graph is adjusted based on the current planned work order to better suit the current work task. The association between the knowledge graph and the work order execution process nodes ensures that the target automated work decision instructions accurately match the execution process, making the entire production process more standardized. This significantly reduces manual intervention during normal operation, solving the problem of excessive reliance on manual labor in existing industrial manufacturing processes and the inability of the business execution system to fully utilize work knowledge. It enables the business execution system to integrate work knowledge, achieve automated operations, and greatly liberate manpower.

[0079] Optionally, the first knowledge graph generation module 310 is used to extract entities and entity relationships from the standardized work procedure document, target equipment manual, and target process standard document to obtain target entities and basic relationships of target entities; acquire state-sensitive operations and sequence-sensitive operations, and determine the execution attributes of work steps in the target entities based on the state-sensitive operations and sequence-sensitive operations; and determine the initial structured knowledge graph according to the target entities, the basic relationships of target entities, and the execution attributes of work steps in the target entities.

[0080] Optionally, the second knowledge graph generation module 320 is used to parse the current planned work order to obtain the work order production task entity and the work order process standard entity; and update the initial structured knowledge graph according to the work order production task entity and the work order process standard entity to obtain the knowledge graph to be mapped.

[0081] Optionally, the knowledge integration module 330 is used to establish a process knowledge mapping relationship between the target entity in the knowledge graph to be mapped and the work order execution process node based on the standardized work procedure document; and to use the process knowledge mapping relationship as the process knowledge integration data.

[0082] Optionally, the job instruction generation module 340 is used to retrieve the job status decision database based on the job status change data and the process knowledge integration data to obtain the target automated job decision instruction; wherein, the target automated job decision includes control equipment reverse control instruction and / or manual guided operation instruction.

[0083] Optionally, the automated operation control device also includes an anomaly warning data generation module, which is used to collect the status of work order operation equipment and real-time material process parameters; based on the knowledge graph to be mapped, it performs attribute verification on the status of work order operation equipment, the real-time material process parameters and operation steps, and generates anomaly warning data when there is a verification anomaly.

[0084] Optionally, the automated operation management device further includes a knowledge graph update module, used to acquire automated operation decision data generated by a digital twin model constructed from historical work order execution data; based on the automated operation decision data, determine the confidence level of optimized process parameters and the execution order of operation steps; and update the initial structured knowledge graph according to the optimized process parameters and the confidence level of the execution order of operation steps.

[0085] The automated operation control device provided in the embodiments of the present invention can execute the automated operation control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0086] Example 5 Figure 6 A schematic diagram of an electronic device that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0087] like Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory, such as ROM 12, RAM 13, etc., communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An I / O interface 15 is also connected to the bus 14. The ROM 12 is a read-only memory, the RAM 13 is a random access memory, and the I / O interface 15 is an input / output interface.

[0088] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0089] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as automated job management methods.

[0090] In some embodiments, the automated job control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the automated job control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the automated job control method by any other suitable means (e.g., by means of firmware).

[0091] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0092] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0093] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0094] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0095] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0096] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS servers, such as high management difficulty and weak business scalability.

[0097] This application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the automated job control method provided in any embodiment of this application. This program product shares the same inventive concept as the automated job control methods disclosed in the embodiments of this application, and therefore will not be described in detail here.

[0098] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An automated operation control method, characterized in that, include: An initial structured knowledge graph is generated based on standardized operating procedure documents, target equipment manuals, and target process standard documents. The initial structured knowledge graph is updated based on the current planned work order to obtain the knowledge graph to be mapped; Based on the knowledge graph to be mapped and the work order execution process nodes, establish process knowledge integration data; Based on the job status change data and the process knowledge integration data, a target automated job decision instruction is generated.

2. The method according to claim 1, characterized in that, Based on standardized operating procedure documents, target equipment manuals, and target process standard documents, an initial structured knowledge graph is generated, including: Entity extraction and entity relation extraction are performed on the standardized operating procedure documents, target equipment manuals, and target process standard documents to obtain target entities and target entity basic relations. Obtain state-sensitive operations and sequence-sensitive operations, and determine the execution attributes of the job steps in the target entity based on the state-sensitive operations and sequence-sensitive operations; The initial structured knowledge graph is determined based on the target entity, the basic relationships between the target entities, and the execution attributes of the operation steps in the target entity.

3. The method according to claim 1, characterized in that, The initial structured knowledge graph is updated based on the current planned work order to obtain the knowledge graph to be mapped, including: The current planned work order is parsed to obtain the work order production task entity and the work order process standard entity; Based on the work order production task entity and the work order process standard entity, the initial structured knowledge graph is updated to obtain the knowledge graph to be mapped.

4. The method according to claim 1, characterized in that, Based on the knowledge graph to be mapped and the work order execution process nodes, process knowledge integration data is established, including: Based on the standardized operating procedure document, establish a process knowledge mapping relationship between the target entity in the knowledge graph to be mapped and the work order execution process node; The process knowledge mapping relationship is used as the process knowledge integration data.

5. The method according to claim 1, characterized in that, Based on the job status change data and the integrated process knowledge data, a target automated job decision instruction is generated, including: Based on the job status change data and the process knowledge integration data, the job status decision database is retrieved to obtain the target automated job decision instruction; The target automated operation decision instructions include control equipment reverse control instructions and / or manual guided operation instructions.

6. The method according to claim 1, characterized in that, After generating the target automated job decision instruction based on the job status change data and the process knowledge integration data, the process knowledge integration also includes: Collect work order equipment status and real-time material and process parameters; Based on the knowledge graph to be mapped, attribute verification is performed on the work order equipment status, the real-time material process parameters, and the work steps, and abnormal warning data is generated when there is a verification anomaly.

7. The method according to claim 1, characterized in that, After generating an initial structured knowledge graph based on standardized operating procedure documents, target equipment manuals, and target process standard documents, the following steps are also included: Automated operation decision data generated by constructing a digital twin model from historical work order execution data; Based on the automated operation decision data, the confidence levels of the optimized process parameters and the execution sequence of operation steps are determined. The initial structured knowledge graph is updated based on the optimized process parameters and the confidence level of the execution order of the operation steps.

8. An electronic device, characterized in that, The electronic device includes: At least one processor, and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the automated operation control method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the automated job control method according to any one of claims 1-7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the automated operation control method according to any one of claims 1-7.

Images