Timing sequence production task active reasoning method and system based on knowledge graph

Abstract

The invention discloses a time sequence production task active reasoning method and system based on a knowledge graph. The method comprises the following steps: analyzing and determining a to-be-executed production task and a resource configuration scheme thereof; obtaining a production task execution state and updating a pre-established knowledge graph; and if an abnormal condition is detected by using the production equipment, determining an affected production task and taking corresponding measures. According to the invention, through an active reasoning mechanism, the efficiency of production scheduling is improved, the response capability of the system to emergencies is enhanced, and the reduction of production delay and resource waste is facilitated.

Description

Technical Field

[0001] The present invention relates to a method and system for active reasoning of time-series production tasks based on a knowledge graph, and belongs to the technical field of active reasoning methods for time-series production tasks based on a knowledge graph. Background Art

[0002] With the development of Industry 4.0 and smart manufacturing, task management and scheduling within the production process are becoming increasingly complex. Traditional production scheduling methods often rely on static rules or manual experience. Faced with complex task dependencies, dynamic resource allocation, and unexpected situations, they are inefficient and slow to respond. This prevents many companies from adapting to changes in production scheduling, leading to reduced production efficiency, wasted resources, and delayed delivery. Against this backdrop, knowledge graphs are gaining increasing attention as an effective data representation and reasoning tool. Knowledge graphs represent entities and their relationships through a graph structure, visually displaying the temporal relationships and dependencies between production tasks. Compared to traditional databases, they support more complex queries and reasoning, helping managers gain deeper insights.

[0003] Knowledge graphs have significant application value in areas such as intelligent manufacturing, project management, and supply chain optimization. In intelligent manufacturing, building a knowledge graph of the production process helps identify relationships between tasks, optimize resource allocation, and predict production bottlenecks. However, existing knowledge graphs still have shortcomings in dynamic reasoning and real-time scheduling, lacking active reasoning mechanisms for time-series production tasks. As data volumes increase, effectively managing and utilizing this data becomes another challenge for enterprises. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide a method and system for active reasoning of time-series production tasks based on a knowledge graph. The present invention is to cope with the increasingly complex production task management needs in the modern manufacturing industry. By constructing a knowledge graph of production tasks, the present invention can effectively represent the temporal relationship and dependency between tasks, analyze the production status in real time, and thus achieve dynamic scheduling and optimize resource allocation. Through the active reasoning mechanism, the method of the present invention not only improves the efficiency of production scheduling, but also enhances the system's ability to respond to emergencies, helping to reduce production delays and resource waste. The present invention improves the intelligence level of enterprises and promotes the transformation of the manufacturing industry to digitalization and intelligence.

[0005] Prioritizing, the present invention provides a method for active reasoning of time-series production tasks based on knowledge graphs, comprising: Analyze and determine the production tasks to be executed and their resource allocation plans; Obtain the execution status of production tasks and update the pre-established knowledge graph; If an abnormal situation is detected using production equipment, the affected production tasks are determined and appropriate measures are taken.

[0006] Prioritize analyzing the current production task status and determining the production tasks to be executed and their resource allocation plans, including: Based on predefined inference rules, traverse the nodes in the knowledge graph, analyze the dependencies between production tasks, and filter out tasks to be started based on the current task status.

[0007] Preferably, the predefined inference rules include: Execute production tasks in order from high to low based on the pre-determined priority of production tasks; Determine whether the production resources required for the production task are occupied. If not, execute the corresponding production task.

[0008] Prioritize obtaining the production task execution status and updating the pre-established knowledge graph, including: Use production equipment to collect production site data in real time; Update the knowledge graph based on production site data.

[0009] Prioritizing, abnormal situations include delays in production tasks, and corresponding measures include adjusting the priority of production tasks and reallocating production resources.

[0010] Prioritize pre-building a knowledge graph, including: Build a knowledge graph based on pre-collected production tasks, production equipment, and resource data; Among them, resource data includes but is not limited to raw materials, human resources, machinery and equipment, and energy resources.

[0011] Prioritize the knowledge graph-based active reasoning system for time-series production tasks, including: The inference engine module is used to analyze and determine the production tasks to be executed and their resource allocation plans; Real-time monitoring module, used to obtain the execution status of production tasks and update the pre-established knowledge graph; The exception handling module is used to determine the affected production tasks and take corresponding measures if an abnormal situation is detected using production equipment.

[0012] Preferably, a knowledge graph construction module is used to establish a knowledge graph based on pre-collected production tasks, production equipment and resource data.

[0013] Preferably, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the first aspect when executing the program.

[0014] Preferably, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any one of the methods described in the first aspect when executed by a processor.

[0015] The beneficial effects achieved by the present invention are: 1. Through active reasoning methods based on knowledge graphs, the execution order and dependencies of production tasks can be automatically identified, dynamic scheduling of production tasks and optimal allocation of resources can be achieved, thereby significantly improving production efficiency.

[0016] 2. The inference engine can analyze current production tasks and resource status in real time, avoiding idle resources or uneven resource allocation, thereby improving resource utilization and reducing unnecessary waste.

[0017] 3. The collaborative work of the real-time monitoring module and the exception handling module enables the system to quickly respond to abnormal situations in the production process, adjust the production task sequence and resource allocation in a timely manner, and ensure the smooth execution of the production plan.

[0018] 4. The exception handling module can effectively respond to emergencies in production, such as task delays and equipment failures. By replanning and adjusting production plans, it ensures production continuity and enhances the robustness of the system.

[0019] 5. Through automated reasoning and scheduling, the present invention reduces dependence on human intervention, reduces labor costs and the possibility of human error, and improves the level of intelligent production management.

[0020] 6. The present invention provides an effective intelligent production management solution for manufacturing enterprises, which can enhance the competitiveness of enterprises in intelligent manufacturing and industrial automation, and help enterprises achieve intelligent transformation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 This is a principle block diagram of the knowledge graph in some embodiments of the present application; Figure 2 It is a system module association diagram in some embodiments of the present application. DETAILED DESCRIPTION

[0023] See also Figure 1, this application discloses an active reasoning method for time-series production tasks based on a knowledge graph, and the knowledge graph construction module is used to establish a knowledge graph of production tasks, production equipment, and resource data, including task nodes and their temporal relationships and dependencies. The knowledge graph construction module collects production task data and represents it as a graph structure, so that each task node and its mutual dependencies can be intuitively displayed. Each node in the knowledge graph represents a specific production task, and the directed edges between the nodes represent the temporal relationship or resource dependency between tasks. By constructing a knowledge graph, the connection and mutual influence of each task in the production system can be fully displayed, which helps the reasoning engine to perform accurate task scheduling.

[0024] The inference engine module is used for active reasoning based on the knowledge graph. Using predefined logical rules, the inference engine infers the status of production tasks, determining the currently executable production tasks and the optimal resource allocation plan. For example, once a task is completed, the inference engine automatically determines the next production task that can be initiated based on the knowledge graph and pushes the relevant information to the scheduling system, enabling automatic connection and efficient scheduling of production tasks. Inference rules can be continuously optimized based on historical production data, enabling the system to adaptively respond to dynamic changes in production and further improve production efficiency.

[0025] The real-time monitoring module is used to monitor the execution of production tasks in real time and collect key data from the production process, including task progress, resource utilization, and equipment operating status. Through this module, the system can obtain real-time information from the production site and feed it back to the knowledge graph for dynamic updates, thereby maintaining the real-time and accuracy of the data in the knowledge graph. The main function of this real-time monitoring module is to ensure that the inference engine's reasoning and decision-making are based on the latest production status, avoiding scheduling errors caused by information lags.

[0026] The exception handling module is used to proactively infer solutions to abnormal situations such as task delays, resource conflicts, and equipment failures. Based on the production task relationships in the knowledge graph and preset inference rules, the exception handling module analyzes the impact of the exception on subsequent production tasks and re-plans the production task sequence or resource allocation to minimize the impact of the exception on production. For example, when a key equipment failure causes a production task delay, the exception handling module can infer alternative production task paths based on the knowledge graph or reasonably adjust the priority of other production tasks to ensure the smooth execution of the production plan.

[0027] The overall workflow of the system includes the following steps: First, a knowledge graph is constructed. By collecting production tasks and their dependent data, a knowledge graph covering production task nodes and their relationships is established. Production task data comes from workshop production equipment, production task execution status, and resource data, ensuring that the knowledge graph fully reflects the actual production environment. Resource data includes raw materials, personnel resources, machinery and equipment, and energy resources, such as the inventory of raw materials required for production tasks, the operating status of equipment, and the availability of personnel.

[0028] Next, the inference engine module analyzes the current production task status and determines the pending production tasks and their resource allocation plans. The inference engine module traverses the nodes in the knowledge graph and, in combination with predefined inference rules, analyzes the dependencies between production tasks and determines which tasks can be initiated based on the current task status. An inference rule might be: If production task A is completed and production equipment X is idle, then start production task B. During this process, the inference engine module also considers resource utilization to ensure optimal resource allocation. For example, if production task B requires production resource R and production resource R is not occupied, then production task B can begin.

[0029] The real-time monitoring module then captures the execution status of production tasks and dynamically updates the knowledge graph. By connecting to production equipment, the real-time monitoring module collects real-time production site data, such as task completion, resource consumption, and equipment status. This data is then passed to the knowledge graph construction module, which then updates the knowledge graph. Dynamic updates to the knowledge graph reflect changes in the production process, providing real-time, accurate reference data for the inference engine.

[0030] Finally, when an abnormal situation is detected, it is handled using the exception handling module. The exception handling module first analyzes the scope of the abnormal situation and then, through the inference engine module, re-plans the order of affected production tasks or reconfigures resource data. For example, when a production task delay is detected in an abnormal situation, the exception handling module can infer which production tasks will be affected and take appropriate measures, such as adjusting the priority of production tasks and reallocating production resources, to minimize the impact of the abnormal situation on production and ensure the continuity and efficiency of production. Abnormal situations include production task delays, resource conflicts, equipment failures, staff absences, and insufficient energy supply, all of which will affect production progress and efficiency.

[0031] In an embodiment of the present application, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above methods when executing the program.

[0032] In an embodiment of the present application, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0033] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0034] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention as disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not invented herein, and the description and examples are to be considered merely as exemplary.

[0035] The above specific implementation methods further illustrate the purpose, technical solutions and beneficial effects of this application in detail. It should be understood that the above are only specific implementation methods of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of this application should be included in the scope of protection of this application.

Claims

1. The active reasoning method for time series production tasks based on knowledge graph is characterized by: include: Analyze and determine the production tasks to be executed and their resource allocation plans; Obtain the execution status of production tasks and update the pre-established knowledge graph; If an abnormal situation is detected using production equipment, the affected production tasks are determined and appropriate measures are taken.

2. The active reasoning method for time series production tasks based on knowledge graph according to claim 1 is characterized in that: Analyze the current production task status and determine the production tasks to be executed and their resource allocation plans, including: Based on predefined inference rules, traverse the nodes in the knowledge graph, analyze the dependencies between production tasks, and filter out tasks to be started based on the current task status.

3. The active reasoning method for time series production tasks based on knowledge graph according to claim 2 is characterized in that: The predefined inference rules include: Execute production tasks in order from high to low based on the pre-determined priority of production tasks; Determine whether the production resources required for the production task are occupied. If not, execute the corresponding production task.

4. The active reasoning method for time series production tasks based on knowledge graph according to claim 1 is characterized in that: Obtain the execution status of production tasks and update the pre-established knowledge graph, including: Use production equipment to collect production site data in real time; Update the knowledge graph based on production site data.

5. The active reasoning method for time series production tasks based on knowledge graph according to claim 1 is characterized in that: Abnormal situations include delays in production tasks, and corresponding measures include adjusting the priority of production tasks and reallocating production resources.

6. The active reasoning method for time series production tasks based on knowledge graph according to claim 1 is characterized in that: Pre-built knowledge graph, including: Build a knowledge graph based on pre-collected production tasks, production equipment, and resource data; Among them, resource data includes but is not limited to raw materials, human resources, machinery and equipment, and energy resources.

7. The active reasoning system for time-series production tasks based on knowledge graph is characterized by: include: The inference engine module is used to analyze and determine the production tasks to be executed and their resource allocation plans; Real-time monitoring module, used to obtain the execution status of production tasks and update the pre-established knowledge graph; The exception handling module is used to determine the affected production tasks and take corresponding measures if an abnormal situation is detected using production equipment.

8. The active reasoning system for time series production tasks based on knowledge graph according to claim 7 is characterized in that: The knowledge graph construction module is used to build a knowledge graph based on pre-collected production tasks, production equipment and resource data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images