Risk assessment method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and discloses a risk assessment method and device, equipment and a storage medium, and the method comprises the steps: determining a parameter change event of target production equipment needing to carry out parameter change; determining a change query condition involved in the parameter change event, and querying a preset risk knowledge graph according to the change query condition to obtain a target change entity matched with the change query condition and a target association relationship related to the target change entity; generating historical similar change events based on the target change entity and the target association relationship; and performing risk assessment on the parameter change event based on a historical parameter change result of the similar historical change events. According to the method, the historical similar change events of the parameter change events of the target production equipment can be efficiently queried through the preset risk knowledge graph, and parameter change risk assessment is performed based on the parameter change results of the historical similar change events, so that the efficiency of parameter change risk assessment is improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to risk assessment methods, apparatus, equipment and storage media. Background Technology

[0002] In modern industrial production, the efficient operation and precise control of production equipment are key factors in ensuring product quality, production efficiency, and enterprise competitiveness. Production equipment typically has complex parameter settings that directly affect its operating status and the quality of the production process. With changes in production demand, fluctuations in raw material prices, process optimization, and equipment aging, the parameters of production equipment usually need to be changed accordingly. However, parameter changes are often accompanied by potential risks, such as equipment failure, decreased product quality, or reduced production efficiency. Therefore, how to effectively manage and assess the risks of parameter changes is an important issue in industrial production.

[0003] Currently, traditional risk assessments for changes in production equipment parameters typically rely on the experience of technical personnel, and the data collection and analysis process usually takes a considerable amount of time, resulting in a long risk assessment cycle. Summary of the Invention

[0004] The main objective of this application is to provide a risk assessment method, apparatus, equipment, and storage medium, which aims to solve the technical problem that existing risk assessment methods for changes in production equipment parameters rely on manual judgment and are inefficient.

[0005] To achieve the above objectives, this application proposes a risk assessment method, which includes: In response to a parameter change request, determine the parameter change event that requires parameter changes for the target production equipment based on the parameter change request; Determine the change query conditions involved in the parameter change event, and query a preset risk knowledge graph based on the change query conditions to obtain the target change entity that matches the change query conditions and the target association relationship related to the target change entity; Generate historical similar change events based on the target changed entity and the target related relationships; Obtain the historical parameter change results of the historical similar change events, and conduct a risk assessment of the parameter change events based on the historical parameter change results to obtain the parameter change risk assessment results.

[0006] In one embodiment, the change query conditions include equipment model, change parameters, and change magnitude; the step of querying a preset risk knowledge graph based on the change query conditions to obtain target change entities matching the change query conditions and target associations related to the target change entities includes: Based on the device model, a preset risk knowledge graph is queried to obtain a target device node that matches the device model, and a first target association relationship related to the target device node is obtained; The preset risk knowledge graph is queried according to the changed parameters to obtain the target parameter node that matches the changed parameters, and the second target association relationship related to the target parameter node is obtained. Based on the change magnitude, the preset risk knowledge graph is queried to obtain a target change record node that matches the change magnitude, and a third target association relationship related to the target change record node is obtained. The target change record node stores the change magnitude of the corresponding change event. The entities represented by the target device node, the target parameter node, and the target change record node are determined as target change entities that match the change query conditions, and the target association relationships related to the target change entities are determined based on the first target association relationship, the second target association relationship, and the third target association relationship.

[0007] In one embodiment, the step of querying the preset risk knowledge graph based on the changed parameters to obtain the target parameter node matching the changed parameters includes: Determine the parameter category to which the historical change parameters represented by all parameter nodes in the preset risk knowledge graph belong; The target change parameter is determined from the historical change parameters based on the parameter category; Obtain the first parameter property and the first parameter influence range of the target change parameter; Determine the nature of the second parameter and the scope of influence of the changed parameter; The parameter similarity between the target change parameter and the change parameter is determined based on the properties of the first parameter, the properties of the second parameter, the influence range of the first parameter, and the influence range of the second parameter. Based on the parameter similarity, obtain the target parameter node that matches the changed parameter from the target changed parameters.

[0008] In one embodiment, the step of performing a risk assessment on the parameter change event based on the historical parameter change results to obtain a parameter change risk assessment result includes: The parameter change event is matched with all change rules in the preset change rule library, and the target matching change rule is determined based on the matching result; The target impact range of the parameter change event is determined based on the preset risk knowledge graph and the target change entity; Based on the historical parameter change results, the target matching change rules, and / or the target impact range, a risk assessment is performed on the parameter change event to obtain the parameter change risk assessment result.

[0009] In one embodiment, the step of determining the target impact range of the parameter change event based on the preset risk knowledge graph and the target change entity includes: Based on the target change entity, a path search is performed in the preset risk knowledge graph to determine the candidate impact path in which the target change entity is located; The environmental impact dimension of the target change entity is determined based on the equipment operating environment of the target production equipment. The candidate impact paths are filtered according to the environmental impact dimensions to obtain the target impact path; Based on the target influence nodes on the target influence path, the target influence path is expanded to obtain an influence path network; The target impact range of the parameter change event is determined based on the impact path network.

[0010] In one embodiment, before the step of determining a parameter change event requiring parameter change for the target production equipment based on the parameter change request, the method further includes: Extract all changed entities of the production equipment to be evaluated from the pre-defined equipment knowledge resource base; Analyze the text of the statements containing each of the modified entities to determine the relationships between them; A pre-defined risk knowledge graph is constructed based on each of the changed entities and the associated relationships.

[0011] In one embodiment, after the step of performing a risk assessment on the parameter change event based on the historical parameter change results to obtain the parameter change risk assessment result, the method further includes: Based on the results of the parameter change risk assessment, determine whether to change the parameters of the target production equipment; If so, obtain the real-time operating data and product quality data of the target production equipment after the change; A structured change case is constructed based on the real-time operating data, the product quality data, and the change event context of the parameter change event, wherein the change event context is used to describe the parameter change event; The preset risk knowledge graph is updated based on the structured change cases.

[0012] Furthermore, to achieve the above objectives, this application also proposes a risk assessment device, the device comprising: The change response module is used to respond to parameter change requests and determine the parameter change event that requires parameter changes for the target production equipment based on the parameter change request. The change query module is used to determine the change query conditions involved in the parameter change event, and query a preset risk knowledge graph according to the change query conditions to obtain the target change entity that matches the change query conditions and the target association relationship related to the target change entity. The change query module is also used to generate historical similar change events based on the target change entity and the target association. The risk assessment module is used to obtain the historical parameter change results of the same historical change events, and to perform a risk assessment on the parameter change events based on the historical parameter change results to obtain the parameter change risk assessment results.

[0013] In addition, to achieve the above objectives, this application also proposes a risk assessment device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the risk assessment method as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the risk assessment method described above.

[0015] This application provides a risk assessment method, apparatus, device, and storage medium. The method includes: responding to a parameter change request, determining a parameter change event for which a target production equipment needs to undergo parameter changes based on the parameter change request; determining change query conditions involved in the parameter change event, and querying a preset risk knowledge graph based on the change query conditions to obtain a target change entity matching the change query conditions and target associations related to the target change entity; generating historical similar change events based on the target change entity and the target associations; obtaining historical parameter change results of the historical similar change events, and performing a risk assessment on the parameter change event based on the historical parameter change results to obtain a parameter change risk assessment result.

[0016] This application can determine the change query conditions involved in the parameter change event when the target production equipment needs to undergo parameter changes. Based on these query conditions, it queries a preset risk knowledge graph for target change entities matching the query conditions and their related target relationships. Then, it generates historical similar change events based on the target change entities and their relationships, and performs a parameter change risk assessment based on the historical parameter change results of these historical similar change events. Because this application can efficiently query historical similar change events for the target production equipment's parameter change events through a preset risk knowledge graph and assess the risk of the current parameter change event based on the results of these historical similar change events, it can efficiently assess the parameter change risk of the production equipment. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the risk assessment device structure for the hardware operating environment involved in the embodiments of this application; Figure 2 This is a flowchart illustrating the first embodiment of the risk assessment method of this application; Figure 3 This is an architecture diagram of the intelligent control system for parameter changes in the risk assessment method of this application; Figure 4 This is the overall architecture diagram of the intelligent control system for parameter changes in the risk assessment method of this application; Figure 5 This is a closed-loop sequence diagram of parameter change events for production equipment in the risk assessment method of this application; Figure 6 This is a flowchart illustrating the second embodiment of the risk assessment method of this application; Figure 7 This is a flowchart illustrating the third embodiment of the risk assessment method of this application; Figure 8 This is a flowchart illustrating the overall process of parameter change risk assessment in the risk assessment methodology of this application. Figure 9 This is a structural block diagram of the first embodiment of the risk assessment device of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a risk assessment device for the hardware operating environment involved in the embodiments of this application.

[0023] like Figure 1 As shown, the risk assessment device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may be connected to a display screen; optionally, the user interface 1003 may include a standard wired interface or a wireless interface. In this application, the wired interface of the user interface 1003 may be a USB interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0024] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the risk assessment equipment and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0025] like Figure 1 As shown, the memory 1005, which is identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a risk assessment program.

[0026] exist Figure 1 In the risk assessment device shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the user equipment; the risk assessment device calls the risk assessment program stored in the memory 1005 through the processor 1001 and executes the steps of the risk assessment method provided in the embodiments of this application.

[0027] It is important to note that in modern industrial production, the efficient operation and precise control of production equipment are key factors in ensuring product quality, production efficiency, and enterprise competitiveness. Production equipment typically has complex parameter settings that directly affect its operating status and the quality of the production process. With changes in production demand, fluctuations in raw material prices, process optimization, and equipment aging, the parameters of production equipment usually need to be changed accordingly. However, parameter changes are often accompanied by potential risks, such as equipment failure, decreased product quality, or reduced production efficiency. Therefore, how to effectively manage and assess the risks of parameter changes is an important issue in industrial production.

[0028] Currently, traditional risk assessments for changes in production equipment parameters typically rely on the experience of technical personnel, and the data collection and analysis process usually takes a considerable amount of time, resulting in a long risk assessment cycle.

[0029] Therefore, to address the aforementioned shortcomings, this embodiment can determine the change query conditions involved in the parameter change event when the target production equipment needs to undergo parameter changes. Based on these query conditions, it queries a preset risk knowledge graph for target change entities matching the query conditions and their related target relationships. Then, it generates historical similar change events based on the target change entities and their relationships, and performs a parameter change risk assessment based on the historical parameter change results of these similar change events. Because this embodiment can efficiently query historical similar change events of the target production equipment's parameter change event using a preset risk knowledge graph, and perform a risk assessment on the current parameter change event of the target production equipment based on the parameter change results of these historical similar change events, it can efficiently assess the parameter change risk of the production equipment.

[0030] For ease of understanding, the following is combined with Figures 2 to 8 The risk assessment method provided in the embodiments of this application will be described in detail.

[0031] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the risk assessment method of this application. The first embodiment of the risk assessment method of this application is presented as follows: Figure 2 As shown, in this embodiment, the specific method includes: Step S10: In response to the parameter change request, determine the parameter change event for which the target production equipment needs to be changed based on the parameter change request.

[0032] It is understood that the method of this embodiment can be applied to the aforementioned risk assessment equipment (hereinafter referred to as the equipment), which can have functions such as data processing, program execution, and data collection. This embodiment does not limit this. The subject executing this method embodiment can use the aforementioned risk assessment equipment to describe this embodiment and the following embodiments.

[0033] It should be understood that the aforementioned parameter change request may be an instruction to adjust one or more operating parameters of the production equipment, which may be generated by production managers, technicians, or automation systems. In practical applications, the parameter change request may include the specific parameters of the production equipment that need to be changed (such as temperature, pressure, speed, etc.), the content of the change (such as the original value and target value of the parameter, and the magnitude of the change), the reason for triggering the change (such as equipment failure, optimization needs, process adjustment, etc.), the change time, and other information. This embodiment does not impose any limitations on this.

[0034] It should also be understood that the aforementioned target production equipment can be a specific production equipment that requires parameter changes. In actual industrial production environments, there are usually multiple types of production equipment, each with its unique parameter settings and operating status. When a production equipment needs to have its parameters changed, a parameter change request can be triggered. After receiving the parameter change request, the system can parse the request, extract the equipment identifier, and determine the target production equipment that needs the parameter change based on the equipment identifier.

[0035] It should be noted that the aforementioned parameter change event can be a specific action of actually performing parameter change on the target production equipment. This can record the specific process and information of the parameter change, including the equipment identifier of the changing equipment, the changed parameters, the change time, the adjustment range, the operator, and the target value after the change. This embodiment does not impose any limitations on this. In this embodiment, after the system determines the target production equipment based on the received parameter change request, it can generate a specific parameter change event based on the request content of the parameter change request and the actual situation of the target production equipment, to clarify the equipment identifier of the production equipment undergoing the parameter change, the parameters to be adjusted, the adjustment range, and other information.

[0036] Step S20: Determine the change query conditions involved in the parameter change event, and query the preset risk knowledge graph according to the change query conditions to obtain the target change entity that matches the change query conditions and the target association relationship related to the target change entity.

[0037] It should be noted that the above-mentioned change query conditions can be specific conditions used to accurately match relevant entities and relationships in a preset risk knowledge graph. In this embodiment, change query conditions may include, but are not limited to, equipment model, change parameters, change range, and other conditions (such as change time range, change reason, etc.). Specifically, based on the equipment model, other production equipment with the same equipment number or equipment model as the target production equipment can be queried in the preset risk knowledge graph; based on the change parameters, parameters with similar parameter types or parameter names to the parameters that need to be changed for the target production equipment can be queried in the preset risk knowledge graph; based on the change range, adjustment ranges similar to the parameter adjustment range of the target production equipment can be queried in the preset risk knowledge graph.

[0038] It should also be noted that the aforementioned preset risk knowledge graph can be a structured knowledge network used to store parameter change events of production equipment and their related data. Nodes and edges in this graph can represent entities and relationships between them, respectively. In this embodiment, entities in the preset risk knowledge graph can include equipment, equipment parameters, equipment type, reasons for change, risk level, and failure cases. Relationships between entities can refer to associations between entities, such as "parameter change leads to increased risk," "equipment type is associated with parameters," and "reason for change is associated with risk level." For example, the preset risk knowledge graph can include: Entities: Equipment parameters (temperature), Equipment type (heating furnace), Risk level (medium), Failure case (overheating alarm); Relationship: Temperature change → Increased risk level → Failure case.

[0039] It should be understood that the aforementioned target change entity can be a specific entity in a preset risk knowledge graph that matches the change query conditions. These entities can contain specific information about historical change events, such as parameter values ​​before and after the change, adjustment range, and change time.

[0040] It should also be understood that the aforementioned target association relationships can be the relationships between the target change entity and other related entities. These relationships describe the logical connections between entities and can be used to deduce the risks and impacts that parameter changes may bring. In this embodiment, the association relationships between entities may include, but are not limited to, direct association, indirect association, and causal association.

[0041] In practical applications, after receiving parameter change requests from production managers, technicians, or automation systems, the system can parse the request content, extract key information (such as parameter name, target value, equipment type, and reason for change), and construct change query conditions based on this key information. This clarifies the specific parameters, equipment types, and reasons for change that need to be queried in the risk knowledge graph. Then, the system can use the change query conditions to search the preset risk knowledge graph, find the target change entities that match the query conditions, and analyze the relationships between the target change entities to obtain target associations.

[0042] Furthermore, in order to improve the efficiency of parameter change risk assessment, before step S10, the method further includes: extracting all change entities of the production equipment to be assessed from a preset equipment knowledge resource base; analyzing the text of the statements containing each change entity to determine the related relationships of each change entity; and constructing a preset risk knowledge graph based on each change entity and the related relationships.

[0043] It should be noted that the aforementioned preset equipment knowledge resource base can be a collection used to store knowledge and data related to production equipment. In this embodiment, the preset equipment knowledge resource base may include equipment manuals, historical audit logs, a fault case library, technical documents, etc., wherein the equipment manual may contain information such as equipment specifications, operation guidelines, and maintenance requirements; the historical audit logs may record information such as operation logs, parameter changes, and maintenance activities during equipment operation; and the fault case library may store information such as cases of equipment failures, cause analysis, and solutions.

[0044] It is understandable that the aforementioned production equipment to be evaluated can be any specific production equipment that needs to be risk-assessed. These production equipment may require parameter changes due to reasons such as adjustments to production tasks, changes in raw materials, or equipment aging.

[0045] It should be noted that the aforementioned changed entities can be specific objects or concepts related to changes in production equipment parameters, such as equipment components (e.g., motors, sensors), parameters (e.g., temperature, pressure, speed), quality indicators (e.g., defect rate, pass rate), and failure modes (e.g., equipment overheating failure, excessive pressure failure), etc. This embodiment does not impose any restrictions on these entities, which form the basis for constructing the risk knowledge graph.

[0046] It should be understood that the aforementioned text statements can be text information containing changed entities extracted from a preset equipment knowledge resource base. This text can come from equipment manuals, historical audit logs, fault case libraries, etc. For example, the text descriptions in the operation guidelines and maintenance manuals of production equipment recorded in the equipment manual; documents recording changes to equipment parameters in the historical audit logs; and texts describing equipment faults and their solutions in the fault case library. In this embodiment, by analyzing the text in the equipment manual, historical audit logs, and fault case library, the changed entities of the production equipment and their relationships can be extracted.

[0047] It should also be understood that the aforementioned relationships can be logical connections between entities involved in the production equipment change, such as causal relationships, influence relationships, and dependency relationships. In practical applications, the relationships between change entities describe the interactions and influences between them. When constructing a knowledge graph, these relationships can be used to connect different change entities, thereby forming a structured knowledge network.

[0048] In practical applications, the system can locate the production equipment to be evaluated from the knowledge resource base based on the equipment number or model, and extract textual information related to the equipment from resources such as equipment manuals, historical audit logs, and fault case libraries. Then, the system can use Natural Language Processing (NLP) techniques, such as Named Entity Recognition (NER), to identify changed entities from the extracted text, analyze the extracted text to identify the relationships between changed entities, and then use dependency parsing or predefined rules to extract the relationships between entities. Finally, the system can use a graph database to construct a risk knowledge graph based on these changed entities and relationships, storing the changed entities and relationships as nodes and edges, and storing the extracted changed entities and relationships in the graph, ultimately obtaining a pre-defined risk knowledge graph.

[0049] Step S30: Generate historical similar change events based on the target change entity and the target association.

[0050] It should be noted that the aforementioned historical similar change events can be change records from past equipment operation and maintenance processes that are similar to the current parameter change event of the target production equipment in certain key characteristics (such as equipment, parameter type, adjustment range, etc.). These events can provide important reference for the risk assessment of the current parameter change. For example, if the current parameter change event is that the temperature parameter of production equipment E001 is adjusted from 30°C to 40°C, with an adjustment range of 10°C, the matching historical similar change events may include: the temperature parameter of equipment E001 is adjusted from 25°C to 35°C, with an adjustment range of 10°C; the temperature parameter of equipment E002 is adjusted from 30°C to 40°C, with an adjustment range of 10°C, etc.

[0051] Step S40: Obtain the historical parameter change results of the historical similar change events, and perform a risk assessment on the parameter change events based on the historical parameter change results to obtain the parameter change risk assessment results.

[0052] It should be noted that the aforementioned historical parameter change results can be the results observed after the implementation of similar historical change events, which may include equipment operating status, changes in quality indicators, and failure occurrences, etc., and this embodiment does not impose any limitations on this. Specifically, equipment operating status can refer to the equipment's operating status after the change (e.g., normal operation, alarm, failure, etc.); changes in quality indicators can refer to the impact of historical changes on product quality (e.g., changes in pass rate, changes in defect rate, etc.); failure occurrences can include whether the change caused a failure, as well as the specific type of failure and its solution.

[0053] It should be understood that the above-mentioned parameter change risk assessment results can be conclusions drawn after assessing the risks that the current parameter change event may bring, which may include information such as risk level, potential impact, and recommended measures.

[0054] In practical applications, the system can extract change query conditions from parameter change events of target production equipment, including equipment model, changed parameters, and change magnitude. Based on these query conditions, it queries a pre-defined risk knowledge graph for matching target change entities, such as entities with the same equipment, similar parameters, or similar adjustment magnitudes, as well as the target associations related to these target change entities, to obtain historical similar change events of the parameter change event. Then, the system can extract information such as parameter values ​​after each change, equipment operating status, quality impact, and fault records from the retrieved historical similar change events to obtain historical parameter change results of historical similar change events. It then analyzes these historical parameter change results to assess the potential risks of parameter change events of the target production equipment, determine the risk level, possible scope of impact, and preventive measures of the parameter change event, and finally generate a detailed parameter change risk assessment report.

[0055] Furthermore, after the step of performing a risk assessment on the parameter change event based on the historical parameter change results to obtain the parameter change risk assessment result, the method further includes: Step S51: Determine whether to change the parameters of the target production equipment based on the parameter change risk assessment results.

[0056] It should be noted that this embodiment can assess the risk level and potential impact of the current parameter change event based on the historical parameter change results. If the risk level is an acceptable level (such as low or medium), the parameter change can be performed; otherwise, it is recommended to reassess the change requirement or take preventive measures.

[0057] Step S52: If yes, then obtain the real-time operating data and product quality data of the target production equipment after the change.

[0058] It should be understood that the target production equipment described above may be production equipment in a new operating state after the execution parameters have been changed, and the parameters of the equipment have been adjusted according to the requirements of the change event.

[0059] It is understandable that the aforementioned real-time operating data can be data generated by the target production equipment during actual operation after parameter changes, which may include, but is not limited to, parameter values, equipment status, and operating time.

[0060] It is also understood that the above-mentioned product quality data can be quality-related data of products produced by the target production equipment after parameter changes, such as defect rate, pass rate, performance indicators, etc., and this embodiment does not limit this.

[0061] Step S53: Construct a structured change case based on the real-time running data, the product quality data, and the change event context of the parameter change event, wherein the change event context is used to describe the parameter change event.

[0062] It should be noted that the aforementioned change event context can be detailed information used to describe parameter change events, which may include the subject of the change (Who), time (When), location (Where), content (What), reason (Why), and method (How). This information is used to comprehensively record and describe change events.

[0063] It should also be noted that the above-mentioned structured change case can be a structured case record generated by integrating change events and their related data (such as real-time operational data, product quality data, and change event context). This change case can be used to record and analyze change events.

[0064] In this embodiment, by constructing structured change cases and updating the risk knowledge graph, knowledge can be accumulated and dynamically updated, thereby providing richer experience and data support for subsequent change management. Furthermore, by continuously optimizing the knowledge graph and risk assessment model based on new change cases, this embodiment can improve the system's adaptability and accuracy, while also increasing the efficiency of parameter change risk assessment.

[0065] Step S54: Update the preset risk knowledge graph based on the structured change case.

[0066] In practical applications, after deciding to change parameters, the target production equipment can execute the change operation according to the predetermined change plan. After the target production equipment completes the parameter change, the system can collect real-time equipment operation data through sensors and monitoring systems on the equipment, and obtain quality data of the changed product through quality inspection equipment or manual inspection. Then, the system can integrate the change event context, real-time operation data, and product quality data into a structured change case. (Refer to...) Figure 3 , Figure 3 This is an architecture diagram of the intelligent control system for parameter changes in the risk assessment method of this application. Figure 3 As shown, the structured change cases in this embodiment may include 5W1H audit logs (i.e., information including Who, When, Where, What, Why, and How), risk assessment reports, equipment operation data of the modified production equipment, product quality data, etc. After generating the structured cases, the system can extract knowledge from them, extracting entities and their related relationships, and integrate this information into a preset risk knowledge graph to update the graph, thereby optimizing its reasoning ability and providing intelligent recommendations for future changes. Subsequently, when production equipment needs parameter changes, the system can query entities and perform similarity matching in this dense knowledge graph to recommend the historically most successful solutions based on the query results.

[0067] In this embodiment, refer to Figure 4 , Figure 4 This is the overall architecture diagram of the intelligent control system for parameter changes in the risk assessment method of this application. Figure 4As shown, the intelligent control system for parameter changes in this application can include a production site layer, an intelligent control core layer, and a user interaction and process layer. These three layers can work together to achieve intelligent control of parameter changes, thereby improving the efficiency and safety of parameter changes in industrial production. The production site layer can include a PLC controller, an HMI (Human-Machine Interface), and an engineer workstation. The PLC controller can collect real-time equipment data and execute parameter change commands; the HMI provides on-site operators with an interface to view parameter status, change results, and other information; and the engineer workstation provides parameter configuration, debugging, and historical data query functions. The intelligent control core layer can include a self-evolving parameter knowledge base, a risk knowledge graph engine, and a full-process audit engine. The self-evolving parameter knowledge base stores equipment parameters, constraints, historical change cases, etc., and can automatically update knowledge through machine learning; the risk knowledge graph engine can be used to construct parameter relationships based on a graph database to infer change risks; and the full-process audit engine can receive probe data and generate "5W1H" logs to ensure that changes are traceable. When parameter changes are required, users can submit parameter change requests through user interaction and workflow layers. At this time, the system can call the risk knowledge graph engine to perform knowledge reasoning, determine the risk level and scope of impact of the current parameter change event, and return a risk assessment report. Then, the system can determine whether the production equipment needs parameter changes based on the returned risk assessment report. If so, it can issue a change instruction to the production equipment.

[0068] In the specific implementation, refer to Figure 5 , Figure 5 This is a closed-loop sequence diagram of parameter change events for production equipment in the risk assessment method of this application. (Example:) Figure 5 As shown in the diagram, this system illustrates the closed-loop management logic of a knowledge graph-based intelligent control system for parameter changes, from requirement submission to effect verification. When production equipment requires parameter changes, engineers can submit change requests through a unified management portal. The portal then synchronizes these requests to the risk knowledge graph engine, which generates and provides a risk assessment report based on historical data and a rule base. After the assessment is approved, the unified management portal issues a safety parameter modification command to the equipment control system. Upon receiving the command, the control system executes the change and returns a confirmation of successful execution. Subsequently, engineers can submit the change effect verification results through the unified management portal. The system then synchronizes complete structured change cases to the self-evolving parameter knowledge base, updating the knowledge graph based on these cases to optimize the accuracy of risk assessments for subsequent changes.

[0069] This embodiment can determine the change query conditions involved in the parameter change event when the target production equipment needs to undergo parameter changes. Based on these query conditions, it queries a preset risk knowledge graph for target change entities matching the query conditions and their related target relationships. Then, it generates historical similar change events based on the target change entities and their relationships, and performs a parameter change risk assessment based on the historical parameter change results of these similar change events. Because this embodiment can efficiently query historical similar change events for the target production equipment's parameter change events using a preset risk knowledge graph, and assess the risk of the current parameter change event based on the results of these historical similar change events, it can efficiently assess the parameter change risk of the production equipment.

[0070] Reference Figure 6 , Figure 6 This is a flowchart illustrating the second embodiment of the risk assessment method of this application. Based on the first embodiment described above, a second embodiment of the risk assessment method of this application is proposed.

[0071] In this embodiment, as Figure 6 As shown, the change query conditions include equipment model, change parameters, and change magnitude; the step of querying a preset risk knowledge graph based on the change query conditions to obtain the target change entity matching the change query conditions and the target association relationships related to the target change entity includes: Step S21: Query the preset risk knowledge graph according to the device model to obtain the target device node that matches the device model, and obtain the first target association relationship related to the target device node.

[0072] It is understandable that the aforementioned equipment model can be a specific model identifier for the production equipment, which can be used to uniquely distinguish different types of equipment. The aforementioned changed parameters can be specific parameters that need to be adjusted for the target production equipment, such as temperature, pressure, and speed. The aforementioned change range can be the specific numerical range of the changed parameter adjustment; for example, if the temperature is adjusted from 30°C to 40°C, the corresponding change range is 10°C.

[0073] It should be understood that the aforementioned target device node can be a device node in a preset risk knowledge graph that matches the device model in the query conditions. This node can contain basic information about the device, such as device number, device model, device location, etc. This embodiment does not impose any restrictions on this.

[0074] It should also be understood that the aforementioned first target association can be an association directly related to the target device node in a pre-defined risk knowledge graph. These associations can be used to describe the direct connection between the target device node and other entities (such as parameter nodes, change record nodes, etc.).

[0075] In this embodiment, the system can extract the equipment model of the target production equipment from the change query conditions, and then search for a matching target equipment node in a preset risk knowledge graph based on the equipment model. Simultaneously, it obtains all relevant information about the target equipment node, including parameter settings, historical change records, and failure cases. Then, the system can analyze the relationships between the target equipment node and other entities in the preset risk knowledge graph, and extract relationships directly related to the target equipment node, such as the relationship between change parameters and equipment model, to obtain the first target relationship.

[0076] Step S22: Query the preset risk knowledge graph according to the changed parameters, obtain the target parameter node that matches the changed parameters, and obtain the second target association relationship related to the target parameter node.

[0077] It is understandable that the aforementioned target parameter nodes can be parameter nodes in the preset risk knowledge graph that match the changed parameters in the query conditions. These parameter nodes can contain specific information about the parameters, such as parameter type, parameter name, parameter value, etc.

[0078] It is also understood that the aforementioned second target association can be an association directly related to the target parameter node in a preset risk knowledge graph. These associations can be used to describe the direct connection between the target parameter node and other entities (such as change record nodes, quality indicator nodes, failure mode nodes, etc.).

[0079] In this embodiment, the system can extract the specific parameters (such as temperature, pressure, etc.) that need to be changed from the change query conditions, and search for matching target parameter nodes in a preset risk knowledge graph based on the changed parameters. Simultaneously, it obtains all relevant information about the target parameter node, such as the parameter definition, historical change records, associated equipment, and risk level. Then, the system can analyze the relationships between the target parameter node and other entities, and extract the relationships directly related to the target parameter node, such as "temperature change → risk level increase," to obtain a second target relationship.

[0080] Further, the step of querying the preset risk knowledge graph based on the changed parameters to obtain target parameter nodes matching the changed parameters includes: determining the parameter category to which the historical changed parameters represented by all parameter nodes in the preset risk knowledge graph belong; determining the target changed parameter from the historical changed parameters based on the parameter category; obtaining the first parameter property and the first parameter influence range of the target changed parameter; determining the second parameter property and the second parameter influence range of the changed parameter; determining the parameter similarity between the target changed parameter and the changed parameter based on the first parameter property, the second parameter property, the first parameter influence range, and the second parameter influence range; and obtaining the target parameter node matching the changed parameter from the target changed parameter based on the parameter similarity.

[0081] It should be understood that the above parameter categories can be the result of classifying parameters according to their functions, properties, or uses. In this embodiment, the system can classify historically changed parameters according to their physical properties (such as temperature, pressure, and speed), functions (such as control parameters and monitoring parameters), or roles in the production process (such as process parameters and safety parameters), and determine the parameter category to which the historically changed parameters belong. These historically changed parameters can be parameters that have undergone changes, represented by parameter nodes in a preset risk knowledge graph.

[0082] It should be noted that the aforementioned target change parameters can be parameters belonging to the same category as the parameters that need to be changed for the target production equipment in the preset risk knowledge graph. Correspondingly, the aforementioned first parameter properties can be property descriptions of the target change parameters recorded in the knowledge graph; these properties describe the basic characteristics of the parameters, such as units, normal range, and change frequency. The aforementioned first parameter impact range can be the potential impact range on equipment operation and product quality after the target change parameter is changed.

[0083] It should be noted that the nature of the second parameter mentioned above can be the nature of the parameter that needs to be changed in the target production equipment; the scope of influence of the second parameter mentioned above can be the potential impact of the parameter that needs to be changed in the target production equipment on the operation of the equipment and the quality of the product after the change.

[0084] It should be understood that the above parameter similarity can be an indicator used to characterize the degree of similarity between the target parameter to be changed and the parameter that needs to be changed now. It can be calculated by comparing the parameter properties and scope of influence of the target parameter to be changed and the parameter that needs to be changed now.

[0085] In practical applications, the system can extract all historical change parameters from a pre-defined risk knowledge graph and determine the parameter categories of these historical change parameters. Then, the system can extract the parameter that needs to be changed currently from the change query conditions. Based on the parameter category of this parameter, it determines the target change parameter from the historical change parameters that shares the same category as the parameter to be changed (i.e., the change parameter). Simultaneously, it obtains the parameter properties and influence ranges of both the target change parameter and the parameter to be changed, and calculates the parameter similarity between them based on these properties and influence ranges. Finally, the system determines the top N parameters with the highest similarity to the change parameter among the target change parameters based on this parameter similarity. The nodes containing these parameters are the target parameter nodes that match the change parameter.

[0086] Step S23: Query the preset risk knowledge graph according to the change range to obtain the target change record node that matches the change range, and obtain the third target association relationship related to the target change record node. The target change record node stores the change range of the corresponding change event.

[0087] It should be understood that the aforementioned target change record nodes can be change record nodes in the preset risk knowledge graph that match the change magnitude in the query conditions. These nodes can record detailed information about parameter change events that have occurred in the past, such as parameter values ​​before and after the change, adjustment magnitude, change time, operator, etc.

[0088] It should also be understood that the aforementioned third target association can be an association related to the target change record node in a pre-defined risk knowledge graph. These associations can be used to describe the logical connection between the target change record node and other entities (such as equipment model, risk level, failure case, etc.).

[0089] In this embodiment, the system can extract the specific change range from the change query conditions, and search for a matching target change record node in a preset risk knowledge graph based on the change range. Simultaneously, it obtains all relevant information about the target change record node, such as detailed records of the change event, the change result, and associated risks. Then, the system can analyze the relationships between the target change record node and other entities, and extract relationships directly related to the target change record node, such as "change range → increased risk level," thus obtaining a third target relationship.

[0090] Step S24: Determine the entities represented by the target device node, the target parameter node, and the target change record node as target change entities that match the change query conditions, and determine the target association relationships related to the target change entities based on the first target association relationship, the second target association relationship, and the third target association relationship.

[0091] In practical applications, the system can extract the device model, changed parameters, and change magnitude from parameter change events. Within a pre-defined risk knowledge graph, it queries the target device node and its associated first-target relationships based on the device model, the target parameter node and its associated second-target relationships based on the changed parameters, and the target change record node and its associated third-target relationships based on the change magnitude. The entities represented by these three nodes are then identified as the target change entity. The first, second, and third-target relationships are integrated to form a complete set of target relationships for the target change entity. In this embodiment, by integrating these three relationships, the system can comprehensively extract all relationships related to the target change entity, thus providing richer information for risk assessment. Simultaneously, based on the target change entity and its corresponding relationships, the system can more scientifically assess the potential risks of parameter changes, thereby obtaining more accurate risk assessment results.

[0092] Reference Figure 7 , Figure 7 This is a flowchart illustrating the third embodiment of the risk assessment method of this application. Based on the above embodiments, the third embodiment of the risk assessment method of this application is proposed.

[0093] In this embodiment, as Figure 7 As shown, the step of conducting a risk assessment of the parameter change event based on the historical parameter change results to obtain the parameter change risk assessment result includes: Step S41: Match the parameter change event with all the change rules in the preset change rule library, and determine the target matching change rule based on the matching result.

[0094] It should be noted that the aforementioned preset change rule library can be a database used to store a collection of all change rules. The change rules can be specific rules used to guide parameter change operations. These rules can define information such as the allowable range, potential risks, and recommended measures for parameter changes under specific conditions. This embodiment does not impose any restrictions on this.

[0095] It should be understood that the aforementioned target matching change rule can be a specific rule in a preset change rule library that matches the current parameter change event. In this embodiment, the system can determine the target matching change rule by matching the characteristics of the change event (such as parameter type and adjustment range) with the conditions in the rule library.

[0096] In this embodiment, the system can extract key features from parameter change events, such as device model, changed parameters, and change magnitude, and check each rule in the preset change rule base one by one. The change event features are matched with the conditions of these rules to find matching rules, and the matching rules are determined as the target matching change rules.

[0097] It should be noted that the preset change rule library stores change rules defined in enterprise or industry standards. These rules can ensure that parameter changes comply with established technical specifications and safety standards. In this embodiment, by matching these rules, it can verify whether the current parameter change event meets the requirements and ensure that the change operation will not lead to equipment failure or safety accidents.

[0098] Step S42: Determine the target impact range of the parameter change event based on the preset risk knowledge graph and the target change entity.

[0099] It should be noted that the aforementioned target impact range can be the range that the parameter change event may affect, which may include equipment components, quality indicators, or other parameters that the parameter change event may affect. This embodiment does not impose any limitations on this. In this embodiment, the system can query relevant information in a preset risk knowledge graph based on the target change entity, extract all impact range information related to the target change entity from the risk knowledge graph, and finally integrate the extracted impact range information to determine the target impact range.

[0100] Further, step S42 includes: performing a path search in the preset risk knowledge graph based on the target change entity to determine the candidate impact path where the target change entity is located; determining the environmental impact dimension of the target change entity based on the equipment operating environment of the target production equipment; filtering the candidate impact paths according to the environmental impact dimension to obtain the target impact path; expanding the target impact path based on the target impact nodes on the target impact path to obtain an impact path network; and determining the target impact range of the parameter change event according to the impact path network.

[0101] It should be noted that the aforementioned candidate impact paths can be all possible impact paths found through path search within a pre-defined risk knowledge graph, starting from the target change entity. These paths describe the specific nodes that the change event may pass through. For example, if the target change entity is "temperature parameter change," the candidate impact paths obtained from path search in the pre-defined risk knowledge graph might include: temperature change → equipment overheating → product quality decline; temperature change → increased energy consumption → increased production costs, etc.

[0102] It should be understood that the above-mentioned equipment operating environment can be the environmental conditions of the target production equipment in actual operation, including physical environment (such as temperature, humidity, and pressure), operating environment (such as operator skill level and maintenance frequency), and other related factors. These environmental conditions may affect the actual effect of parameter changes.

[0103] It is understandable that the above-mentioned environmental impact dimensions can be specific aspects of the equipment operating environment that may affect parameter changes. These dimensions can be used to assess the degree of impact of environmental conditions on change events.

[0104] It is also understood that the aforementioned target impact path can be the path most relevant to the current operating environment of the device among the candidate impact paths. Correspondingly, the aforementioned target impact nodes can be key nodes on the target impact path, and these nodes can be used to characterize the equipment components, parameters, or quality indicators that parameter changes may directly affect.

[0105] It should be noted that the aforementioned impact path network can be a complete impact path network formed by expanding the target impact path. This network can be used to describe the comprehensive impact of parameter change events of the target production equipment on the equipment operating environment, and can cover all relevant impact paths and nodes of all parameter change events.

[0106] In practical applications, the system can start with the target entity undergoing change and use graph search algorithms (such as breadth-first search or depth-first search) to search for all possible impact paths in the knowledge graph, selecting the found paths as candidate impact paths. Then, the system can obtain the actual operating environment information of the target production equipment and, based on this environment, determine dimensions that may affect the change's effectiveness, such as temperature sensitivity and humidity impact. After determining all environmental impact dimensions, the system can evaluate the relevance of each candidate path to the equipment's operating environment, filtering out irrelevant paths and retaining those highly relevant to the operating environment to generate the target impact path. Finally, the system can extract key target impact nodes from the target impact path and expand the target impact path based on these nodes to form a more comprehensive impact path network. Then, it can extract all possible impact ranges from the impact path network and integrate these impact ranges into the target impact range.

[0107] Step S43: Based on the historical parameter change results, the target matching change rules, and / or the target impact range, perform a risk assessment on the parameter change event to obtain the parameter change risk assessment result.

[0108] In the specific implementation, refer to Figure 8 , Figure 8 This is a flowchart illustrating the overall process of parameter change risk assessment in the risk assessment methodology of this application. Figure 8 As shown, upon receiving a parameter change request, the system can invoke a predefined rule base to verify whether the changed parameters meet the system's preset constraints. Simultaneously, the system can retrieve historical similar cases from the risk knowledge graph, calculating the success / failure ratio of these cases. Furthermore, the system can perform correlational impact reasoning within the risk knowledge graph to analyze the potential correlational effects of the parameter change. Finally, the system can integrate the rule verification results, historical case data, and correlational reasoning conclusions to generate a change risk rating report.

[0109] In this embodiment, historical parameter change results can provide actual change cases and results, target matching change rules can provide a basis for compliance and technical specifications, and target impact scope can clarify the various aspects that the change may affect. By comprehensively considering historical parameter change results, target matching change rules, and target impact scope, the system can more accurately predict the risks that parameter change events of production equipment may bring, thereby improving the efficiency of parameter change risk assessment.

[0110] In addition, refer to Figure 9 , Figure 9 This is a structural block diagram of the first embodiment of the risk assessment device of this application; as shown below. Figure 9 As shown in the embodiments of this application, a risk assessment device is also proposed, which includes: The change response module 901 is used to respond to a parameter change request and determine a parameter change event that requires parameter changes for the target production equipment based on the parameter change request. The change query module 902 is used to determine the change query conditions involved in the parameter change event, and query a preset risk knowledge graph according to the change query conditions to obtain the target change entity that matches the change query conditions and the target association relationship related to the target change entity. The change query module 902 is also used to generate historical similar change events based on the target change entity and the target association relationship; The risk assessment module 903 is used to obtain the historical parameter change results of the historical similar change events, and to perform a risk assessment on the parameter change event based on the historical parameter change results to obtain the parameter change risk assessment result.

[0111] In one implementation, the change response module 901 is further configured to extract all change entities of the production equipment to be evaluated from a preset equipment knowledge resource base; analyze the text of the statements containing each change entity to determine the related relationships of each change entity; and construct a preset risk knowledge graph based on each change entity and the related relationships.

[0112] In one implementation, the risk assessment module 903 is further configured to determine whether to change the parameters of the target production equipment based on the parameter change risk assessment result; if so, to obtain the real-time operating data and product quality data of the target production equipment after the change; to construct a structured change case based on the real-time operating data, the product quality data, and the change event context of the parameter change event, wherein the change event context is used to describe the parameter change event; and to update the preset risk knowledge graph based on the structured change case.

[0113] Based on the first embodiment of the risk assessment device described in this application, a second embodiment of the risk assessment device of this application is proposed.

[0114] In this embodiment, the change query conditions include equipment model, change parameters, and change magnitude; the change query module 902 is further configured to query a preset risk knowledge graph based on the equipment model to obtain a target equipment node matching the equipment model, and obtain a first target association relationship related to the target equipment node; query the preset risk knowledge graph based on the change parameters to obtain a target parameter node matching the change parameters, and obtain a second target association relationship related to the target parameter node; query the preset risk knowledge graph based on the change magnitude to obtain a target change record node matching the change magnitude, and obtain a third target association relationship related to the target change record node, wherein the target change record node stores the change magnitude of the corresponding change event; determine the entity represented by the target equipment node, the target parameter node, and the target change record node as the target change entity matching the change query conditions, and determine the target association relationship related to the target change entity based on the first target association relationship, the second target association relationship, and the third target association relationship.

[0115] In one implementation, the change query module 902 is further configured to: determine the parameter category to which the historical change parameters represented by all parameter nodes in the preset risk knowledge graph belong; determine a target change parameter from the historical change parameters according to the parameter category; obtain a first parameter property and a first parameter influence range of the target change parameter; determine a second parameter property and a second parameter influence range of the change parameter; determine the parameter similarity between the target change parameter and the change parameter based on the first parameter property, the second parameter property, the first parameter influence range, and the second parameter influence range; and obtain a target parameter node matching the change parameter from the target change parameters according to the parameter similarity.

[0116] Based on the above embodiments of the risk assessment device of this application, a third embodiment of the risk assessment device of this application is proposed.

[0117] In this embodiment, the risk assessment module 903 is further configured to match the parameter change event with all change rules in the preset change rule library, and determine the target matching change rule based on the matching result; determine the target impact range of the parameter change event based on the preset risk knowledge graph and the target change entity; and perform a risk assessment on the parameter change event based on the historical parameter change results, the target matching change rule and / or the target impact range to obtain a parameter change risk assessment result.

[0118] In one implementation, the risk assessment module 903 is further configured to: perform path search in the preset risk knowledge graph based on the target change entity to determine the candidate impact path in which the target change entity is located; determine the environmental impact dimension of the target change entity based on the equipment operating environment of the target production equipment; filter the candidate impact paths according to the environmental impact dimension to obtain the target impact path; expand the target impact path based on the target impact nodes on the target impact path to obtain the impact path network; and determine the target impact range of the parameter change event according to the impact path network.

[0119] Other embodiments or specific implementations of the risk assessment device described in this application can be found in the above-described method embodiments, and will not be repeated here.

[0120] Furthermore, embodiments of this application also propose a risk assessment device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the risk assessment method described above.

[0121] Furthermore, embodiments of this application also propose a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the risk assessment method described above.

[0122] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0123] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0124] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0125] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A risk assessment method, characterized in that, The method includes: In response to a parameter change request, determine the parameter change event that requires parameter changes for the target production equipment based on the parameter change request; Determine the change query conditions involved in the parameter change event, and query a preset risk knowledge graph based on the change query conditions to obtain the target change entity that matches the change query conditions and the target association relationship related to the target change entity; Generate historical similar change events based on the target changed entity and the target related relationships; Obtain the historical parameter change results of the historical similar change events, and conduct a risk assessment of the parameter change events based on the historical parameter change results to obtain the parameter change risk assessment results.

2. The method as described in claim 1, characterized in that, The change query conditions include equipment model, change parameters, and change magnitude; the step of querying a preset risk knowledge graph based on the change query conditions to obtain the target change entity matching the change query conditions and the target association relationships related to the target change entity includes: Based on the device model, a preset risk knowledge graph is queried to obtain a target device node that matches the device model, and a first target association relationship related to the target device node is obtained; The preset risk knowledge graph is queried according to the changed parameters to obtain the target parameter node that matches the changed parameters, and the second target association relationship related to the target parameter node is obtained. Based on the change magnitude, the preset risk knowledge graph is queried to obtain a target change record node that matches the change magnitude, and a third target association relationship related to the target change record node is obtained. The target change record node stores the change magnitude of the corresponding change event. The entities represented by the target device node, the target parameter node, and the target change record node are determined as target change entities that match the change query conditions, and the target association relationships related to the target change entities are determined based on the first target association relationship, the second target association relationship, and the third target association relationship.

3. The method as described in claim 2, characterized in that, The step of querying the preset risk knowledge graph based on the changed parameters to obtain the target parameter node matching the changed parameters includes: Determine the parameter category to which the historical change parameters represented by all parameter nodes in the preset risk knowledge graph belong; The target change parameter is determined from the historical change parameters based on the parameter category; Obtain the first parameter property and the first parameter influence range of the target change parameter; Determine the nature of the second parameter and the scope of influence of the changed parameter; The parameter similarity between the target change parameter and the change parameter is determined based on the properties of the first parameter, the properties of the second parameter, the influence range of the first parameter, and the influence range of the second parameter. Based on the parameter similarity, obtain the target parameter node that matches the changed parameter from the target changed parameters.

4. The method as described in claim 2, characterized in that, The step of conducting a risk assessment of the parameter change event based on the historical parameter change results to obtain the parameter change risk assessment result includes: The parameter change event is matched with all change rules in the preset change rule library, and the target matching change rule is determined based on the matching result; The target impact range of the parameter change event is determined based on the preset risk knowledge graph and the target change entity; Based on the historical parameter change results, the target matching change rules, and / or the target impact range, a risk assessment is performed on the parameter change event to obtain the parameter change risk assessment result.

5. The method as described in claim 4, characterized in that, The step of determining the target impact range of the parameter change event based on the preset risk knowledge graph and the target change entity includes: Based on the target change entity, a path search is performed in the preset risk knowledge graph to determine the candidate impact path in which the target change entity is located; The environmental impact dimension of the target change entity is determined based on the equipment operating environment of the target production equipment. The candidate impact paths are filtered according to the environmental impact dimensions to obtain the target impact path; Based on the target influence nodes on the target influence path, the target influence path is expanded to obtain an influence path network; The target impact range of the parameter change event is determined based on the impact path network.

6. The method according to any one of claims 1 to 5, characterized in that, Before the step of responding to a parameter change request and determining, based on the parameter change request, a parameter change event requiring parameter change for the target production equipment, the method further includes: Extract all changed entities of the production equipment to be evaluated from the pre-defined equipment knowledge resource base; Analyze the text of the statements containing each of the aforementioned changed entities to determine the relationships between them; A pre-defined risk knowledge graph is constructed based on each of the changed entities and the associated relationships.

7. The method as described in claim 6, characterized in that, After the step of performing a risk assessment on the parameter change event based on the historical parameter change results to obtain the parameter change risk assessment result, the method further includes: Based on the results of the parameter change risk assessment, determine whether to change the parameters of the target production equipment; If so, obtain the real-time operating data and product quality data of the target production equipment after the change; A structured change case is constructed based on the real-time operating data, the product quality data, and the change event context of the parameter change event, wherein the change event context is used to describe the parameter change event; The preset risk knowledge graph is updated based on the structured change cases.

8. A risk assessment device, characterized in that, The device includes: The change response module is used to respond to parameter change requests and determine the parameter change event that requires parameter changes for the target production equipment based on the parameter change request. The change query module is used to determine the change query conditions involved in the parameter change event, and query a preset risk knowledge graph according to the change query conditions to obtain the target change entity that matches the change query conditions and the target association relationship related to the target change entity. The change query module is also used to generate historical similar change events based on the target change entity and the target association. The risk assessment module is used to obtain the historical parameter change results of the same historical change events, and to perform a risk assessment on the parameter change events based on the historical parameter change results to obtain the parameter change risk assessment results.

9. A risk assessment device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the risk assessment method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the risk assessment method as described in any one of claims 1 to 7.

Images