Equipment information processing method and device based on ontology modeling and computer equipment

Abstract

The invention relates to an equipment information processing method and device based on ontology modeling and computer equipment. The method comprises the following steps: acquiring equipment operation data, environment monitoring data, equipment historical data and an equipment data ontology model of a target equipment set; standardizing data structures of the equipment operation data, the environment monitoring data and the equipment historical data according to data standardization setting in the equipment data ontology model to obtain equipment operation standardized data; performing equipment fault analysis on the equipment operation standardized data according to a semantic reasoning rule in the equipment data ontology model to obtain equipment fault analysis data; performing data-driven risk causal analysis on the equipment fault analysis data to obtain a data-driven risk analysis result; the data-driven risk analysis result is used for generating risk exclusion data for any device in the target device set. By adopting the method, abnormal conditions caused by dynamically changing complex environments and equipment characteristics can be effectively handled.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a device information processing method, apparatus and computer equipment based on ontology modeling. Background Art

[0002] In traditional technologies, device information processing usually relies on collecting, storing, analyzing and processing device data in a rule-based or hard-coded manner. Specifically, real-time data of the device is obtained through sensors or device interfaces, and these data are transmitted to the central processing system through communication protocols. The system then classifies, filters and analyzes the device information according to the preset algorithm. The processed information can be used for device status monitoring, performance evaluation, etc. In addition, traditional technologies also rely on manually set thresholds and conditions to trigger alarms or automatically perform operations. Therefore, traditional technologies lack flexibility and intelligence in device information processing, and it is difficult to effectively respond to abnormal situations caused by dynamically changing complex environments and device characteristics. Summary of the invention

[0003] Based on this, it is necessary to provide a device information processing method, apparatus, computer equipment, computer-readable storage medium and computer program product based on ontology modeling that can effectively deal with abnormal situations caused by dynamically changing complex environments and device characteristics in order to address the above technical problems.

[0004] In a first aspect, the present application provides a device information processing method based on ontology modeling, comprising: Obtain device operation data, environmental monitoring data, device history data, and device data ontology model of the target device set; According to the data standardization setting in the equipment data ontology model, the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data is standardized to obtain equipment operation standardized data; According to the semantic reasoning rules in the equipment data ontology model, performing equipment failure analysis on the equipment operation standardized data to obtain equipment failure analysis data; A data-driven risk causal analysis is performed on the equipment failure analysis data to obtain a data-driven risk analysis result; the data-driven risk analysis result is used to generate risk elimination data for any device in the target equipment set.

[0005] In a second aspect, the present application also provides a device information processing apparatus based on ontology modeling, comprising: A data acquisition module, used to acquire device operation data, environmental monitoring data, device history data and device data ontology model of a target device set; A data conversion module, used to standardize the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data according to the data standardization setting in the equipment data ontology model, so as to obtain equipment operation standardized data; A fault analysis module, used to perform equipment fault analysis on the equipment operation standardized data according to the semantic reasoning rules in the equipment data ontology model to obtain equipment fault analysis data; The risk analysis module is used to perform data-driven risk causal analysis on the equipment failure analysis data to obtain data-driven risk analysis results; the data-driven risk analysis results are used to generate risk elimination data for any device in the target device set.

[0006] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: Obtain device operation data, environmental monitoring data, device history data, and device data ontology model of the target device set; According to the data standardization setting in the equipment data ontology model, the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data is standardized to obtain equipment operation standardized data; According to the semantic reasoning rules in the equipment data ontology model, performing equipment failure analysis on the equipment operation standardized data to obtain equipment failure analysis data; A data-driven risk causal analysis is performed on the equipment failure analysis data to obtain a data-driven risk analysis result; the data-driven risk analysis result is used to generate risk elimination data for any device in the target equipment set.

[0007] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented: Obtain device operation data, environmental monitoring data, device history data, and device data ontology model of the target device set; According to the data standardization setting in the equipment data ontology model, the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data is standardized to obtain equipment operation standardized data; According to the semantic reasoning rules in the equipment data ontology model, performing equipment failure analysis on the equipment operation standardized data to obtain equipment failure analysis data; A data-driven risk causal analysis is performed on the equipment failure analysis data to obtain a data-driven risk analysis result; the data-driven risk analysis result is used to generate risk elimination data for any device in the target equipment set.

[0008] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor: Obtain device operation data, environmental monitoring data, device history data, and device data ontology model of the target device set; According to the data standardization setting in the equipment data ontology model, the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data is standardized to obtain equipment operation standardized data; According to the semantic reasoning rules in the equipment data ontology model, performing equipment failure analysis on the equipment operation standardized data to obtain equipment failure analysis data; A data-driven risk causal analysis is performed on the equipment failure analysis data to obtain a data-driven risk analysis result; the data-driven risk analysis result is used to generate risk elimination data for any device in the target equipment set.

[0009] The above-mentioned device information processing method, apparatus, computer equipment, storage medium and computer program product based on ontology modeling obtains the device operation data, environmental monitoring data, device history data and device data ontology model of the target device set; standardizes the data structure of the device operation data, environmental monitoring data and device history data according to the data standardization settings in the device data ontology model to obtain device operation standardized data; performs device failure analysis on the device operation standardized data according to the semantic reasoning rules in the device data ontology model to obtain device failure analysis data; performs data-driven risk causal analysis on the device failure analysis data to obtain data-driven risk analysis results; and the data-driven risk analysis results are used to generate risk elimination data for any device in the target device set.

[0010] By introducing the equipment data ontology model, the equipment operation data, environmental monitoring data and historical data are standardized, which effectively solves the heterogeneity problem of different data sources and ensures the uniformity of data at the structural and semantic levels, thereby enhancing the accuracy and reliability of data fusion. Equipment fault analysis based on semantic reasoning rules can deeply explore the implicit associations between data, quickly locate potential fault points and identify abnormal trends, and avoid diagnostic omissions caused by single rules or insufficient associations in traditional fault analysis. Subsequently, through data-driven risk causal analysis, the fault phenomenon and potential risks are linked to form a causal chain, further clarifying the key risk sources and risk propagation paths, greatly improving the accuracy and guiding value of the analysis results. The targeted risk elimination data finally generated can effectively respond to abnormal situations caused by dynamically changing complex environments and equipment characteristics, and further provide refined operation and maintenance solutions for each device in the target equipment set when no abnormal situation occurs, which not only improves the equipment's fault prevention and self-adaptation capabilities, but also significantly reduces the impact of systemic risks on the overall equipment operation efficiency and business continuity, providing strong support for the management and optimization of the entire life cycle of equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 An application environment diagram of a device information processing method based on ontology modeling in one embodiment; Figure 2 A schematic diagram of a flow chart of a device information processing method based on ontology modeling in one embodiment; Figure 3 A schematic flow chart of a method for obtaining standardized data of equipment operation in one embodiment; Figure 4 It is a flowchart of a method for obtaining device operation attribute data in one embodiment; Figure 5 A schematic diagram of a process for obtaining device fault analysis data in one embodiment; Figure 6 A schematic diagram of a flow chart of a method for obtaining equipment fault inference data in an embodiment; Figure 7 A schematic diagram of a process for obtaining a data-driven risk analysis result in one embodiment; Figure 8A schematic diagram of a process for obtaining risk diffusion analysis results in one embodiment; Fig. 9 A structural block diagram of a device information processing apparatus based on ontology modeling in one embodiment; Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] The device information processing method based on ontology modeling provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the equipment operation data, environmental monitoring data, equipment historical data and equipment data ontology model of the target equipment set through the terminal 102; according to the data standardization setting in the equipment data ontology model, the data structure of the equipment operation data, environmental monitoring data and equipment historical data is standardized to obtain equipment operation standardized data; according to the semantic reasoning rules in the equipment data ontology model, the equipment operation standardized data is analyzed for equipment failure to obtain equipment failure analysis data; the equipment failure analysis data is subjected to data-driven risk causal analysis to obtain data-driven risk analysis results; the data-driven risk analysis results are used to generate risk elimination data for any device in the target equipment set. Among them, the server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0015] In an exemplary embodiment, Figure 2 As shown in the figure, a device information processing method based on ontology modeling is provided, and the method is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 208. Among them: Step 202: Acquire device operation data, environmental monitoring data, device history data, and device data ontology model of the target device set.

[0016] The target device set can be a collection of all devices that need to be used for data collection, monitoring, fault analysis, and risk assessment in a specific application scenario. These devices can be machines of the same type, or multiple devices running in different environments. The collection covers the device resources that need to be optimized and managed, aiming to improve the efficiency and safety of device operation through data analysis.

[0017] Among them, equipment operation data can be various performance data generated by the equipment in real time under normal or abnormal conditions, including but not limited to parameters such as temperature, pressure, current, and speed. These data reflect the current working status of the equipment.

[0018] The environmental monitoring data may include various external condition data of the environment in which the equipment is located, including air temperature and humidity, noise, vibration, air pressure and other environmental factors.

[0019] The equipment history data may include the operation records, maintenance records, fault logs and repair history of the equipment since it was put into use.

[0020] Among them, the device data ontology model can be an abstract description of the device and its various related data, aiming to achieve standardization and normalization of device information by defining the structure, attributes, types and their relationships of device data.

[0021] Specifically, through the multi-source data acquisition module, the device operation data, environmental monitoring data and device historical data of the target device set are acquired in real time or in batches. Operation data includes the operating status and key indicators of the equipment (such as temperature, current, pressure, etc.); environmental monitoring data covers the external conditions of the environment where the equipment is located (such as humidity, temperature, vibration, etc.); historical data comes from the long-term operation records, fault logs and maintenance records of the equipment. Data acquisition uses protocol adaptation technology (such as Modbus, OPC, HTTP, etc.) to ensure compatibility with different types of equipment, and introduces the device data ontology model, which contains the structured definition of device data, data types, attribute constraints, and knowledge expression of device functions and relationships. Data transmission uses an efficient encryption protocol to ensure data integrity and security, and is stored in a distributed database after receipt to provide data support for subsequent processing.

[0022] In a specific embodiment, the source of equipment maintenance and support data is historical data of the equipment use process, which generally involves four aspects of information: equipment information, test information, maintenance information, and fault information. The design data table is shown in Table 1.

[0023]

[0024] By analyzing the existing equipment usage quality information, all data are defined into four basic categories: equipment information, test information, maintenance information, and fault cases.

[0025] In a specific embodiment, for the construction of the device data ontology model, ontology editing and knowledge acquisition software is used as an ontology modeling tool. A complete ontology consists of classes, object / data relationships (ObjectProperties / Data Properties), and instances (Individuals). The exported ontology is saved in OWL format. Taking device information as an example to show the ontology modeling process: 1. Create classes: Create a root class "Equipment". Create subclasses under the "Equipment" class: equipment model, equipment name, equipment number, equipment composition, assembly information, production information, equipment distribution date.

[0026] 2. Define data properties: define corresponding data properties for each class. For example: device model: string; device name: string; device number: string; equipment distribution date: date.

[0027] 3. Define Object Properties: Create object properties to represent the relationship between classes. For example: hasComponent: from "equipment" to "equipment composition"; hasAssemblyInfo: from "equipment" to "assembly information"; hasManufacturerInfo: from "equipment" to "production information".

[0028] 4. Create classes for complex structures (such as assembly information and production information): Create classes for complex structures, for example: Assembly information: Manufacturer name: string; Contact information: string. Production information: Manufacturer name: string; Contact information: string.

[0029] 5. Define data attributes for complex structures: Define data attributes for complex structures, for example, the "Manufacturer Name" and "Contact Information" attributes of the "Assembly Information" class. The "Manufacturer Name" and "Contact Information" attributes of the "Production Information" class.

[0030] 6. Create instances (Individuals): Create instances for each class. For example: "Equipment" instance: Equipment A; "Equipment composition" instance: Component 1, Component 2; "Assembly information" instance: Assembly information A; "Production information" instance: Production information A.

[0031] Step 204 , based on the data standardization setting in the equipment data ontology model, the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data is standardized to obtain the equipment operation standardized data.

[0032] Among them, data standardization settings can be rules and processes for unified processing of data collected from different sources and in different formats, including data cleaning, format unification, missing value completion, outlier identification, etc.

[0033] Among them, the equipment operation standardized data can be consistent data obtained after data standardization processing, including unified format data of various performance indicators of the equipment during operation. These data can eliminate data heterogeneity.

[0034] Specifically, in the data preprocessing stage, the collected equipment operation data, environmental monitoring data, and equipment historical data are cleaned, converted, and unified through the standardized settings in the equipment data ontology model. Cleaning includes outlier identification and elimination (such as using box plots, statistical rules, etc.) and missing value completion (such as time series interpolation or mean filling); data conversion maps data fields from different sources to standard fields defined by the ontology model; format unification is achieved through normalization, standardizing numerical data to the range of 0-1, or encoding and converting categorical data (such as One-Hot Encoding). At the same time, the timestamps of the data are aligned through interpolation algorithms to ensure the temporal consistency of multidimensional data. The standardized data is stored in a unified data structure to generate standardized equipment operation data, and can dynamically support calls from other application modules.

[0035] Step 206 , performing equipment failure analysis on the equipment operation standardized data according to the semantic reasoning rules in the equipment data ontology model, to obtain equipment failure analysis data.

[0036] Among them, semantic reasoning rules can be a rule system established based on the device data ontology model, which is used to infer potential failure modes and device behaviors from existing data through reasoning. These rules combine the working principle of the device, historical failure experience and abnormal mode, and can deduce possible failure causes based on the real-time data of the device, thereby realizing intelligent diagnosis of the device status.

[0037] Among them, equipment failure analysis data can be the failure prediction and failure cause analysis results obtained through the analysis of equipment operation data, especially in combination with the equipment's historical failure mode, environmental factors and current operating status. It usually includes quantitative information such as failure probability, failure type, and failure point location, and combines non-quantitative data (such as operator reports and logs) to comprehensively evaluate the health status of the equipment.

[0038] Specifically, in the fault analysis phase, a rule-based reasoning engine is constructed through the semantic reasoning rules in the device data ontology model. The reasoning engine uses logical reasoning technology combined with historical failure modes to perform semantic-level analysis on standardized equipment operation data. Reasoning rules such as "there may be pipe blockage when the equipment temperature is too high and the pressure is abnormal" are automatically judged through the condition-action rule library. At the same time, correlation analysis is used to identify the preceding signals of abnormal patterns, such as whether the current spike when the equipment starts will cause subsequent temperature rise problems. The reasoning result is output as equipment failure analysis data, which contains information such as potential failure causes, failure probabilities, and similarities with historical failures, to support subsequent risk causal analysis.

[0039] In a specific embodiment, the equipment failure analysis data includes the comprehensive results of quantitative data and non-quantitative data. The quantitative data may include specific values ​​such as the temperature of the equipment (such as the temperature rises to 85°C), the current (such as the current fluctuation exceeds the normal range of 10A), and the vibration frequency (such as the vibration amplitude reaches 1.5 times the vibration standard). These data are monitored and recorded in real time by sensors. Non-quantitative data include the history of equipment failures, abnormal conditions reported by operators (such as "abnormal noise when the equipment starts"), fault categories (such as "overload", "short circuit" or "overheating"), and related environmental factors (such as "room temperature is too high" or "high humidity"). These data are collected through manual records or system logs, providing contextual information in the operation of the equipment. Combining these quantitative and non-quantitative data, fault analysis can reveal the root cause of equipment failures and provide strong support for subsequent risk assessment and preventive measures.

[0040] Step 208: Perform data-driven risk causal analysis on the equipment failure analysis data to obtain data-driven risk analysis results.

[0041] Among them, data-driven risk causal analysis can be a method that uses advanced data mining and machine learning methods and mathematical models to establish a causal relationship model between equipment failure and potential risk factors through statistical analysis of equipment failure and abnormal data. By analyzing the mutual influence between different risk factors, the risk source that is most likely to cause failure can be identified.

[0042] Among them, the results of data-driven risk analysis can be a risk assessment report obtained through in-depth analysis of equipment operation, environmental monitoring and fault data. The report is usually in the form of a combination of quantitative results (such as risk probability, risk index) and qualitative descriptions (such as risk factors, cause-and-effect diagrams).

[0043] Specifically, based on the equipment failure analysis data, a data-driven causal analysis model is constructed, and causal graphs (Causal Graphs) or structural equation models (SEM) are used to define the causal relationship network between the fault phenomenon and the risk source. Using machine learning methods such as Bayesian networks and / or risk path analysis mathematical models, probabilistic inferences are made on possible risk paths, and the key influencing factors of the failure are identified in combination with the statistical characteristics of historical failure data. The analysis process includes causal inference, sensitivity analysis, and visualization of risk propagation paths to clarify the contribution of each risk factor and the possible direction of risk diffusion. For example, abnormal vibration may cause performance degradation through the mechanical aging path, which in turn leads to downtime risks. The results of data-driven risk analysis are presented in the form of a variety of different data, and a specific risk chain diagram and key risk source location information are generated for each device.

[0044] In a specific embodiment, the data-driven risk analysis results also include quantitative data and non-quantitative data, where quantitative data can show the probability of equipment failure, such as "the probability of equipment overheating failure is 25%", and a chart is used to show the contribution of each risk factor to the overall risk, such as the weight of the impact of temperature, vibration, load, etc. on equipment failure. Secondly, a causal relationship diagram (such as a Bayesian network or a causal diagram) shows the relationship between risk factors, such as "high temperature (temperature>90°C) may cause a circuit short circuit, further leading to downtime risk", and the risk value of each node is visualized as a color depth, with dark colors indicating high risks. Non-quantitative data is presented in text form, such as "Device A has reported overheating problems many times in the past 6 months, and the ambient temperature is high", combined with the failure mode summary in historical data, to generate a "equipment overheating risk" label and corresponding operational suggestions, such as "it is recommended to strengthen equipment heat dissipation measures" or "replace overheating components in a timely manner". Through this multi-level and multi-form data fusion, the risk analysis results provide decision makers with a comprehensive risk profile and help formulate accurate risk control strategies.

[0045] Combine data-driven risk analysis results with the equipment data ontology model to generate personalized risk elimination data for each device. Built-in optimization algorithms (such as genetic algorithms or reinforcement learning algorithms) provide support for the formulation of risk reduction strategies, including adjusting operating parameters (such as reducing equipment load), regularly replacing high-risk components, and improving environmental conditions (such as enhancing heat dissipation or vibration reduction measures). Risk elimination data is presented in a structured and actionable form, such as providing specific maintenance instructions or alarm reminder information for equipment operators. At the same time, an optimized equipment operation strategy is generated and automatically pushed to the equipment management system to achieve accurate and proactive risk management and maximize the operating stability and service life of the equipment.

[0046] In the above-mentioned device information processing method based on ontology modeling, the device operation data, environmental monitoring data, device historical data and device data ontology model of the target device set are obtained; according to the data standardization setting in the device data ontology model, the data structure of the device operation data, environmental monitoring data and device historical data is standardized to obtain the device operation standardized data; according to the semantic reasoning rules in the device data ontology model, the device operation standardized data is subjected to equipment failure analysis to obtain the device failure analysis data; the device failure analysis data is subjected to data-driven risk causal analysis to obtain the data-driven risk analysis result; the data-driven risk analysis result is used to generate risk elimination data for any device in the target device set.

[0047] By introducing the equipment data ontology model, the equipment operation data, environmental monitoring data and historical data are standardized, which effectively solves the heterogeneity problem of different data sources and ensures the uniformity of data at the structural and semantic levels, thereby enhancing the accuracy and reliability of data fusion. Equipment fault analysis based on semantic reasoning rules can deeply explore the implicit associations between data, quickly locate potential fault points and identify abnormal trends, and avoid diagnostic omissions caused by single rules or insufficient associations in traditional fault analysis. Subsequently, through data-driven risk causal analysis, the fault phenomenon and potential risks are linked to form a causal chain, further clarifying the key risk sources and risk propagation paths, greatly improving the accuracy and guiding value of the analysis results. The targeted risk elimination data finally generated can effectively respond to abnormal situations caused by dynamically changing complex environments and equipment characteristics, and further provide refined operation and maintenance solutions for each device in the target equipment set when no abnormal situation occurs, which not only improves the equipment's fault prevention and self-adaptation capabilities, but also significantly reduces the impact of systemic risks on the overall equipment operation efficiency and business continuity, providing strong support for the management and optimization of the entire life cycle of equipment.

[0048] In an exemplary embodiment, Figure 3 As shown, according to the data standardization setting in the equipment data ontology model, the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data is standardized to obtain the equipment operation standardized data, including steps 302 to 306. Among them: Step 302 , according to the data standardization setting in the equipment data ontology model, attribute mapping is performed on the equipment operation data, the environment monitoring data and the equipment history data to obtain the equipment operation attribute data.

[0049] Among them, attribute mapping can be the process of matching fields in equipment operation data, environmental monitoring data and equipment historical data collected from different data sources with standard attributes predefined in the equipment data ontology model one by one.

[0050] The equipment operation attribute data may be attribute data that meets the requirements during the equipment operation process obtained after attribute mapping processing. Such data include but are not limited to performance indicators such as temperature, pressure, current, vibration, etc. of the equipment, as well as the working status and load conditions of the equipment.

[0051] Specifically, during the attribute mapping process, each field in the equipment operation data, environmental monitoring data, and equipment historical data needs to be analyzed in detail to ensure that it is consistent with the standard attributes in the equipment data ontology model. This includes identifying and calibrating the type, range, unit, and other information of the equipment data. For example, the "temperature" in the equipment operation data may contain different units (Celsius or Fahrenheit), while the ontology model specifies a unified unit (such as Celsius). Through unit conversion rules, ensure that all data fields match the standard attributes in the ontology model. In addition, for environmental monitoring data from different sources, such as "humidity", there may be different value ranges or data accuracy. By comparing the attribute standards defined in the ontology model, the fields of each data source are mapped to the corresponding standardized attributes, so that data from different sources have consistent attribute definitions and obtain equipment operation attribute data.

[0052] Step 304, fill in missing values ​​for the equipment operation attribute data to obtain equipment filled attribute data.

[0053] Missing value filling can be the process of using certain methods to supplement or fill in missing values ​​when there are blank or incomplete data in the data set.

[0054] The device filled attribute data can be a device data set obtained after completing the missing value filling, in which all vacant or missing data fields have been completed by appropriate methods. These filled data maintain the same format and unit as the original data, and the quality of the filled data is improved, making it more complete and reliable. Fill the attribute data through the device.

[0055] Specifically, the process of filling missing values ​​in equipment operation attribute data needs to adopt different methods according to the type and missing pattern of the data. For time series data (such as temperature and pressure data of equipment), interpolation methods (linear interpolation, spline interpolation, etc.) are often used to fill missing values, which can maintain the temporal continuity of the data. For example, if the temperature data at a certain point in time is missing, the interpolation method will use the temperature values ​​of the previous and next time points to infer and fill the missing values. For other non-time series data (such as equipment status tags or environmental data), the mean filling method, the most common value filling method, or the machine learning-based prediction method (such as K nearest neighbor algorithm, regression analysis, etc.) can be used to predict missing data. These filling methods can be selected according to the data missing pattern (completely random missing, systematic missing, etc.) to ensure that the filled data will not introduce bias or distortion, and obtain equipment filled attribute data.

[0056] Step 306, performing standardization rule conversion on each data information in the equipment filling attribute data to obtain equipment operation standardization data.

[0057] Among them, the standardization rule conversion can be to eliminate the dimensional differences between different data sources or different data types of device data, so that the data can be compared and analyzed under the same standard.

[0058] Specifically, in the stage of converting the standardization rules for each data information in the equipment fill attribute data, standardization methods will be applied to numerical data. Common methods include "Min-Max Normalization", which scales the data to the range of 0 to 1, or "Z-score standardization" (zero mean processing), which makes the data obey the standard normal distribution by subtracting the mean and dividing by the standard deviation. For categorical data with multiple categories of attributes, encoding methods such as One-Hot Encoding are used to convert categorical data into binary vectors. For categorical data with multiple levels (for example, the working status of the equipment ranges from "normal", "warning" to "fault"), label encoding methods (LabelEncoding) can be used to convert it into integer values. All these standardized transformations ensure that the equipment data has consistent dimensions and ranges between different sources, and obtain standardized data on equipment operation.

[0059] In this embodiment, attribute mapping, missing value filling and standardized rule conversion are performed on the equipment operation data, environmental monitoring data and equipment historical data, which helps to improve the consistency and integrity of the data. Attribute mapping unifies the structure of different data sources, making various types of data compatible and integrated, and eliminating the differences between data. Missing value filling solves the problem of missing data and avoids the analysis errors and inaccuracies caused by null values. Standardized rule conversion unifies the units and dimensions of different data to ensure that the data can be compared and analyzed at the same scale. The quality of the data processed by these steps is significantly improved, providing a more reliable and accurate basis for subsequent equipment fault diagnosis, risk analysis and decision support.

[0060] In an exemplary embodiment, Figure 4 As shown, according to the data standardization setting in the device data ontology model, attribute mapping is performed on the device operation data, the environmental monitoring data and the device history data to obtain the device operation attribute data, including steps 402 to 404. Among them: Step 402, determining the simple structure creation class, the complex structure creation class, the simple structure data attributes, the complex structure data attributes and the definition object attributes in the data standardization setting.

[0061] Among them, simple structure creation classes usually refer to simple data models composed of basic data types (such as integers, floating-point numbers, strings, etc.). These classes contain only a single data element without complex nesting or substructures. For example, temperature, pressure, equipment status, etc. can be classified as simple structure classes. Complex structure creation classes contain multiple attributes or more complex data relationships, usually composed of multiple subclasses, data fields, or nested structures. For example, a device's "fault record" class may include multiple attributes such as fault type, fault occurrence time, and maintenance status. Such a class is a complex structure class.

[0062] Simple structure data attributes refer to the basic data fields contained in simple structure classes, such as the current temperature and pressure value of the equipment. They are directly measurable and usually exist in numerical form. Complex structure data attributes refer to attributes in complex structure classes that contain multiple related data fields. For example, "fault type" and "maintenance record" in the equipment fault log are complex structure data attributes. These attributes usually contain multiple levels of detailed information and may be associated with other equipment or environmental data. Defined object attributes refer to specific information related to the equipment defined in the equipment data ontology model (such as equipment model, location, maintenance cycle, etc.). These attributes provide detailed background and context information for subsequent data processing, analysis, and management.

[0063] Specifically, in the initial stage of data standardization, it is necessary to define the structure types in the data model. This includes determining the "simple structure creation class" and "complex structure creation class" and their respective attribute types. Simple structure creation classes usually refer to classes that contain a single data element or basic data type (such as numeric values, strings, etc.), while complex structure creation classes may contain multiple attributes or nested data structures. Next, clarify the "simple structure data attributes" and "complex structure data attributes" contained in each structure. Simple structure data attributes are usually directly available numeric data (such as temperature, pressure, etc.), while complex structure data attributes may involve multiple sub-attributes (such as equipment failure type and maintenance records). Finally, defining object attributes refers to mapping specific information related to the equipment (such as equipment model, location, maintenance cycle, etc.) into the data structure for subsequent processing and management.

[0064] Step 404, according to the simple structure creation class, the complex structure creation class, the simple structure data attributes, the complex structure data attributes and the defined object attributes, the equipment operation data, the environmental monitoring data and the equipment historical data are mapped to obtain the equipment operation attribute data.

[0065] Specifically, after defining the structure classes and attributes in the data standardization settings, the equipment operation data, environmental monitoring data, and equipment historical data are mapped to these structure classes. This process requires dividing the data into different categories through simple structure classes and complex structure classes. For each field in the equipment operation data (such as temperature, pressure, current, etc.), it is mapped to the corresponding data attribute in the simple structure creation class according to the nature of the data, such as the temperature field is mapped to the "temperature attribute"; for environmental monitoring data and equipment historical data. If it contains more complex associated information (such as equipment fault logs and repair records), it needs to be mapped to the data attributes in the complex structure creation class; this mapping ensures that all equipment information is organized according to the standard structure in the ontology model, which is convenient for unified processing. In the end, all equipment operation data, environmental monitoring data, and equipment historical data will be organized into equipment operation attribute data, which conforms to the standardized settings in structure, facilitating subsequent analysis and decision-making.

[0066] In this embodiment, by determining the simple structure creation class, complex structure creation class, simple structure data attributes, complex structure data attributes, and defined object attributes in the data standardization settings, and mapping the equipment operation data, environmental monitoring data, and equipment historical data according to these settings, the data can be effectively structured and standardized. This process can uniformly convert data from different sources and types into data with clear attributes and structures, ensuring that the data is consistent and operational in subsequent analysis. Through attribute mapping, the differences between device data are eliminated, and the expression of data becomes standardized, thereby improving the efficiency and accuracy of data processing and analysis. This standardized processing method provides a clearer and more reliable data foundation for equipment failure prediction, risk analysis, and decision support, which helps to improve the intelligence level of the system.

[0067] In an exemplary embodiment, Figure 5 As shown, according to the semantic reasoning rules in the equipment data ontology model, the equipment operation standardized data is analyzed for equipment failure to obtain equipment failure analysis data, including steps 502 to 506. Among them: Step 502: Determine a device data reasoning framework corresponding to the semantic reasoning rule based on the device operation standardized data.

[0068] Among them, the equipment data reasoning framework can be a logical structure built based on the equipment data ontology model and semantic reasoning rules, which provides a basis and path for data analysis for equipment fault analysis.

[0069] Specifically, based on the standardized data of equipment operation, identify and select the reasoning framework corresponding to the semantic reasoning rules in the equipment data ontology model. Among them, the equipment data reasoning framework is a logical framework built based on semantic reasoning rules, which is used to reason and analyze the operating status of the equipment. This framework usually includes various performance indicators, failure modes, working environment and relationships between equipment. When constructing the equipment data reasoning framework, the system will combine the standardized data of equipment operation (such as temperature, pressure, load, etc.) with the fault reasoning rules to determine the position and function of each data point in the reasoning framework, thereby providing a basis for subsequent fault reasoning. The determination of the reasoning framework is the core part of semantic reasoning, which provides rules and structural support for the subsequent reasoning analysis.

[0070] Step 504 , performing equipment fault inference on the equipment operation standardized data according to the equipment data inference framework to obtain equipment fault inference data.

[0071] Among them, equipment failure reasoning can be a process of analyzing the equipment operation data by applying semantic reasoning rules on the basis of the equipment data reasoning framework, so as to infer the possible equipment failure type or risk.

[0072] Among them, the equipment failure reasoning data can be the result data generated through the equipment failure reasoning process, which usually includes information such as the potential failure type, the probability of failure occurrence, the possible cause of the failure and the influencing factors obtained by reasoning.

[0073] Specifically, after determining the equipment data inference framework, the system will analyze the standardized data item by item according to the preset inference rules of the equipment data inference framework (such as threshold judgment based on statistics, causal inference rules or expert knowledge base rules). For each key indicator (such as equipment temperature, pressure, vibration amplitude, etc.), the system will determine whether it is within the normal range based on historical data and operating environment. If the data exceeds the normal range, the inference engine will trigger the corresponding fault inference rule. For example, if the temperature is too high and the equipment load is large, the system may infer the risk of electrical failure. Furthermore, the inference rules may also combine environmental data (such as humidity, air pressure, etc.) and historical equipment failure data to comprehensively judge the potential failure mode under multiple factors. This process usually uses machine learning algorithms, Bayesian reasoning or rule engines to help the system derive equipment failure inference data.

[0074] Step 506, organizing the equipment fault reasoning data according to the fault structured analysis rules of the equipment data ontology model to obtain equipment fault analysis data.

[0075] Among them, the fault structured analysis rules can be standardized rules for classifying, sorting and organizing equipment fault reasoning data. These rules are designed to organize the equipment's failure mode, cause of failure, influencing factors, failure data and other information in a structured form to facilitate subsequent analysis and decision-making. These rules usually include fault classification, priority sorting, causal relationship modeling and other content.

[0076] Specifically, according to the fault structured analysis rules in the equipment data ontology model, the equipment fault reasoning data usually contains information such as failure mode, failure probability, possible failure causes and related performance data. These data need to be structured and organized, that is, they are classified, sorted and associated according to the rules of the equipment fault model to generate a clear equipment fault analysis data. For example, the system will classify different types of faults (such as mechanical failures, electrical failures, etc.) and sort them by importance and urgency. Through the application of fault structured analysis rules, the final equipment fault analysis data can provide a basis for subsequent risk assessment, maintenance decisions and optimization measures.

[0077] In this embodiment, by determining the equipment data reasoning framework corresponding to the semantic reasoning rules based on the standardized data of equipment operation, and performing equipment fault reasoning on it, an in-depth analysis of the equipment status and early prediction of potential faults can be achieved. This process enables the operation data of the equipment to be structured and analyzed through the semantic reasoning framework, automatically identifying potential fault modes and abnormal conditions, and providing strong support for fault warning. By applying the fault structured analysis rules and organizing the reasoning results, the relevant data of the equipment failure can be systematically presented, making fault diagnosis more accurate and efficient. This method improves the accuracy and timeliness of equipment fault detection, helps to optimize equipment maintenance strategies, reduce downtime, reduce maintenance costs, and provide guarantees for the long-term stable operation of equipment.

[0078] In an exemplary embodiment, Figure 6 As shown, according to the equipment data inference framework, equipment failure inference is performed on the equipment operation standardized data to obtain equipment failure inference data, including steps 602 to 606. Among them: Step 602 : Use the device data inference framework to execute semantic inference rules to infer initial device failure data and initial device failure mode in the device operation standardized data.

[0079] Among them, the initial equipment failure data can be the preliminary failure information derived from the standardized data of equipment operation by semantic reasoning rules. These data usually come from the real-time operating status of the equipment, such as temperature, pressure, vibration and other sensor data.

[0080] The initial device failure mode may be a failure type or a failure state matched by the initial device failure data.

[0081] Specifically, the system selects appropriate semantic reasoning rules to analyze the standardized data of equipment operation according to the semantic reasoning rules set in the equipment data reasoning framework. These semantic reasoning rules may include judgments based on thresholds (for example, when the equipment temperature exceeds 80°C, it is inferred to be an overheating fault), causal reasoning (such as "excessive vibration frequency will cause mechanical wear"), failure modes appearing in the equipment's historical data, and reasoning rules for abnormal data in the equipment (abnormal statistical algorithms, abnormal analysis algorithms), etc. The system further applies the semantic reasoning rules to the standardized data of equipment operation based on the equipment data reasoning framework, and uses the specific reasoning details and reasoning algorithms (such as rule engines or Bayesian reasoning) in the semantic reasoning rules to obtain the initial fault data and initial equipment failure mode.

[0082] Step 604: merge the initial device failure data into the initial device failure mode to obtain device failure link data.

[0083] The device failure link data may be a data set after a multi-level failure propagation path is formed by connecting the initial device failure data with the corresponding failure mode through a causal relationship.

[0084] Specifically, the system associates preliminary fault data (such as excessive temperature, abnormal pressure, etc.) with the corresponding initial equipment failure mode to form an associated fault data unit. For example, if a data point of "too high temperature" appears during equipment operation, this data point may be associated with "overheating failure mode" to form a preliminary link of "too high temperature → overheating failure mode". The system not only needs to simply pair single fault data with fault modes, but also needs to consider multiple relationships and fault propagation between devices. For example, excessive temperature of a certain device may first cause damage to electrical components, thereby causing system shutdown, thus forming a multi-level fault link. In this way, the system integrates all initial fault data and initial fault modes to form complete equipment fault link data, and ensures that the causal relationship between each link can accurately reflect the fault propagation path, providing a basis for subsequent risk analysis and decision-making.

[0085] Step 606: perform link anomaly analysis on the equipment failure link data to obtain equipment failure analysis data.

[0086] Among them, link anomaly analysis can be an in-depth analysis of the data in the device fault data link, with the purpose of discovering abnormal fault data or inconsistent inference results that may exist in the link.

[0087] Specifically, the system will review each link in the entire equipment failure link data to check whether the data conforms to the preset logical order. For example, the failure link of a certain device may start with "temperature anomaly" and then infer "electrical failure" through "overheating failure mode". If the data of a certain link in the equipment failure link data (such as the inference of electrical failure) does not match the data of other links, the system will mark it as abnormal. In addition, the system also needs to check whether there are omissions or errors in the data in the equipment failure link data, such as failure data that the device failed to record or abnormal jumps in the reasoning process. If a data point in the equipment failure link data is inconsistent with the normal fault propagation pattern, it may mean that there is a deviation in the fault reasoning rule or data is missing. Through the abnormal analysis of the equipment failure link data, the system can identify the unconventional parts of the fault chain, and then adjust the reasoning rules or fill in the data gaps.

[0088] When the link is confirmed to be correct, the device fault link data is analyzed for abnormalities. For example, the system may find that the data value of a certain fault mode in the link is abnormal, such as temperature abnormality does not match the vibration mode, or the fault data of a certain device component (such as low voltage) does not match the actual operating status. Through this abnormal analysis, the system can find "abnormal fault data" or inconsistent data points in the link data. These abnormal data may come from equipment failure, data collection errors, or problems with the inference model. Once abnormal data in the link is found, the system will mark it as equipment failure inference data. This data includes abnormal data identified in the faulty link, error points in the inference process, and potential root causes of failure.

[0089] In this embodiment, by using the device data inference framework to execute semantic reasoning rules, the initial device failure data and failure modes can be effectively inferred from the standardized data of device operation, thereby realizing early identification of potential device failures. The initial device failure data is integrated with the failure mode to further construct the device failure link data, which can reveal the propagation path and causal relationship of the failure in each component or system of the device, and provide systematic information for subsequent failure analysis. Link anomaly analysis of the device failure link data can deeply explore potential problems in the fault propagation process, identify abnormal links, and help locate the source of the failure and potential risk points. This series of processes helps to improve the accuracy and timeliness of equipment fault detection, optimize maintenance decisions, reduce unplanned equipment downtime, and improve the reliability and safety of the overall system.

[0090] In an exemplary embodiment, Figure 7 As shown, data-driven risk causal analysis is performed on the equipment failure analysis data to obtain data-driven risk analysis results, including steps 702 to 708. Among them: Step 702: Perform risk causal analysis on the equipment failure analysis data to obtain risk causal analysis results.

[0091] Among them, risk causal analysis can be the process of identifying and understanding the cause-and-effect relationship between equipment failures or system problems. In this analysis, the system constructs the cause-and-effect chain between failure or risk factors by evaluating equipment failure analysis data. Its purpose is to clarify which factors are the root cause of failures or risks, and which factors will lead to further failures or system failures.

[0092] Among them, the risk causal analysis result can be a specific conclusion obtained after analysis, which describes the causal relationship between different fault data or risk factors.

[0093] Specifically, the system will extract relevant information such as failure modes, root causes, frequency of failures, and equipment operating environment from the equipment failure analysis data, and use statistical methods (such as regression analysis, Bayesian networks) or machine learning techniques (such as decision trees and neural networks) to establish a causal relationship model between failure data. For example, the system can derive the main data and main causes of electrical failures based on historical data, and the main data and main causes of electrical failures may further lead to serious consequences such as equipment damage data and equipment damage conditions. Through this analysis, the system identifies the relationship between different failure modes, failure factors, and failure data, and evaluates the degree of impact of each factor on the risk, and finally generates risk causal analysis results.

[0094] Step 704, perform graphical conversion on the risk causal analysis results to obtain risk causal graphical data.

[0095] Among them, graphical conversion can be the process of presenting the abstract risk causal analysis results in a graphical form. Through visualization, complex causal relationships and risk propagation paths are converted into intuitive charts or images, making the data easier to understand and analyze.

[0096] Among them, risk causal image data can be a data format that presents the results of risk causal analysis in a graphical way. These data include visualization charts or images of failure modes, failure data, risk factors and their interrelationships. Graphical data usually contains multiple nodes, each node represents an equipment failure, failure data, risk mode or risk factor, and the lines between nodes represent the causal relationship or impact path between different failures or risks.

[0097] Specifically, the system converts the different output data and output results of the risk causal analysis into charts, flow charts or network diagrams. In this visualization process, each failure mode, equipment component or risk factor will be a node in the diagram, and the node is marked with failure data (the node is usually a circle or rectangle). The lines between nodes represent causal relationships or risk propagation paths. For example, a line in the diagram may connect the "overtemperature" failure mode with the "overheating" failure mode, indicating that abnormal temperature can cause equipment to overheat, and mutual reasoning and prediction can be made through the failure data on the node. Each node can contain specific risk values, such as the probability of failure or the severity of the risk. In this way, the visualized risk causal diagram can help decision makers quickly identify key risk points in the equipment system and their mutual influence, thereby optimizing the decision-making process.

[0098] Step 706, performing risk diffusion analysis on the risk causal image data to obtain risk diffusion analysis results.

[0099] Among them, risk diffusion analysis can be a process of simulating how risk factors in a device or system spread from one component to other components, which is used to reveal how failures or risks propagate through a chain of cause and effect, ultimately affecting the stability of the entire system or device.

[0100] Among them, the risk diffusion analysis results can be specific conclusions obtained based on the risk diffusion analysis process, revealing the propagation path of risk factors in the equipment system and the extent of their impact.

[0101] Specifically, the system uses risk causal image data to perform risk diffusion analysis, simulating how faults or risk factors propagate within a device or system. The core of risk diffusion analysis is to identify how a local fault (such as a single component fault) affects other device components or subsystems, leading to a wider system-level fault. The system builds a diffusion model to analyze the connections and propagation paths between various risk nodes and evaluate how a fault may trigger a chain reaction. For example, in a complex device, the failure of a sensor may cause erroneous outputs from multiple system modules, ultimately leading to a complete shutdown of the device. In order to achieve diffusion analysis, the system usually uses graph theory methods, combined with the node and edge information of risk causal image data, to simulate the transmission effects between various fault modes and fault data. Through this analysis, the system can identify which fault points may become the source of diffusion risk, as well as the propagation speed and range of fault diffusion, and obtain risk diffusion analysis results. The diffusion analysis results provide decision makers with a detailed view of the fault propagation path, helping them identify high-risk areas and take targeted risk prevention measures.

[0102] Step 708, performing risk control optimization on the risk diffusion analysis results to obtain data-driven risk analysis results.

[0103] Among them, risk control optimization can be achieved by adjusting and improving equipment management and maintenance strategies to reduce the probability of equipment failure and the impact of risk diffusion.

[0104] Specifically, the system will analyze the data of key risk points and fault propagation paths in the risk diffusion analysis results, evaluate the effectiveness of existing control measures (such as monitoring frequency, redundant configuration, maintenance cycle, etc.), and optimize them. For example, if the analysis finds that a key component has a high risk of fault diffusion, the system may recommend increasing the monitoring frequency of the component or designing a redundant system to reduce the impact of single point failures. At the same time, the system can also adjust the control strategy through a data-driven approach based on the maintenance history and operation data of the equipment to minimize risk exposure and optimize resource allocation. The optimization process may include adjusting maintenance plans, increasing spare parts inventory, improving equipment design, etc. Finally, the optimized risk control measures will be output as data-driven risk analysis results, which contain adjusted risk control data and strategies, risk mitigation data, measures and their expected effects.

[0105] In this embodiment, by performing risk causal analysis on the equipment failure analysis data, the causal relationship between the equipment failure and the risks caused by it can be deeply identified and understood, helping the system to predict potential risk sources and their possible consequences in advance. The results of the risk causal analysis are converted into images, making complex risk data more intuitive and easier to understand, providing decision makers with a clear risk view. Next, by performing risk diffusion analysis on the risk causal image data, the risk propagation process in the system can be simulated, its impact on other equipment or system components can be evaluated, and then the key risk diffusion path can be identified. Finally, risk control optimization based on the results of the risk diffusion analysis can accurately formulate effective risk management strategies, reduce the impact of potential failures, optimize resource allocation, and improve the system's risk resistance. This series of steps effectively improves the scientificity and foresight of risk management, helps reduce the economic losses caused by equipment failures, and improves the stability and safety of equipment and systems.

[0106] In an exemplary embodiment, Figure 8 As shown, risk diffusion analysis is performed on risk causal image data to obtain risk diffusion analysis results, including steps 802 to 808. Among them: Step 802: Analyze the node risk status information of each node in the risk causal graphical data to obtain node risk analysis data of each node.

[0107] The node risk status information may be the health status or risk status of each device node (such as a device component, sensor, or risk factor) at a specific moment.

[0108] Among them, the node risk analysis data can be data obtained through multi-dimensional analysis and calculation based on the node risk status information to further evaluate the overall risk level of the node.

[0109] Specifically, the system analyzes the risk status information of each node in the risk causal image data. Each node usually represents a possible failure type, failure data, failure mode, risk factor or system component of a device, and the risk status of the node reflects the risk level corresponding to the node, such as the degree of harm caused by the failure, the health status of the equipment, and the expected life span. The system obtains specific risk analysis data for each node through quantitative analysis of the status of these nodes (such as failure probability based on historical data, anomaly detection of monitoring data, etc.). These data may include information such as the node's failure rate, risk index, stability assessment, etc., to help the system fully understand the current status and potential threats of each risk node.

[0110] The node risk status information of each node in the risk causal image data is analyzed, and the calculation formula corresponding to the node risk analysis data of each node is obtained as follows:

[0111] Among them, R i (t+1) is the risk value of node i at time t+1; In(i) is the set of parent nodes connected to node i; P ji (t) is the dynamic risk propagation probability from node j to node i at time t; R j (t) is the risk value of node j at time t; W ji (t) is the dynamic weight from node j to node i; α is the decay rate; β i is the sensitivity of the node to environmental factors; d ji is the physical distance or logical distance between two nodes; F i (t) is the external environment effect on node i at time t, f j (t) is the state impact factor of node j, f k (t) is the state influence factor of any parent node in the set of parent nodes connected to node i, and k is the identifier of any parent node in the set of parent nodes connected to node i.

[0112] Among them, the dynamic risk propagation probability is obtained by analyzing historical fault data and counting the correlation between faults between different nodes. For example, the relationship between sensor failure and control signal loss in past fault events is analyzed; or by using statistical methods such as regression analysis and maximum likelihood estimation (MLE) to calculate the probability from historical data.

[0113] Among them, the risk value of node j at time t is usually used to quantify the operating status and failure risk of node j at time t of a device or system module. The calculation of the risk value depends on multiple factors, such as real-time monitoring data, historical failure data, equipment health status, and environmental factors.

[0114] Among them, the dynamic weight calculates the health status of the node in real time based on the data of the device sensor (temperature, pressure, vibration, etc.), and updates the weight according to the health status. For example, if the sensor fails frequently, the weight is increased, indicating that it has a greater impact on subsequent modules.

[0115] The attenuation rate is determined by regression analysis after estimating the attenuation characteristics of risk propagation measurements between different devices and modules through experiments or historical data.

[0116] Among them, the external environment effect uses sensors to collect environmental data and maps it to the risk value of the node; or it is determined by analyzing the impact of environmental factors on the equipment based on historical data or theoretical models.

[0117] The sensitivity of environmental factors is determined by the technical specifications provided by the device manufacturer to determine the sensitivity of the device to environmental changes; or it is determined by calculating the device's responsiveness to environmental factors (such as temperature, humidity, etc.) based on historical data.

[0118] The physical distance between two nodes is determined based on the geometric distance in space; the logical distance between two nodes is determined by the direct or indirect dependency between device modules. For example, the signal transmission between sensors and controllers and actuators forms a logical dependency. The logical distance reflects the strength or impact of this dependency.

[0119] The state impact factor is defined by monitoring the failure rate or abnormal frequency of each node. The higher the abnormal frequency of a node, the greater its impact on other nodes.

[0120] Among them, f k (t) is the state impact factor of any parent node in the set of parent nodes connected to node i. The state impact factor is defined by monitoring the failure rate or abnormal frequency of any parent node in the set of parent nodes connected to node i.

[0121] Step 804 , identifying key risk analysis data corresponding to each risk key node from the node risk analysis data of each node.

[0122] Among them, key risk analysis data can be risk data obtained by identifying and analyzing nodes that are critical to system security and stability. These data focus on key nodes that may cause system-level risks or affect system operation once a failure occurs.

[0123] Specifically, the node risk analysis data of each node in the system is screened to identify the key risk nodes in the system. Key risk nodes usually refer to those nodes that have a greater impact on the overall system security and stability. These nodes may be important links in the failure chain, or their failures may cause major problems at the system level. By sorting, evaluating and comparing the node risk analysis data, the system identifies the most risky nodes and extracts these nodes to generate detailed node risk analysis data as key risk analysis data.

[0124] Step 806, determining the key risk path according to each key risk analysis data.

[0125] Specifically, after identifying the key risk nodes, the system will further derive the key risk path based on these key risk analysis data. The key risk path refers to the path in the system that starts from a certain failure or risk factor, propagates through a series of risk nodes, and ultimately affects the overall performance or safety of the system. The system will analyze the causal relationship and risk propagation path between each key risk node. For example, the system uses graph theory, causal reasoning or network analysis algorithms to determine these paths, and evaluate the potential contribution of each path to system risk, and identify those chains that may cause cascading failures or risk spread. If the failure of a key node affects multiple subsequent nodes, resulting in a chain reaction, then these nodes and the connections between them constitute a key risk path.

[0126] Step 808, obtaining risk diffusion analysis results based on each key risk analysis data and key risk path.

[0127] Specifically, after determining the critical risk path, the system combines the critical risk analysis data and the critical risk path to conduct risk diffusion analysis. The goal is to simulate and analyze how these critical risk nodes and paths spread within the device or system, ultimately affecting the overall stability and safety of the system. Based on the previous critical risk analysis data (such as node failure probability, fault propagation speed, system redundancy design, etc.), the system combines the causal relationship of the critical risk path and the interdependence between devices, and applies it to the diffusion model (such as algorithms based on graph theory, propagation models, etc.), analyzes the way risks are transmitted from one node to other nodes, and calculates the speed and scope of risk diffusion. Finally, the system comprehensively considers the equipment redundancy design, fault tolerance mechanism, and the amplification effect of risk transmission, and obtains the risk diffusion analysis results, which clearly defines which paths and nodes are the most risky and which areas may cause system-level failures, thereby providing decision support for subsequent risk control and optimization measures.

[0128] In this embodiment, by analyzing the node risk status information of each node in the risk causal graphical data, the potential risk situation of each node can be fully understood, helping to identify nodes with higher risks and their failure probabilities. Further extracting key risk analysis data from the node risk analysis data helps to accurately locate key nodes that may cause system-level impacts once a failure occurs. By identifying these key nodes and their related data, the diffusion path of risks in the system can be determined, revealing how failures spread to other nodes or system parts through causal relationships. Ultimately, based on these key risk analysis data and risk paths, the risk diffusion analysis results obtained not only help predict the risk propagation trend, but also provide effective decision-making support for risk prevention and control and emergency response, improve the safety and reliability of the system, and reduce potential losses and failure impacts.

[0129] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0130] Based on the same inventive concept, the embodiment of the present application also provides a device information processing apparatus based on ontology modeling for implementing the device information processing method based on ontology modeling involved above. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more device information processing apparatus embodiments based on ontology modeling provided below can refer to the limitations of a device information processing method based on ontology modeling above, and will not be repeated here.

[0131] In an exemplary embodiment, Fig. 9 As shown, a device information processing apparatus based on ontology modeling is provided, including: a data acquisition module 902, a data conversion module 904, a fault analysis module 906 and a risk analysis module 908, wherein: Data acquisition module 902, used to acquire device operation data, environmental monitoring data, device history data and device data ontology model of the target device set; The data conversion module 904 is used to standardize the data structure of the equipment operation data, the environmental monitoring data and the equipment history data according to the data standardization setting in the equipment data ontology model to obtain the equipment operation standardized data; The fault analysis module 906 is used to perform equipment fault analysis on the equipment operation standardized data according to the semantic reasoning rules in the equipment data ontology model to obtain equipment fault analysis data; The risk analysis module 908 is used to perform data-driven risk causal analysis on the equipment failure analysis data to obtain data-driven risk analysis results; the data-driven risk analysis results are used to generate risk elimination data for any device in the target device set.

[0132] In one embodiment, the data conversion module 904 is also used to perform attribute mapping on the equipment operation data, environmental monitoring data and equipment historical data according to the data standardization settings in the equipment data ontology model to obtain equipment operation attribute data; fill in missing values ​​on the equipment operation attribute data to obtain equipment filled attribute data; and perform standardization rule conversion on each data information in the equipment filled attribute data to obtain equipment operation standardized data.

[0133] In one embodiment, the data conversion module 904 is also used to determine the simple structure creation class, the complex structure creation class, the simple structure data attributes, the complex structure data attributes and the definition object attributes in the data standardization setting; according to the simple structure creation class, the complex structure creation class, the simple structure data attributes, the complex structure data attributes and the definition object attributes, the equipment operation data, the environmental monitoring data and the equipment historical data are mapped to obtain the equipment operation attribute data.

[0134] In one embodiment, the fault analysis module 906 is also used to determine an equipment data reasoning framework corresponding to a semantic reasoning rule based on the equipment operation standardized data; perform equipment fault reasoning on the equipment operation standardized data according to the equipment data reasoning framework to obtain equipment fault reasoning data; organize the equipment fault reasoning data according to the fault structured analysis rules of the equipment data ontology model to obtain equipment fault analysis data.

[0135] In one embodiment, the fault analysis module 906 is also used to use the equipment data inference framework to execute semantic reasoning rules to infer the initial equipment failure data and the initial equipment failure mode in the equipment operation standardized data; merge the initial equipment failure data into the initial equipment failure mode to obtain equipment failure link data; perform link anomaly analysis on the equipment failure link data to obtain equipment failure reasoning data.

[0136] In one embodiment, the risk analysis module 908 is also used to perform risk causal analysis on the equipment failure analysis data to obtain risk causal analysis results; perform graphical conversion on the risk causal analysis results to obtain risk causal graphical data; perform risk diffusion analysis on the risk causal graphical data to obtain risk diffusion analysis results; perform risk control optimization on the risk diffusion analysis results to obtain data-driven risk analysis results.

[0137] In one embodiment, the risk analysis module 908 is also used to analyze the node risk status information of each node in the risk causal graphical data to obtain the node risk analysis data of each node; identify the key risk analysis data corresponding to each risk key node from the node risk analysis data of each node; determine the key risk path based on each key risk analysis data; and obtain the risk diffusion analysis result based on each key risk analysis data and the key risk path.

[0138] Each module in the device information processing apparatus based on ontology modeling can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0139] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a device information processing method based on ontology modeling is implemented.

[0140] Those skilled in the art will understand that Fig.10The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0141] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0142] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0143] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0144] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0146] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A device information processing method based on ontology modeling, characterized in that: The method comprises: Obtain device operation data, environmental monitoring data, device history data, and device data ontology model of the target device set; According to the data standardization setting in the equipment data ontology model, the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data is standardized to obtain equipment operation standardized data; According to the semantic reasoning rules in the equipment data ontology model, performing equipment failure analysis on the equipment operation standardized data to obtain equipment failure analysis data; A data-driven risk causal analysis is performed on the equipment failure analysis data to obtain a data-driven risk analysis result; the data-driven risk analysis result is used to generate risk elimination data for any device in the target equipment set.

2. The method according to claim 1, characterized in that The data structure of the equipment operation data, the environment monitoring data and the equipment history data is standardized according to the data standardization setting in the equipment data ontology model to obtain equipment operation standardized data, including: According to the data standardization setting in the device data ontology model, attribute mapping is performed on the device operation data, the environment monitoring data and the device history data to obtain device operation attribute data; Filling missing values ​​in the equipment operation attribute data to obtain equipment filled attribute data; The various data information in the device filling attribute data are converted according to standardization rules to obtain the device operation standardized data.

3. The method according to claim 2, characterized in that According to the data standardization setting in the device data ontology model, attribute mapping is performed on the device operation data, the environment monitoring data and the device history data to obtain device operation attribute data, including: Determine the simple structure creation class, the complex structure creation class, the simple structure data attributes, the complex structure data attributes and the definition object attributes in the data standardization setting; According to the simple structure creation class, the complex structure creation class, the simple structure data attributes, the complex structure data attributes and the definition object attributes, the equipment operation data, the environmental monitoring data and the equipment historical data are mapped to obtain the equipment operation attribute data.

4. The method according to claim 1, characterized in that: The step of performing equipment failure analysis on the equipment operation standardized data according to the semantic reasoning rules in the equipment data ontology model to obtain equipment failure analysis data includes: Determining a device data reasoning framework corresponding to the semantic reasoning rule according to the device operation standardized data; According to the equipment data inference framework, performing equipment fault inference on the equipment operation standardized data to obtain equipment fault inference data; The equipment fault reasoning data is organized according to the fault structured analysis rules of the equipment data ontology model to obtain the equipment fault analysis data.

5. The method according to claim 4, characterized in that The step of performing equipment failure reasoning on the equipment operation standardized data according to the equipment data reasoning framework to obtain equipment failure reasoning data includes: Execute the semantic reasoning rules using the equipment data reasoning framework to infer the initial equipment failure data and the initial equipment failure mode in the equipment operation standardized data; Merging the initial device failure data into the initial device failure mode to obtain device failure link data; Perform link anomaly analysis on the device failure link data to obtain the device failure inference data.

6. The method according to any one of claims 1 to 5, characterized in that: The performing data-driven risk causal analysis on the equipment failure analysis data to obtain a data-driven risk analysis result includes: Performing risk causal analysis on the equipment failure analysis data to obtain risk causal analysis results; Performing graphical conversion on the risk causal analysis results to obtain risk causal graphical data; Performing risk diffusion analysis on the risk causal image data to obtain risk diffusion analysis results; The risk diffusion analysis result is subjected to risk control optimization to obtain the data-driven risk analysis result.

7. The method according to claim 6, characterized in that The performing risk diffusion analysis on the risk causal graphical data to obtain the risk diffusion analysis result includes: Analyze the node risk status information of each node in the risk causal graphical data to obtain node risk analysis data of each node; Identifying key risk analysis data corresponding to each key risk node from the node risk analysis data of each of the nodes; Determine the key risk path based on the key risk analysis data; The risk diffusion analysis result is obtained according to each of the key risk analysis data and the key risk path.

8. The method according to claim 7, characterized in that The node risk status information of each node in the risk causal graphical data is analyzed to obtain the calculation formula corresponding to the node risk analysis data of each node: Among them, R i (t+1) is the risk value of node i at time t+1; In(i) is the set of parent nodes connected to node i; P ji (t) is the dynamic risk propagation probability from node j to node i at time t; R j (t) is the risk value of node j at time t; W ji (t) is the dynamic weight from node j to node i; α is the decay rate; β i is the sensitivity of the node to environmental factors; d ji is the physical distance or logical distance between two nodes; F i (t) is the external environment effect on node i at time t, f j (t) is the state impact factor of node j, f k (t) is the state influence factor of any parent node in the set of parent nodes connected to node i, and k is the identifier of any parent node in the set of parent nodes connected to node i.

9. A device information processing device based on ontology modeling, characterized in that: The device comprises: A data acquisition module, used to acquire device operation data, environmental monitoring data, device history data and device data ontology model of a target device set; A data conversion module, used to standardize the data structure of the equipment operation data, the environmental monitoring data and the equipment historical data according to the data standardization setting in the equipment data ontology model, so as to obtain equipment operation standardized data; A fault analysis module, used to perform equipment fault analysis on the equipment operation standardized data according to the semantic reasoning rules in the equipment data ontology model to obtain equipment fault analysis data; The risk analysis module is used to perform data-driven risk causal analysis on the equipment failure analysis data to obtain data-driven risk analysis results; the data-driven risk analysis results are used to generate risk elimination data for any device in the target device set.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images