An IT asset management system and method based on data analysis

Abstract

The application discloses an IT asset management system and method based on data analysis, and relates to the technical field of business information management and intelligent decision-making, which comprises a data fusion module, a digital shadow construction module, a deduction analysis module, a decision generation module and a dynamic coupling relationship digital shadow calibration module. The application realizes a fundamental change from passive response operation to active prediction risk management by constructing a dynamic digital shadow containing a double coupling relationship of physical environment and business logic and simulating deduction of operation on the dynamic digital shadow. The method can reveal and quantify the implicit cascading risk caused by physical proximity or business dependence, so that the operation team can predict the potential chain effect on the entire production system before performing any operation, thereby eliminating most secondary failure risks in the embryonic state without affecting the actual production safety, and enhancing the stability and operation resilience of the system.

Description

Technical Field

[0001] This invention relates to the field of business information management and intelligent decision-making technology, specifically to an IT asset management system and method based on data analysis. Background Technology

[0002] Offshore oil and gas platforms are complex industrial facilities integrating production, processing, and living quarters. Their stable operation highly depends on the collaborative work of various information technology assets and operational technology assets. Information technology assets, or IT assets, mainly include servers, network equipment, and management systems used for data processing, storage, communication, and management. Operational technology assets, or OT assets, encompass controllers, sensors, and production execution systems used to directly monitor and control physical production processes. Efficient and intelligent operation and maintenance management of these assets, especially IT assets that play a crucial supporting role in production operations, is a key link in ensuring the safe production and economic benefits of offshore platforms.

[0003] Existing technologies, such as the comparative cases related to IT asset management published in CN119759980A and CN119759876A, demonstrate that current operation and maintenance management of offshore oil and gas platform assets typically employs multiple independent systems to monitor and maintain IT and OT assets separately. The IT operations team primarily focuses on indicators such as server performance, network connectivity, and information security, while the OT operations team focuses on the real-time performance and reliability of the production control system. Routine operations and maintenance activities mainly rely on alarm systems based on fixed thresholds to identify problems, and troubleshooting and handling are conducted through regular on-site inspections by engineers or remote login. Decisions regarding asset optimization, upgrades, or replacement investments are largely based on a comprehensive assessment of the equipment's age, historical failure rate, and the practical experience of the operations and maintenance personnel.

[0004] However, existing technologies have significant limitations. First, the disconnect between IT and OT systems in management leads to information silos in asset data, preventing operations personnel from obtaining a comprehensive view of the relationship between assets and production operations. Second, the reliance on threshold-based alarms and manual inspections is essentially a reactive approach, making it difficult to detect and warn of potential fault chains caused by complex interrelationships between multiple systems and devices. Furthermore, operational decisions heavily depend on personal experience, lacking a quantitative analysis method that comprehensively assesses asset costs, effectiveness, and potential risks, making it difficult to guarantee optimal and safe decisions in complex operational scenarios. Summary of the Invention

[0005] In view of the above-mentioned technical shortcomings, the purpose of this invention is to provide an IT asset management system and method based on data analysis.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The first aspect of the present invention provides an IT asset management system based on data analysis, including: a data fusion module, used to acquire multi-source asset data in the information network and production network of offshore oil and gas platforms, and to perform fusion processing on the multi-source asset data to generate a fusion data packet.

[0007] The digital image construction module constructs a dynamically coupled digital image based on the fused data package, including the coupling relationship between the physical environment and the business logic.

[0008] The deduction and analysis module is used to simulate the propagation process of a selected event in the digital accompanying image of the dynamic coupling relationship, calculate the cascading effect of the event, and thus generate the deduction results of the correlation effects.

[0009] The decision generation module is used to evaluate the expected repair efficiency and implementation risks of different operation and maintenance operation instructions based on the correlation impact inference results, and generate an operation and maintenance decision package that includes the preferred solution and at least one alternative solution.

[0010] A second aspect of the present invention provides a method for executing the data analysis-based IT asset management system, comprising: S1, acquiring multi-source asset data from offshore oil and gas platform information networks and production networks, and performing fusion processing on the multi-source asset data to generate a fusion data packet.

[0011] S2. Used to construct a dynamically coupled digital image based on the fused data package, including the coupling relationship between the physical environment and the coupling relationship between business logic.

[0012] S3. Simulate the propagation process of the selected event in the dynamic coupling relationship digital image, calculate the cascading effect of the event, and thus generate the correlation effect inference result.

[0013] S4. Based on the correlation effect deduction results, evaluate the expected repair efficiency and implementation risks of different operation and maintenance instructions, and generate an operation and maintenance decision package that includes the preferred solution and at least one alternative solution.

[0014] S5. After a certain scheme in the operation and maintenance decision package is executed, the parameters of the physical environment coupling relationship or the business logic coupling relationship in the dynamic coupling relationship digital image are calibrated.

[0015] The beneficial effects of this invention are as follows: By constructing a dynamic digital image that incorporates both physical environment and business logic, and simulating and extrapolating operational processes on it, this invention achieves a fundamental shift from passive, reactive operations to proactive, predictive risk management. This method can reveal and quantify implicit cascading risks arising from physical proximity or business dependencies, enabling the operations team to anticipate the potential chain reaction on the entire production system before performing any operation. This eliminates the vast majority of secondary failure risks at their inception without compromising actual production safety, thereby enhancing system stability and operational resilience.

[0016] This invention transforms complex and abstract system analysis into clear and intuitive decision-making criteria by quantitatively evaluating the repair effectiveness and implementation risks of the simulation results, thereby improving the scientific nature and quality of operation and maintenance decisions. The resulting operation and maintenance decision package, containing preferred and alternative solutions, provides on-site operation and maintenance personnel with a flexible operating guide that ensures they are informed of the risks. This changes the previous model of relying solely on personal experience for judgment, making the decision-making process more objective and reliable, and providing ample contingency plans to cope with complex and ever-changing on-site situations.

[0017] This invention introduces a closed-loop mechanism of execution feedback and model adaptive calibration, enabling the entire intelligent operation and maintenance system to possess continuous learning and self-optimization capabilities. It can continuously learn from actual operation and maintenance events, automatically correcting the parameters of the digital image model, thus enhancing its predictive ability over time and making it increasingly aligned with the actual operating conditions of specific platforms. This growth-oriented intelligence ensures the long-term effectiveness of the method, enabling the accumulation and inheritance of operation and maintenance knowledge, and providing sustainable technical support for ensuring the long-term, efficient, and safe operation of offshore oil and gas production systems. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the system structure connection of the present invention.

[0020] Figure 2 This is a schematic diagram of the implementation steps of the method of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Reference Figure 1 As shown, the first aspect of the present invention provides an IT asset management system based on data analysis, including: a data fusion module, used to acquire multi-source asset data in the information network and production network of offshore oil and gas platforms, and to perform fusion processing on the multi-source asset data to generate a fusion data packet.

[0023] As a preferred technical solution, the step of acquiring multi-source asset data in the information network and production network of offshore oil and gas platforms, and fusing the multi-source asset data to generate a fused data packet includes: collecting static configuration information, real-time operating status information and environmental perception information of assets in the information network and production network to form an original data set.

[0024] It should be noted that data is collected from IT devices in the information network, such as data servers and switches, and OT devices in the production network, such as PLC controllers and measurement and control terminals, through dedicated data acquisition terminals or software agents deployed on offshore oil and gas platforms. This process collects three types of information: first, static configuration information describing the fixed attributes of the equipment, such as equipment model, IP address, and software version; second, real-time operating status information reflecting the current workload of the equipment, such as CPU utilization, network traffic, and process status; and third, environmental awareness information describing the physical environment in which the equipment is located, such as temperature, humidity, and vibration data of the cabinet where the equipment is located.

[0025] The original dataset is timestamped and formatted to generate a standard data stream.

[0026] It should be noted that the diverse and varied static configuration information, real-time operational status information, and environmental perception information collected undergo preprocessing. This preprocessing first involves timestamp alignment, which uses a unified reference time to calibrate data from different devices and time points, ensuring the synchronicity of subsequent analyses and the accuracy of causal relationships. Then, format standardization is performed, converting all data into a predefined unified data structure. For example, all temperature data is standardized to degrees Celsius, and all configuration items are standardized to key-value pairs, thus forming a structured, directly processable raw data set.

[0027] Based on the unique identifier of the asset, data belonging to the same asset in the standard data stream are aggregated to generate the fused data packet.

[0028] It should be noted that the standard data stream undergoes in-depth processing based on a set of preset asset identification rules. These rules define how to uniquely identify an individual asset, for example, by combining the device's MAC address, serial number, or unique name in the asset management database. Using these rules, all data describing the same physical device or belonging to the same logical functional unit are filtered and associated in the original data set. These associated data are then aggregated into a complete, multi-dimensional information unit—the final fused data package. Each fused data package comprehensively depicts all aspects of an asset's information, from configuration and operation to its environment.

[0029] For example, if a server's MAC address is 00-1B-44-11-3A-B7, all CPU utilization, network traffic, and rack temperature data collected through this MAC address will be considered as associated data for that server. Similarly, if a PLC controller's serial number is SN20230510001, regardless of its installation location or IP address, as long as the serial number matches, all related measurement and control data and operational status data will be attributed to this controller. Likewise, if a platform names a data acquisition system "Drilling Data Acquisition Group-003," this name is unique in the asset management database, and all sensor and acquisition terminal data belonging to this acquisition group will be associated and aggregated through this name.

[0030] The digital image construction module constructs a dynamically coupled digital image based on the fused data package, including the coupling relationship between the physical environment and the business logic.

[0031] As a preferred technical solution, the step of constructing a dynamically coupled digital companion image based on the fused data packet, which includes the coupling relationship between the physical environment and the business logic, includes: extracting the identity attributes and status parameters of the asset from the fused data packet and creating an asset entity node.

[0032] It should be noted that identity attributes are fixed identification information of the asset, used to uniquely identify the asset, which is equivalent to the asset's ID card information. They come entirely from the static configuration information mentioned earlier, including device model, IP address, MAC address, serial number, etc. Status parameters are dynamic change information of the asset, used to reflect the asset's current working status and environmental conditions, which is equivalent to the asset's real-time health check data. They come from the latter two types of data mentioned earlier and are also key components of the fused data packet. They include real-time operating status parameters such as CPU utilization, network traffic, process status, etc., as well as environmental awareness status parameters such as temperature, humidity, and vibration data of the cabinet where the device is located.

[0033] Identify the asset entity nodes that have shared relationships in physical space or infrastructure, and establish the physical environment coupling relationship therebetween.

[0034] It should be noted that physical environment coupling relationships specifically include two types of physical associations: one is the spatial proximity relationship of assets, such as whether they are located in the same physical container; the other is the infrastructure sharing relationship of assets, such as whether they rely on the same power supply or cooling resources. The physical environment coupling edge will be accompanied by relevant environmental state parameters, such as the real-time temperature of the shared cabinet, so that the virtual model can reflect physical proximity and shared risks.

[0035] Identify the asset entity nodes that have dependencies in the business process or data flow, establish the business logic coupling relationship between them, and combine the asset entity nodes, the physical environment coupling relationship and the business logic coupling relationship to form the dynamic coupling relationship digital companion.

[0036] It should be noted that the identification of asset entity nodes that have dependencies in business processes or data flows relies on the role division of assets in production operations and two types of key dependencies: one is the collaborative dependency at the business process level, and the other is the supply and demand dependency at the data flow level. The business logic coupling edge will be subject to key performance constraints such as the upper limit of data transmission latency to match the actual business operation requirements.

[0037] It should also be noted that the asset entity nodes are virtual digital objects. Through the above, a one-to-one corresponding mirror image of the physical asset is created in virtual space. By establishing the coupling relationship between the physical environment and the business logic, a complete multi-layer network model is formed, which is the final dynamic coupling relationship digital mirror image. The dynamic coupling relationship digital mirror image is not only a digital list of assets, but also a computable high-fidelity virtual system that can dynamically reflect its operating status, physical dependencies, and business associations.

[0038] This invention elevates the cognitive depth of operations and maintenance (O&M) management from isolated asset states to a systematic, panoramic, and interconnected view by constructing a dynamic digital image of multiple coupling relationships. It moves beyond simply listing assets; instead, it creatively digitizes and models often-overlooked physical environmental dependencies and key business logic constraints, revealing hidden risk propagation paths that traditional methods cannot detect. This causal-rich model provides crucial, near-realistic system context for subsequent accurate fault prediction and risk simulation, enabling the prediction and analysis of complex system behavior. This fundamentally improves the predictability and accuracy of O&M decisions, laying a solid foundation for truly proactive and intelligent O&M.

[0039] As a preferred technical solution, the step of identifying the asset entity nodes that have a shared relationship in physical space or infrastructure, and establishing the physical environment coupling relationship therebetween, includes: obtaining an asset physical location topology map describing the physical deployment location of the assets and an infrastructure supply relationship table describing the service scope of the infrastructure.

[0040] Specifically, the asset physical location topology map describing the physical deployment location of the assets and the infrastructure supply relationship table describing the service scope of the infrastructure are retrieved from the knowledge base or configuration management database. The asset physical location topology map records a digital blueprint of the physical coordinates of each device, accurate to the location of the data center, cabinet or even rack where it is located. The infrastructure supply relationship table details the various critical infrastructures, such as power supply, cooling and critical networks, and which specific asset devices they serve.

[0041] Analyze the physical location topology of the assets to establish spatial sharing coupling relationships for asset entity nodes located in the same physical region.

[0042] Specifically, the process involves locating all asset entities marked within the same physical container in the asset physical location topology map. The specific analysis steps are as follows: ① Extract the unique identifier, physical location coordinates, physical container type, and associated infrastructure information of the assets in the topology map; ② Preset physical area judgment criteria based on independent enclosed spaces / functional zones, and clarify the boundary thresholds of the same area; ③ Filter out asset clusters with overlapping physical locations or belonging to the same physical container based on the judgment criteria; ④ Verify the physical correlation between assets and eliminate redundant assets; ⑤ Associate the environmental perception parameter types of the corresponding physical areas, and finally establish a spatial sharing coupling relationship between the entity nodes of the same asset cluster.

[0043] For example, servers and switches located in the same enclosed cabinet or the same process module, once found, establish a logical connection between their respective digital companion nodes, which is called a spatial shared coupling relationship, as shown in Table 1.

[0044] Table 1 - Examples of Spatial Sharing Coupling Relationships and Functions of Asset Entity Nodes

[0045] It should be noted that a digital mirror node is a digital mirror unit established for each asset entity node.

[0046] Analyze the infrastructure supply relationship table to establish facility sharing coupling relationships for asset entity nodes that share the same infrastructure, and combine the spatial sharing coupling relationship with the facility sharing coupling relationship to form the physical environment coupling relationship.

[0047] Specifically, the infrastructure supply relationship table is parsed, and asset entities sharing the same service source are identified by querying the infrastructure supply relationship table. The specific analysis steps are as follows: ① Extract elements such as infrastructure unique identifier, asset entity identifier, supply relationship type, and operating parameter threshold from the table; ② Preset a sharing judgment standard based on the consistency of infrastructure unique identifier and primary supply status; ③ Filter out asset clusters associated with the same infrastructure according to the standard; ④ Verify the legality of the supply relationship and the completeness of asset coverage; ⑤ Mark the operating parameter threshold of the shared infrastructure, and finally establish a facility sharing coupling relationship between entity nodes in the same asset cluster.

[0048] For example, all equipment groups connected to the same power supply circuit, cooled by the same cooling system, or exchanging data through the same communication backbone, and establishing another logical connection for all nodes within these equipment groups, namely facility sharing coupling relationship, as shown in Table 2.

[0049] Table 2 - Examples of Facility Sharing Coupling Relationships and Functions

[0050] This invention significantly enhances the fidelity of digital imagery models in simulating physical reality by specifically defining and constructing two coupling relationships: spatial sharing and facility sharing. It allows operational analysis to move beyond the logical level, enabling the identification and calculation of implicit common-cause risks arising from physical proximity or shared infrastructure. When a fire occurs in a certain area or a power line is interrupted, all affected equipment can be instantly and accurately deduced based on these established physical coupling relationships, rather than being checked one by one. This improves the accuracy of fault impact prediction and the efficiency of root cause analysis, providing solid technical support for preventing and responding to systemic and cascading failures caused by the physical environment.

[0051] As a preferred technical solution, the step of identifying the asset entity nodes that have dependencies in the business process or data flow, and establishing the business logic coupling relationship therebetween, includes: obtaining a production business process diagram that defines the production business functions and a data interface definition table that defines the data interaction interface.

[0052] Specifically, the production business process diagram depicts the logical blueprint of how each key link from oil and gas exploration to sales operates, defining each specific production business function, such as drilling operation optimization, and which sub-tasks and logical services constitute it. The data interface definition table records the rules for data exchange between different devices or software, clarifying which device generates what kind of data, and which device consumes this data.

[0053] Analyze the production business process diagram to establish business support coupling relationships for asset entity nodes that jointly support the same production business function.

[0054] Specifically, the process involves tracing each specific production business function, following the production business process flowchart, identifying all logical services that must be invoked to realize the specific production business function, and further locating the physical assets that carry these logical services. The specific analysis steps are as follows: ① Identify the target key production business functions, such as drilling operation optimization and crude oil export metering, from the production business process flowchart; ② Decompose the sub-tasks and corresponding logical services of the business function layer by layer; ③ Trace the physical asset carriers of each logical service and clarify the service-asset correspondence; ④ Verify whether the assets cover the entire business chain without redundancy or omissions; ⑤ Mark the collaboration dependency order between assets, and finally identify all asset entity nodes that carry the business logic service as an asset cluster that jointly supports the business, and establish business support coupling relationships among them.

[0055] For example, in drilling operation optimization, the real-time data analysis service and control command issuance service that it depends on are identified, and it is finally determined which server and which engineer station they run on. Then, a relationship is established among the digital image nodes of all these identified physical assets, which is called business support coupling relationship, indicating that they jointly serve the same business goal, as shown in Table 3.

[0056] Table 3 - Examples of Business Support Coupling Relationships and Functions

[0057] Analyze the data interface definition table to establish data flow coupling relationships for asset entity nodes with data production and consumption relationships, and combine the business support coupling relationship with the data flow coupling relationship to form the business logic coupling relationship.

[0058] Specifically, the process involves searching the data production and consumption entries in the data interface definition table to identify asset entity pairs with direct data exchange relationships. The specific analysis steps are as follows: ① Extract key elements from the data interface definition table, such as producer identifier, consumer identifier, data type, transmission protocol, and performance constraints; ② Traverse the interface records and filter out asset entity pairs with direct data exchange relationships; ③ Verify the legality of the data flow direction and the matching degree of the data type of the entity pairs; ④ Mark the flow direction of the data flow and the corresponding performance constraint parameters; ⑤ Associate with key business scenarios of the platform to verify the integrity of key data links, and finally establish a directed data flow coupling relationship between each pair of data producer-consumer asset entity nodes.

[0059] For example, an underwater pressure sensor acts as a data producer, while a data acquisition server acts as a consumer. A directed connection, or data flow coupling, is established between the digital companion nodes of these two asset entities, clearly indicating the direction of data flow. See Table 4 for specific examples.

[0060] Table 4 - Examples of Business Support Coupling Relationships and Functions

[0061] This invention successfully elevates the operational perspective from isolated equipment management to a strategic level of business process assurance by constructing two coupling relationships: business support and data flow. It transforms digital imaging from merely a collection of hardware into a business-aware system capable of deeply understanding its position and role within the entire production value chain. When a production metric becomes abnormal, these business coupling relationships allow for rapid focus on the complete asset cluster and critical data links supporting that business, shortening troubleshooting time. Similarly, before making changes, it can accurately assess which specific business processes and data flows will be affected, thus achieving a leap from focusing on equipment health to ensuring business continuity, providing operational insights and foresight for operational decisions.

[0062] The deduction and analysis module is used to simulate the propagation process of a selected event in the digital accompanying image of the dynamic coupling relationship, calculate the cascading effect of the event, and thus generate the deduction results of the correlation effects.

[0063] As a preferred technical solution, the step of simulating the propagation process of a selected event in the dynamic coupling digital image, calculating the cascading effect of the event, and generating the correlation influence deduction result includes: identifying the initial influence source as the starting point of the simulation from the dynamic coupling digital image or externally input operation and maintenance instructions.

[0064] It should be noted that, in order to simulate and extrapolate potential anomalies or operational operations and generate correlation impact projection results, a series of calculations and analyses are performed on the constructed dynamic coupling relationship digital image. First, all nodes in the dynamic coupling relationship digital image are continuously monitored, or external operational instructions are received, to identify starting nodes that meet preset triggering conditions. Triggering conditions specifically refer to the conditions that trigger selected events. Selected events are potential anomalies or planned operational operations included in the simulation to predict impacts in advance, and may have a correlation impact on the IT / OT assets and production operations of offshore oil and gas platforms. These are divided into two categories: one is when equipment status parameters meet anomaly threshold conditions, such as CPU utilization or equipment temperature continuously exceeding the normal range; the other is when preset operational instructions are received, such as server restart or equipment parameter configuration adjustment instructions.

[0065] Driven by the initial source of influence, state propagation simulation is performed along the path defined by the physical environment coupling relationship and the business logic coupling relationship.

[0066] During the state propagation simulation, the state deviation of each affected node is calculated, and the correlation impact deduction result, which includes the impact chain and business impact assessment, is generated based on the state deviation.

[0067] It should be noted that the state deviation is the difference between its simulated state and the normal reference state.

[0068] Specifically, driven by the initial source of influence, state propagation simulation is performed along the path defined by the physical environment coupling relationship and the business logic coupling relationship; specifically, the following steps are included: 1. Initialize propagation parameters: take the state parameters of the initial source of influence as the initial input, and set the propagation trigger threshold, attenuation coefficient and termination condition.

[0069] 2. Matching coupling paths: Filter out the physical environment coupling paths (i.e., space sharing / facility sharing coupling edges) and the business logic coupling paths (i.e., business support / data flow coupling edges).

[0070] 3. Node-by-node state iterative calculation: Update the state of downstream digital shadow nodes sequentially according to path priority, and record the state change value and the source of the impact.

[0071] 4. Output propagation results: Generate a state propagation topology graph, and mark the range of affected nodes, state deviation, and influence chain.

[0072] The key rules for state propagation simulation include: using the real-time state parameters of the initial impact source as the initial input, propagating along the coupling path according to a preset time step, such as 100ms for data flow scenarios and 5s for environmental scenarios; setting propagation trigger thresholds, such as temperature > 40℃ for 30s, attenuation coefficients, such as physical environment path attenuation > business logic path attenuation, and termination conditions, such as stopping when the impact degree is < 5%; iteratively calculating state changes node by node according to path priority, such as level 1 data flow, level 2 facility sharing, etc., and finally outputting the range of affected nodes, state deviation, and impact chain to achieve dynamic risk prediction.

[0073] For example, if the initial impact source is server overheating, the simulation will increase the ambient temperature parameters of other nodes in the same rack along the physical environment coupling edge; if the initial impact source is database service interruption, the simulation will change the state of data analysis applications that depend on this service along the business logic coupling edge.

[0074] It should also be noted that the correlation impact deduction result, which includes the impact chain and business impact assessment, is generated based on the state deviation. Specifically, it involves continuously determining whether the state deviation of each affected node triggers a threshold alarm for its associated performance constraint indicator or environmental state parameter. For example, it determines whether the simulated response time of a service exceeds the latency limit defined on its business logic coupling edge. Finally, it summarizes the state deviation of all affected nodes and all triggered threshold alarms throughout the simulation process, records the path of the impact propagating from the starting node to the final node, forming the impact chain path, and combines this with the assessment of the actual impact on production by the affected business nodes (i.e., the business impact assessment). All this information is then encapsulated to generate the final correlation impact deduction result.

[0075] Based on the state deviation, a correlation impact projection result containing the impact chain and business impact assessment is generated, specifically including: ① binding each affected node to its supported key production business functions; ② determining the severity of the impact, such as severe / moderate / minor, based on the state deviation and threshold alarm type; ③ tracing the affected business links along the impact chain to determine whether key business main processes are affected; ④ adjusting the weighted level based on business priority, such as security > production > auxiliary; ⑤ summarizing the names, impact levels, and specific impact manifestations of all affected businesses, and encapsulating them together with the impact chain, state deviation, and threshold alarm records into a correlation impact projection result. For example, if a drilling data analysis server triggers a computational latency threshold alarm due to 92% CPU utilization, the associated drilling operation optimization business is classified as severely affected, manifesting as delayed command issuance. This assessment result is output along with the impact chain from sensors to actuators. The severity of the impact is determined as follows: if the deviation is >20% and a safety threshold alarm is triggered, such as SIS system pressure exceeding the limit, the business impact level is severe; if the deviation is 10% < and the deviation is ≤20% and a performance threshold alarm is triggered, such as data transmission latency exceeding the limit, the level is moderate; if the deviation is ≤10% or there is no alarm, the level is minor.

[0076] As a preferred technical solution, the step of calculating the state deviation of each affected node includes: obtaining the baseline state value of the affected node before the state propagation simulation begins.

[0077] Obtain the current simulation state value of the affected node during the state propagation simulation process.

[0078] The state deviation is obtained by calculating the baseline state value and the current simulated state value using a quantization function.

[0079] For example, the quantization function calculates the percentage change or standard deviation multiple for numerical parameters such as temperature or CPU utilization, while for status parameters such as whether a device is online or offline, it determines the status difference. For instance, if the statuses are the same, the status deviation is recorded as 0; otherwise, it is recorded as 1. The final output of the quantization function is the status deviation, which accurately quantifies the degree of change in the node's status. This step, by transforming the abstract state changes in the simulation into concrete, measurable status deviation values, provides an objective basis for evaluation throughout the entire simulation and analysis process.

[0080] This invention achieves a fundamental shift in operational decision-making from reactive response to proactive prediction by simulating state changes in digital imaging. Instead of waiting for failures to occur and then analyzing logs, it pre-simulates, in a virtual environment, the complete cascading failure chain that a single event might trigger, spanning both IT and OT systems. This simulation capability allows operations personnel to anticipate the potential consequences of operations, accurately identify systemic risks that are difficult to detect due to complex coupling relationships, and thus formulate the most effective avoidance or response strategies before problems occur. The final simulation results, containing clear impact chain paths and business impact assessments, provide decision-makers with unprecedented insights, enhancing the stability and security of complex production systems in the face of uncertainty.

[0081] By constructing a dynamic digital image that incorporates both physical environment and business logic, and simulating operational processes on it, a fundamental shift from reactive, responsive operations to proactive, predictive risk management has been achieved. This method reveals and quantifies implicit cascading risks arising from physical proximity or business dependencies, enabling operations teams to anticipate the potential chain reactions on the entire production system before performing any operation. This allows for the elimination of most secondary failure risks at their inception without compromising actual production safety, thereby enhancing system stability and operational resilience.

[0082] The decision generation module is used to evaluate the expected repair efficiency and implementation risks of different operation and maintenance operation instructions based on the correlation impact inference results, and generate an operation and maintenance decision package that includes the preferred solution and at least one alternative solution.

[0083] As a preferred technical solution, the step of evaluating the expected repair efficiency and implementation risk of different operation and maintenance operation instructions based on the correlation impact deduction results, and generating an operation and maintenance decision package containing the preferred solution and at least one alternative solution, includes: calculating the expected repair efficiency score for different operation and maintenance operation instructions based on the business impact assessment in the correlation impact deduction results.

[0084] It should be noted that, following the example above, the indicators for business impact assessment include the business impact level (severe, moderate, or minor), the scope of impact (i.e., key business processes and auxiliary business links), and the business priority (i.e., security > production > auxiliary). First, a base score is assigned according to the business impact level. Then, the business priority weight is determined based on the business priority. Finally, a correction coefficient is applied based on the scope of impact. The final score equals the base score * business priority weight * correction coefficient for the scope of impact, yielding the final expected repair effectiveness score. For example, a severe impact level is assigned 80 points, a moderate impact level 15 points, and a minor impact level 5 points. The priority weight for security-related businesses is 1.5, for production-related businesses 1.2, and for auxiliary businesses × 1.0. The correction coefficient for impacting key business processes is 1.3, and for impacting only auxiliary businesses, it is 0.8.

[0085] For example, a certain operation and maintenance operation has a serious impact on security-critical business, with a base score of 80 points, a business priority weight of 1.5, and an impact scope correction coefficient of 1.3. The final score is 80 × 1.5 × 1.3 = 156 points, and its expected repair efficiency is higher than that of an operation that has a general impact on auxiliary business.

[0086] Based on the impact chain in the correlation impact deduction results, the expected implementation risk score is calculated for the different operation and maintenance instructions.

[0087] It should be noted that, based on the impact chain in the aforementioned correlation impact simulation results, the number of affected nodes, the type of affected nodes, and the business priority involved in the impact chain are obtained. These indicators are then converted into numerical values. A base score is assigned based on the number of affected nodes. Then, the node importance weight is determined by the type of affected node. Next, the risk diffusion correction coefficient is determined by the business priority involved in the impact chain. The final score is equal to the base score * node importance weight * risk diffusion correction coefficient. For example, if the affected nodes include safety equipment such as SIS controllers, emergency shut-off valves, or critical business equipment such as central control servers and drilling controllers, the node importance weight is 1.4; if they only include ordinary equipment such as auxiliary monitoring terminals, the node importance weight is 0.7; if the impact chain touches on the critical main business process, the risk diffusion correction coefficient is 1.2; if it only involves auxiliary business links, the risk diffusion correction coefficient is 0.9.

[0088] By combining the expected repair performance score and the expected implementation risk score, the preferred solution and the at least one alternative solution are determined, and together they constitute the operation and maintenance decision package.

[0089] It should be noted that different operation and maintenance (O&M) operation instructions are sorted in descending order according to their expected repair effectiveness scores to obtain a first sorting table. Then, they are sorted in ascending order according to their expected implementation risk scores to obtain a second sorting table. From the first sorting table, O&M operation instructions ranked in the first constraint ratio are selected to form a first instruction set. From the second sorting table, O&M operation instructions ranked in the second constraint ratio are selected to form a second instruction set. O&M operation instructions that exist in both the first and second instruction sets are recorded as candidate O&M operation instructions. These candidate O&M operation instructions are then sorted in descending order according to the ratio of their expected repair effectiveness score to their expected implementation risk score. The candidate O&M operation instruction ranked first is selected as the preferred solution, and the candidate O&M operation instruction ranked second is selected as an alternative solution.

[0090] This invention transforms complex simulation data into clear and comparable decision-making criteria by quantitatively evaluating the effectiveness and risk of the simulation results from two dimensions, thereby changing the traditional model of operation and maintenance decision-making that relies on personal experience. Operation and maintenance personnel no longer blindly choose solutions but can scientifically weigh the pros and cons of different operations before taking action, intuitively seeing the expected effects of each solution and its accompanying potential risks. The resulting operation and maintenance decision package, containing preferred and alternative solutions, provides operational flexibility and safety redundancy to cope with complex and ever-changing field situations. It ensures that even if the preferred solution cannot be implemented, there are proven and reliable contingency plans available, thus improving the quality of operation and maintenance decisions and the operational resilience of the entire production system.

[0091] This invention transforms complex and abstract system analysis into clear and intuitive decision-making criteria by quantitatively evaluating the repair effectiveness and implementation risks of the simulation results, thereby improving the scientific nature and quality of operation and maintenance decisions. The resulting operation and maintenance decision package, containing preferred and alternative solutions, provides on-site operation and maintenance personnel with a flexible operating guide that ensures they are informed of the risks. This changes the previous model of relying solely on personal experience for judgment, making the decision-making process more objective and reliable, and providing ample contingency plans to cope with complex and ever-changing on-site situations.

[0092] As a preferred technical solution, it also includes a dynamic coupling relationship digital image calibration module, the specific content of which is: after a certain scheme in the operation and maintenance decision package is executed, the operation data of the scheme in the actual production system is collected, and actual system feedback data is generated.

[0093] It should be noted that the actual system feedback data includes the real changes in the performance, status, and environmental parameters of the operated device and its associated devices over a period of time after execution.

[0094] The actual system feedback data is compared with the correlation impact inference results on which the scheme was based to generate model deviation data.

[0095] It should be noted that the actual system feedback data is compared with the correlation impact projection results used to generate the solution. Specifically, the comparison process involves checking the differences between the simulated predictions and the actual results item by item. For example, the projection predicted a service recovery time of five minutes, while the actual recovery time was seven minutes; or the projection predicted a network traffic peak of 100 Mbps, while the actual peak reached 120 Mbps. All these quantitative differences between predictions and reality are collected and recorded by the system, forming structured model bias data.

[0096] The parameters of the physical environment coupling relationship or the business logic coupling relationship in the dynamic coupling relationship digital image are calibrated using the model deviation data.

[0097] Specifically, the coupling parameters that need to be calibrated are determined based on the mapping table between deviation data and coupling parameters. For example, a deviation of >15% corresponds to the calibration of the propagation attenuation coefficient, and a delay exceeding the tolerance corresponds to the calibration of the upper limit of the data flow coupling edge delay. The mapping table between deviation data and coupling parameters is established in advance and determined based on the causal relationship between the characteristics of offshore oil and gas platform assets, the causes of deviations, and coupling parameters. Specifically, it is determined through a standardized mapping relationship preset by historical operation and maintenance data and business logic. This mapping table only needs to clarify the correspondence between deviation types and corresponding coupling parameters to be calibrated, without the need for additional complex configuration. Its specific detailed rules can be adjusted according to the actual operating conditions of the platform, which will not be detailed here.

[0098] The parameters are adjusted iteratively according to preset rules: if the deviation Δ > 10%, it is corrected by Δ × 0.8; if 5% ≤ Δ ≤ 10%, it is corrected by Δ × 0.5; and if Δ < 5%, no adjustment is made.

[0099] Re-enter the calibrated parameters into the digital imaging simulation until the deviation value is less than 5%, which is the convergence threshold. At this point, the calibration is complete.

[0100] For example, the simulated propagation attenuation coefficient of a shared coupling edge of a certain facility is 10%, while the actual propagation attenuation coefficient calculated from actual operation and maintenance data is 12%, with a deviation Δ=16.7%. After correction according to the rules, the propagation attenuation coefficient is 11.6%, and after resimulation, the deviation is reduced to 3.3%, which meets the convergence requirements.

[0101] This invention introduces a closed-loop mechanism of execution feedback and model adaptive calibration, enabling the entire intelligent operation and maintenance system to possess continuous learning and self-optimization capabilities. It can continuously learn from actual operation and maintenance events, automatically correcting the parameters of the digital image model, thus enhancing its predictive ability over time and making it increasingly aligned with the actual operating conditions of specific platforms. This growth-oriented intelligence ensures the long-term effectiveness of the method, enabling the accumulation and inheritance of operation and maintenance knowledge, and providing sustainable technical support for ensuring the long-term, efficient, and safe operation of offshore oil and gas production systems.

[0102] The technical principle of this invention lies in breaking down the data barriers between information technology and operational technology, integrating the dispersed IT and OT asset data of offshore oil and gas platforms to form a comprehensive data foundation. Its key innovation is that it doesn't simply analyze this data, but rather, based on this integrated data and deeply combining pre-defined physical environment dependency rules and business logic constraint rules, constructs a digital mirror that dynamically reflects the complex coupling relationships in the real world, such as physical adjacency between devices, facility sharing, and mutual support of business processes. This digital mirror is not a static asset list, but a computable and predictable high-fidelity virtual system. Based on this, this method simulates and extrapolates all potential risk events or planned operational operations in this virtual system before they occur in the real world, predicting their cascading impact on the entire production system by calculating their chain reactions. Finally, the predictive extrapolation results are transformed into a quantitative assessment of the risks and effectiveness of different operational solutions, thereby generating a decision set containing multiple validated optimization solutions.

[0103] Implementing this invention yields significant technical benefits. The most crucial advantage lies in its ability to proactively mitigate and eliminate operational risks through virtual simulations and verifications. This fundamentally prevents secondary failures and production interruptions caused by improper operation or insufficient consideration in real, high-risk production environments, greatly enhancing system security and production continuity. Furthermore, this method enables operations personnel to gain a deep, holistic understanding of the implicit connections between assets formed by physical and business logic, shifting from passively responding to alarms to proactively predicting and mitigating systemic risks. The resulting decision package, containing multiple alternatives, provides the operations team with scientific and quantitative decision-making support and flexible response strategies, enabling them to make more confident optimal choices when facing complex problems, thereby significantly improving overall operational efficiency and asset management.

[0104] Reference Figure 2 As shown, a second aspect of the present invention provides a method for executing the data analysis-based IT asset management system, comprising: S1, acquiring multi-source asset data from offshore oil and gas platform information networks and production networks, and performing fusion processing on the multi-source asset data to generate a fusion data packet.

[0105] S2. Used to construct a dynamically coupled digital image based on the fused data package, including the coupling relationship between the physical environment and the coupling relationship between business logic.

[0106] S3. Simulate the propagation process of the selected event in the dynamic coupling relationship digital image, calculate the cascading effect of the event, and thus generate the correlation effect inference result.

[0107] S4. Based on the correlation effect deduction results, evaluate the expected repair efficiency and implementation risks of different operation and maintenance instructions, and generate an operation and maintenance decision package that includes the preferred solution and at least one alternative solution.

[0108] S5. After a certain scheme in the operation and maintenance decision package is executed, the parameters of the physical environment coupling relationship or the business logic coupling relationship in the dynamic coupling relationship digital image are calibrated.

[0109] It should be added that the formulas mentioned above, through the principle of dimensional consistency and mathematical standardization methods such as normalization, dimensionless parameter conversion, or unit system unification, can translate physical quantities with different properties into unitless standard values ​​or parameters that can be superimposed in the same dimension. This eliminates the interference of different dimensions on the computational logic, allowing the formulas to retain the original data distribution characteristics while possessing mathematical rationality and adaptability to objective laws. The above descriptions are merely exemplary embodiments of the present invention and should not be construed as limiting the scope of the invention.

[0110] It should also be noted that the various preset thresholds described in this invention are based on historical operating data of offshore oil and gas platform equipment, failure cases, and a large number of experimental test results, combined with the experience of experts in the field, and determined by comprehensively considering the actual operating environment of the equipment, the design life and performance indicators of key components. They have a solid scientific basis and are practically operable. The preset thresholds specified in the specification, such as state deviation deviation > 15% and delay exceeding tolerance, are only exemplary presets for adapting to the scenario. They can be adjusted according to the actual operating conditions of the platform. The relevant detailed rules are mature in existing technologies and will not be elaborated here.

[0111] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0113] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

[0114] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. An IT asset management system based on data analysis, characterized in that, include: The data fusion module is used to acquire multi-source asset data from the information network and production network of offshore oil and gas platforms, and to fuse the multi-source asset data to generate a fused data packet. The digital image construction module constructs a dynamically coupled digital image based on the fused data package, including the coupling relationship between the physical environment and the coupling relationship between business logic. The step of constructing a dynamically coupled digital companion image based on the fused data packet, including the coupling relationship between the physical environment and the business logic, includes: Extract the asset's identity attributes and status parameters from the fused data packet to create an asset entity node; Identify the asset entity nodes that have shared relationships in physical space or infrastructure, and establish the physical environment coupling relationship therebetween; Identify the asset entity nodes that have dependencies in business processes or data flows, establish the business logic coupling relationship between them, and combine the asset entity nodes, the physical environment coupling relationship and the business logic coupling relationship to form the dynamic coupling relationship digital image; The step of identifying asset entity nodes that have shared relationships in physical space or infrastructure, and establishing the physical environment coupling relationship therebetween, includes: Obtain the asset physical location topology map describing the physical deployment location of the assets and the infrastructure supply relationship table describing the service scope of the infrastructure; Analyze the physical location topology of the assets to establish spatial sharing coupling relationships for asset entity nodes located in the same physical region; Analyze the infrastructure supply relationship table to establish facility sharing coupling relationships for asset entity nodes that share the same infrastructure, and combine the spatial sharing coupling relationship with the facility sharing coupling relationship to form the physical environment coupling relationship; The step of identifying the asset entity nodes that have dependencies in the business process or data flow, and establishing the business logic coupling relationship therebetween, includes: Obtain the production business process diagram that defines the components of the production business functions and the data interface definition table that defines the data interaction interfaces; Analyze the aforementioned production business process diagram to establish business support coupling relationships for asset entity nodes that jointly support the same production business function; Analyze the data interface definition table to establish data flow coupling relationships for asset entity nodes with data production and consumption relationships, and combine the business support coupling relationship with the data flow coupling relationship to form the business logic coupling relationship; The simulation and analysis module is used to simulate the propagation process of a selected event in the digital accompanying image of the dynamic coupling relationship, calculate the cascading effect of the event, and thus generate the simulation results of the correlation effects. The step of simulating the propagation process of a selected event in the dynamically coupled digital image, calculating the cascading effects of the event, and generating the inference results of the associated effects includes: Identify the initial influence source as the starting point of the simulation from the digital accompanying image of the dynamic coupling relationship or the operation and maintenance instructions input externally; Driven by the initial source of influence, state propagation simulation is performed along the path defined by the physical environment coupling relationship and the business logic coupling relationship; During the state propagation simulation, the state deviation of each affected node is calculated, and the correlation impact deduction result, which includes the impact chain and business impact assessment, is generated based on the state deviation. The decision generation module is used to evaluate the expected repair efficiency and implementation risks of different operation and maintenance operation instructions based on the correlation impact inference results, and generate an operation and maintenance decision package that includes the preferred solution and at least one alternative solution.

2. The IT asset management system based on data analysis according to claim 1, characterized in that, The step of acquiring multi-source asset data from the offshore oil and gas platform information network and production network, and fusing the multi-source asset data to generate a fused data packet, includes: Collect static configuration information, real-time operating status information, and environmental perception information of assets in information networks and production networks to form a raw data set; The original dataset is timestamped and formatted to generate a standard data stream; Based on the unique identifier of the asset, data belonging to the same asset in the standard data stream are aggregated to generate the fused data packet.

3. The IT asset management system based on data analysis according to claim 1, characterized in that, It also includes a dynamic coupling relationship digital image calibration module, the specific contents of which are as follows: After a certain scheme in the operation and maintenance decision package is executed, the operation data of the scheme in the actual production system is collected to generate actual system feedback data; The actual system feedback data is compared with the correlation impact inference results on which the scheme was based to generate model deviation data. The parameters of the physical environment coupling relationship or the business logic coupling relationship in the dynamic coupling relationship digital image are calibrated using the model deviation data.

4. The IT asset management system based on data analysis according to claim 1, characterized in that, The step of calculating the state deviation of each affected node includes: Obtain the baseline state value of the affected node before the state propagation simulation begins; Obtain the current simulation state value of the affected node during the state propagation simulation process; The state deviation is obtained by calculating the baseline state value and the current simulated state value using a quantization function.

5. The IT asset management system based on data analysis according to claim 1, characterized in that, The step of evaluating the expected repair effectiveness and implementation risks of different operation and maintenance instructions based on the correlation impact deduction results, and generating an operation and maintenance decision package containing the preferred solution and at least one alternative solution, includes: Based on the business impact assessment in the aforementioned correlation impact deduction results, calculate the expected repair efficiency score for different operation and maintenance instructions; Based on the impact chain in the correlation impact deduction results, calculate the expected implementation risk score for the different operation and maintenance instructions; By combining the expected repair performance score and the expected implementation risk score, the preferred solution and the at least one alternative solution are determined, and together they constitute the operation and maintenance decision package.

6. A method for executing the data analysis-based IT asset management system according to any one of claims 1-5, characterized in that, include: S1. Acquire multi-source asset data from the information network and production network of offshore oil and gas platforms, and perform fusion processing on the multi-source asset data to generate a fusion data packet; S2. Used to construct a dynamically coupled digital image based on the fused data packet, including the coupling relationship between the physical environment and the coupling relationship between business logic; S3. Simulate the propagation process of the selected event in the digital accompanying image of the dynamic coupling relationship, calculate the cascading effect of the event, and thus generate the correlation effect inference results; S4. Based on the correlation impact deduction results, evaluate the expected repair efficiency and implementation risks of different operation and maintenance operation instructions, and generate an operation and maintenance decision package that includes the preferred solution and at least one alternative solution. S5. After a certain scheme in the operation and maintenance decision package is executed, the parameters of the physical environment coupling relationship or the business logic coupling relationship in the dynamic coupling relationship digital image are calibrated.

Images