A system risk monitoring method, device, computer equipment, and medium

Abstract

This invention discloses a system risk monitoring method, device, computer equipment, and medium. It constructs a risk characteristic database covering the entire lifecycle of ship equipment development, collects data from existing ship projects, defines six primary risks and their subordinate secondary risks, and sets scoring criteria to map the risk characteristics of existing projects into vectors and store them in association. It extracts information from projects to be reviewed, calculates the dynamic risk index of each secondary risk category of the project using a dynamic risk index model, and classifies the risk level. It establishes target risk characteristic vectors based on the ship type and development stage of the project to be reviewed. It calculates the cosine similarity between the target risk characteristic vector and the risk characteristic vectors of all existing ship projects in the full lifecycle risk characteristic database, clusters similar project groups, statistically analyzes risk data to generate prompt statements, and establishes a risk response plan library to select an initial plan and determine the execution plan.

Description

Technical Field

[0001] This invention belongs to the field of project risk management technology and relates to a system risk monitoring method, device, computer equipment and medium. Background Technology

[0002] In the field of ship equipment development, ship projects are typically characterized by long cycles, high technical complexity, large resource investment, and strong external dependence. The development process of such projects needs to go through the planning stage, engineering development stage, testing and verification stage, and delivery assurance stage. Each stage may face various risks, and the effectiveness of risk management directly affects whether the project can proceed as planned and whether it can achieve the expected technical indicators and economic benefits.

[0003] Currently, the risk management methods employed by shipbuilding companies during project development have many limitations. In the risk identification phase, traditional methods often rely on the past experience of staff to list risk sources, failing to construct a systematic risk identification framework that considers the full lifecycle characteristics of ship equipment development. This approach often results in incomplete risk coverage, particularly overlooking risks unique to the shipbuilding industry, such as the impact of maritime regulation updates on equipment compliance, equipment adaptability risks under different sea conditions, and stability risks during the localization of key components. This creates blind spots in subsequent risk management.

[0004] In the risk quantification phase, existing technologies mostly calculate the risk index by simply multiplying the probability of risk occurrence by the severity of its consequences. This static quantification method does not consider the coupling of risk factors in shipbuilding projects, nor does it reflect the differences in the degree of risk impact at different development stages. This leads to a significant deviation between the quantification results and the actual risk situation of shipbuilding projects, making it difficult to accurately reflect the true impact of risks. For example, immature power system technology may simultaneously lead to technical failures, schedule delays, and cost overruns. Furthermore, design flaws discovered during the testing and verification phase have a far greater impact on the project than those discovered during the design phase.

[0005] In the risk prediction stage, current risk management is mostly based on qualitative summaries of historical projects, lacking a dedicated risk characteristic database for the shipping industry. This makes it impossible to effectively predict the potential risks of new projects through data mining techniques. For shipping projects with similar historical versions, it is difficult to accurately correlate historical risk data; for entirely new types of shipping projects, there is a lack of effective risk prediction basis, relying solely on subjective human judgment, resulting in low accuracy and reliability of risk prediction.

[0006] In the risk management phase, existing technologies often offer only general suggestions, failing to design specific solutions tailored to the development process and technical characteristics of ship equipment. This results in poor operability of the measures, making it difficult to effectively control risks and potentially leading to project delays, cost overruns, and even impacting the delivery quality and performance of the equipment. For example, regarding sea state adaptability risks, only general recommendations to strengthen testing are made, without specifying the specific types of tests, simulated sea state parameters, or test sequence; regarding supply chain risks, alternative solutions are not developed based on the supply cycles and domestic production status of key ship components.

[0007] In summary, existing risk management methods for ship development can no longer meet the needs of ship equipment manufacturing projects for precise risk control. There is an urgent need for a risk management technology that can achieve full-cycle risk identification, precise quantification, data-driven prediction, and targeted responses to improve the risk control capabilities of ship development and ensure the smooth progress of projects. Summary of the Invention

[0008] To address the problems existing in the background art, the present invention proposes a system risk monitoring method, device, computer equipment, and medium.

[0009] The first aspect of this application provides a system risk monitoring method, including:

[0010] Construct a risk characteristic database for the entire lifecycle of ship equipment development: collect data on existing ship projects, define the categories and specific characteristics of six primary risks (including technology, schedule, cost, compliance, supply chain, and operation and maintenance support) and their subordinate secondary risks, and set up scoring criteria to map the risk characteristics of existing projects into vectors and store them in association;

[0011] The dynamic risk index model calculates the dynamic risk index of each secondary risk category of the ship project under review and classifies the risk level.

[0012] Based on the ship type and development stage of the ship project to be reviewed, a target risk feature vector is established; the cosine similarity between the target risk feature vector and the risk feature vectors of all existing ship projects in the full life cycle risk feature database of ship equipment development is calculated, similar project groups are clustered, and statistical risk data is used to generate prompt statements to determine the risk category;

[0013] Establish a risk response plan library, select an initial plan, formulate an implementation plan, and periodically review and adjust the plan.

[0014] Optionally, the process of calculating the index by the dynamic risk index model is as follows: ,in, This is a dynamic risk index. Rate the probability. For severity scoring, β is the coupling coefficient, and β is the stage influence coefficient.

[0015] Optionally, the secondary risks under the technical risks of the primary risk include: system compatibility risk, domestic substitution risk, and sea state adaptability risk; the specific characteristics of system compatibility risk include the data interaction delay between the navigation system and the communication system, and the matching degree between the power system and the propulsion system.

[0016] Optionally, a target risk characteristic vector can be established based on the ship type and development stage of the ship project to be reviewed, specifically including:

[0017] If there are similar historical versions of ship projects for the ship project to be reviewed, the risk feature vector of the latest version of such ship projects in the full life cycle risk feature database of ship equipment development will be extracted as the target risk feature vector.

[0018] If there is no similar historical version of the ship project to be reviewed but there are similar ship projects, then extract all risk feature vectors of the same type of ship at the same development stage from the full life cycle risk feature database of ship equipment development, calculate the average value of the corresponding elements of each vector, and form the target risk feature vector.

[0019] If the ship project to be reviewed is a completely new type of ship project, then ship experts will be organized to score the risk characteristics of each secondary risk category, and a target risk characteristic vector will be constructed based on the scoring results.

[0020] Optionally, the cosine similarity is calculated as follows:

[0021] ;

[0022] in, This represents the target risk feature vector of the ship project to be reviewed; This represents the risk feature vector of any existing shipbuilding project in the database. This represents the i-th element of the target risk feature vector; Represents the risk feature vector of existing shipbuilding projects The i-th element, where n represents the number of elements in the risk feature vector; () indicates the similarity of project risk characteristics.

[0023] Optionally, a risk response plan library is established. When establishing the risk response plan library, each risk response plan includes implementation steps and implementation effect verification indicators. The risk status of the ship projects under review is reassessed quarterly. When adjusting the risk response plan based on the assessment results, if the risk level decreases by more than or equal to 30%, the original risk response plan is maintained; if the risk level increases or decreases by less than 10%, the implementation steps or resource allocation of the risk response plan are adjusted.

[0024] Optionally, the data entered after the project is completed includes: the actual risk category, the time of occurrence, the scope of impact, the amount of loss, and the actual implementation steps, time, and effect of the response plan.

[0025] A second aspect of this application provides a device risk monitoring device, comprising:

[0026] The data construction unit is used to build a risk characteristic database for the entire life cycle of ship equipment development, collect data on existing ship projects, define the categories and exclusive characteristics of six primary risks including technology, schedule, cost, compliance, supply chain, and operation and maintenance support, as well as their subordinate secondary risks, and set scoring criteria to map the risk characteristics of existing projects into vectors and store them in association.

[0027] The risk quantification unit is used to extract information about the project to be reviewed, calculate the dynamic risk index of each secondary risk category of the ship project to be reviewed using the dynamic risk index model, and classify the risk level.

[0028] The risk prediction unit is used to establish a target risk feature vector based on the ship type and development stage of the ship project to be reviewed; calculate the cosine similarity between the target risk feature vector and the risk feature vectors of all existing ship projects in the full life cycle risk feature database of ship equipment development, cluster similar project groups, and generate prompt statements based on statistical risk data.

[0029] The risk response unit is used to establish a risk response plan library, select an initial plan, formulate an implementation plan, and periodically review and adjust the plan.

[0030] A third aspect of this application is a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executed, implements the aforementioned system risk monitoring method.

[0031] A fourth aspect of this application provides a computer-readable medium storing a computer program that, when executed by a processor, implements the above-described system risk monitoring method.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] This invention provides a system risk monitoring method, device, computer equipment, and medium, which effectively solves the problems of fragmented risk identification, strong subjectivity in quantification, lack of data support for prediction, and insufficient targeted solutions in existing ship project risk management. It has significant technical advantages and practical value. Attached Figure Description

[0034] Figure 1 This is a flowchart of a system risk monitoring method according to an embodiment of the present invention;

[0035] Figure 2 This is a schematic diagram of a system risk monitoring device according to an embodiment of the present invention;

[0036] Figure 3 This is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0037] 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.

[0038] In one embodiment, such as Figure 1 As shown, a system risk monitoring method is provided, which is then applied to... Figure 1 Taking China as an example, the following specific steps will be used:

[0039] S10: Construct a risk characteristic database for the entire lifecycle of ship equipment development: collect data on existing ship projects, define the categories and specific characteristics of six primary risks (technology, schedule, cost, compliance, supply chain, and operation and maintenance support) and their subordinate secondary risks, set up scoring criteria to map the risk characteristics of existing projects into vectors and store them in association.

[0040] Specifically, when constructing a risk characteristics database covering the entire lifecycle of ship equipment development, it is first necessary to collect data on existing ship projects. This data encompasses three core categories of information: basic project information, risk issue data, and ship-specific data.

[0041] The basic project information clarifies the fundamental attributes of existing shipbuilding projects, specifically including project number, ship type, development stage, contract amount, planned duration, actual duration, and supply chain information. The project number is a unique identifier for each existing shipbuilding project and can be obtained through the company's internal project management system. The ship type is determined based on the project's design purpose and structural characteristics; for example, guided-missile destroyers, replenishment ships, and special research vessels. The development stage is divided according to the shipbuilding equipment development process into the conceptual stage, engineering development stage, testing and verification stage, and delivery support stage. The contract amount is the total budget agreed upon at the time of project signing. The planned duration is the expected completion time set at the time of project initiation. The actual duration is the actual time consumed from project launch to final delivery. Supply chain information includes the names of key component suppliers, their supply cycles, and the localization rate of key components.

[0042] Risk data is used to record risk-related information actually occurring during the development of existing shipbuilding projects. Specifically, it includes the details of risk events that occurred at each development stage, the time of occurrence, the scope of impact, the amount of loss caused, and the mitigation measures. The details of risk events at each development stage must describe the manifestation of the risk event in detail; for example, incorrect power system selection during the design phase, defects in hull welding processes during the engineering development phase, or substandard radar system anti-jamming performance during the testing and verification phase. The time of occurrence must be accurate to the specific date to facilitate subsequent analysis of the phased patterns of risk occurrence. The scope of impact must clearly define which aspects of the project's technical implementation, schedule progress, and cost control are affected by the risk; for example, affecting only schedule, or affecting both technology and costs. The amount of loss caused by the risk must be calculated as the direct economic losses resulting from the risk event, including rework costs and material waste costs. Mitigation measures must record the specific actions taken to address the risk event; for example, changing the power system model, optimizing hull welding process parameters, or upgrading the radar system's anti-jamming algorithm.

[0043] Specific data in the marine industry are crucial information reflecting the unique characteristics of a shipbuilding project. This includes maritime regulation versions, sea state test data, records of client requirement changes, and progress on domestic substitution. The maritime regulation versions must record the specific versions of international or domestic maritime regulations followed during project execution. Sea state test data must cover relevant parameters tested in different sea areas and under different sea state conditions; for example, equipment operating temperature and stability data in tropical seas with wave heights of 2 to 3 meters; or equipment startup performance data in frigid seas below -20 degrees Celsius. Client requirement change records must detail the adjustments requested by the client during project execution; for example, changes to ship combat performance indicators and electromagnetic interference resistance levels. Progress on domestic substitution must record the process of key components in the project transitioning from reliance on imports to domestic substitution, including the model of the substituted component, the substitution time, and the performance test results of the substituted component.

[0044] After completing the data collection for existing shipbuilding projects, it is necessary to define the risk categories and characteristics of these projects. Shipbuilding project risks are categorized into six main types: technical risk, schedule risk, cost risk, compliance risk, supply chain risk, and operation and maintenance support risk. Each main risk category is further subdivided into several secondary risk categories. Specifically, the secondary risk categories under technical risk include system compatibility risk, domestic substitution risk, and sea condition adaptability risk. The secondary risk categories under schedule risk include supply chain delay risk and testing cycle risk. The secondary risk categories under cost risk include material cost overrun risk and rework cost risk. The secondary risk categories under compliance risk include maritime regulatory risk and customer requirement change risk. The secondary risk categories under supply chain risk include key supplier dependence risk and domestic supply chain stability risk. The secondary risk categories under operation and maintenance support risk include after-sales maintenance risk and personnel training risk.

[0045] Each secondary risk category should have corresponding ship-specific risk characteristics defined, taking into account the technical characteristics and development requirements of the ship project. For system compatibility risk under technical risk, the corresponding ship-specific risk characteristics include data interaction latency between navigation and communication systems and the matching degree between power and propulsion systems. For domestic substitution risk under technical risk, the corresponding ship-specific risk characteristics include the domestic production rate of key components and the ratio of the lifespan of substitute parts to that of imported parts. For sea state adaptability risk under technical risk, the corresponding ship-specific risk characteristics include equipment failure rate in cold-water areas and radar detection range attenuation rate in high sea states. For supply chain delay risk under schedule risk, the corresponding ship-specific risk characteristics include the deviation days between the delivery cycle and the planned cycle for special steel and the deviation days between the debugging cycle and the planned cycle for core equipment. For testing cycle risk under schedule risk, the corresponding ship-specific risk characteristics include the cumulative number of days of interruption of sea trials due to weather and the number of rework operations in land-based joint testing. For material cost overrun risk under cost risk, the corresponding ship-specific risk characteristics include the increase in special steel prices and the proportion of cost overruns caused by increased tariffs on imported components. Regarding rework cost risk under cost risk, the corresponding shipbuilding-specific risk characteristics include the amount of rework costs caused by hull welding defects and the deviation ratio between software system reconstruction costs and planned costs. Regarding maritime regulatory risk under compliance risk, the corresponding shipbuilding-specific risk characteristics include the number of non-compliant clauses caused by updates to maritime regulations during project execution. Regarding customer requirement change risk under compliance risk, the corresponding shipbuilding-specific risk characteristics include the number of times the customer requests requirement changes and the extent of technical solution adjustments due to these changes. Regarding key supplier dependence risk under supply chain risk, the corresponding shipbuilding-specific risk characteristics include the proportion of core equipment provided by a single supplier to the total amount of core equipment in the project and the political risk level of the supplier's region. Regarding the stability risk of the domestic supply chain under supply chain risk, the corresponding shipbuilding-specific risk characteristics include the batch pass rate of domestically produced components and the degree of matching between supplier capacity and project schedule requirements. Regarding after-sales maintenance risk under operation and maintenance support risk, the corresponding shipbuilding-specific risk characteristics include the average annual number of equipment failures after delivery and the inventory fulfillment rate of key spare parts. For personnel training risks under operation and maintenance support risks, the corresponding shipbuilding-specific risk characteristics include the shipyard's operation and maintenance personnel's proficiency in operating new equipment and the number of days the personnel training cycle deviates from the planned cycle.

[0046] Subsequently, the risk characteristics of each existing shipbuilding project are mapped into a risk characteristic vector. First, quantitative scoring standards are established for the shipbuilding-specific risk characteristics of each secondary risk category. The scoring ranges from 1 to 5, with 1 representing extremely low risk and 5 representing extremely high risk. For example, for the risk characteristic of data interaction latency between navigation and communication systems, a score of 1 is given for latency less than or equal to 10 milliseconds, 2 for 10 to 30 milliseconds, 3 for 30 to 50 milliseconds, 4 for 50 to 80 milliseconds, and 5 for greater than 80 milliseconds. As another example, for the risk characteristic of the localization rate of key components, a score of 1 is given for a localization rate greater than or equal to 90%, 2 for 70 to 90%, 3 for 50 to 70%, 4 for 30 to 50%, and 5 for less than 30%. Based on the actual data of each existing shipbuilding project, and in accordance with the quantitative scoring standards, corresponding scores are assigned to all shipbuilding-specific risk characteristics corresponding to that project. Using the score of each risk feature as a vector element, a risk feature vector for the existing vessel project is constructed according to a pre-defined order of secondary risk categories. This pre-defined order of secondary risk categories must remain consistent throughout the database construction process. For example, the vector elements can be arranged in the following order: system compatibility risk, domestic substitution risk, sea state adaptability risk, supply chain delay risk, testing cycle risk, material cost overrun risk, rework cost risk, maritime regulatory risk, customer requirement change risk, key supplier dependence risk, domestic supply chain stability risk, after-sales maintenance risk, and personnel training risk.

[0047] Finally, the constructed risk feature vectors are linked and stored with the corresponding existing shipbuilding project data to form a risk feature database covering the entire lifecycle of shipbuilding equipment development. During the linking and storage process, a correspondence must be established between the risk feature vectors and the project numbers in the existing shipbuilding project data. This ensures that the risk feature vector, along with basic project information, risk issue data, and shipbuilding-specific data, can be quickly retrieved using the project number. The database can be stored using a relational database, such as MySQL. Basic project information, risk issue data, shipbuilding-specific data, and risk feature vectors are stored in different tables, and the tables are linked using the project number. This allows for efficient retrieval of necessary data from the database when conducting risk management for shipbuilding projects under review.

[0048] S20: The dynamic risk index model calculates the dynamic risk index of each secondary risk category of the ship project to be reviewed and classifies the risk level.

[0049] Specifically, to identify and quantify the risks of a vessel project under review, it is first necessary to extract the project information. This project information encompasses four core components: basic information, technical solutions, test plans, and compliance requirements.

[0050] The basic information of the ship projects under review is consistent with that of existing ship projects, including project number, ship type, development stage, contract amount, project timeline, and supply chain information. The project number serves as a unique identifier within the company, used to distinguish the project from existing projects in the database. The ship type is determined based on the project's intended use; for example, a new type of missile frigate or polar research vessel. The development stage must clearly specify the current stage of the project, i.e., the conceptual design stage, engineering development stage, testing and verification stage, or delivery assurance stage. The contract amount is the total budget stipulated in the contract for the project under review. The project timeline is the total planned duration from project initiation to delivery. Supply chain information includes the proposed suppliers for key components, the planned supply cycle, and the target localization rate for key components.

[0051] The technical proposal for the vessel project under review must detail the core technologies and related configurations employed. This includes, for example, the model and parameters of the power system, including engine power and propulsion method; the type and functions of the navigation system, including positioning accuracy and data update frequency; the frequency band and transmission rate of the communication system; and the detection range and anti-interference capabilities of the radar system. The extraction of the technical proposal must be combined with the project design documents to ensure an accurate reflection of the technical composition of the project under review.

[0052] The test plan for the vessel project under review must clearly define the test content, test locations, and test schedule for each stage of the project. Test content includes land-based integrated testing and sea trials. Land-based integrated testing must specify the system modules and test items to be tested, such as the collaborative testing of the power system and navigation system, and the data interaction testing of the communication system and radar system. Sea trials must specify the test sea area, such as the East China Sea or the South China Sea, and clearly define the simulated sea conditions, such as wave height and temperature ranges. The test schedule must specify the planned start and end times for each test stage to ensure alignment with the overall project timeline.

[0053] The compliance requirements for the vessel projects under review must clearly define the various norms and standards to be followed during project execution. This includes specific versions of international maritime regulations, such as relevant conventions issued by the International Maritime Organization; specific numbers and names of domestic shipbuilding industry standards; and specific technical requirements proposed by the client, such as electromagnetic interference immunity levels and operational performance indicators. The extraction of compliance requirements should refer to relevant project compliance documents to ensure that the project development complies with all applicable norms.

[0054] After extracting information on the vessels awaiting review, the dynamic risk index for each secondary risk category is calculated based on the dynamic risk index model. The formula for calculating the dynamic risk index model is as follows: .in, The dynamic risk index represents the i-th secondary risk category, which is used to quantitatively assess the impact of the secondary risk on the project. Pi represents the probability score of the occurrence of the i-th secondary risk. The score ranges from 1 to 5 and needs to be determined based on the actual situation of the project under review and the risk occurrence data of similar projects in the database. For example, if the target for the localization rate of key components in the project under review is 75%, the specific value of Pi is determined by referring to the probability of occurrence of localization substitution risk in projects with a localization rate of 70% to 80% in the database. This represents the severity score of the i-th secondary risk, ranging from 1 to 5. The score must be determined based on the potential economic losses, schedule delays, and other consequences that the risk might cause. For example, if a secondary risk could lead to a project cost overrun of 8 million yuan, the severity score would be determined based on the extent of the cost loss. The specific value. The coupling coefficient represents the i-th secondary risk, ranging from 1.0 to 1.5. Determining the coupling coefficient requires analyzing the correlation between this secondary risk and other secondary risks; if the occurrence of this risk leads to an increase in the probability of other risks occurring or an expansion of their impact, then... Take a value greater than 1.0; if this risk is not significantly related to other risks, then... Take 1.0. β represents the stage impact coefficient of the ship development project under review. The specific value is determined according to the stage of the project. The stage impact coefficient is 1.0 for the design stage, 1.5 for the engineering development stage, and 2.0 for the test and verification stage. The difference in stage impact coefficient reflects the different degrees of impact of risks on the overall project at different development stages.

[0055] After calculating the dynamic risk index for each secondary risk category, the risk level is determined based on the dynamic risk index. The classification criteria must be pre-defined. For example, a dynamic risk index greater than or equal to 30 is classified as a catastrophic risk; a dynamic risk index greater than or equal to 20 and less than 30 is classified as a severe risk; a dynamic risk index greater than or equal to 10 and less than 20 is classified as a moderate risk; a dynamic risk index greater than or equal to 5 and less than 10 is classified as a minor risk; and a dynamic risk index less than 5 is classified as a negligible risk. The risk level classification must be strictly implemented according to the pre-defined criteria to ensure the accuracy and consistency of the risk level assessment results for each secondary risk category, providing a basis for the development of subsequent risk response plans.

[0056] S30: Establish a target risk feature vector based on the ship type and development stage of the ship project to be reviewed; calculate the cosine similarity between the target risk feature vector and the risk feature vectors of all existing ship projects in the full life cycle risk feature database of ship equipment development, cluster similar project groups, statistically analyze risk data to generate prompt statements, and determine the risk category.

[0057] Specifically, to conduct risk prediction for a ship project under review, it is first necessary to establish a target risk characteristic vector based on the ship type and its current development stage. Establishing the target risk characteristic vector requires three different approaches to ensure that the vector accurately reflects the risk characteristics of the project under review.

[0058] In the first scenario, if the ship project to be reviewed has a similar historical version, meaning the database stores historical projects of the same type and product series as the ship project under review, then the risk feature vector of the latest version of that type of ship project in the full lifecycle risk feature database of ship equipment development is extracted as the target risk feature vector. For example, if the project to be reviewed is an improvement project for a certain type of missile destroyer, and the database stores development project data for the previous version of that missile destroyer, then the risk feature vector of the previous version project is directly retrieved as the target risk feature vector.

[0059] In the second scenario, if the ship project under review has no similar historical versions but has similar projects, meaning there are no historical projects in the database for the same product series, but there are historical projects of the same ship type in other product series, then all risk feature vectors of the same type of ship at the same development stage are extracted from the full-cycle risk feature database for ship equipment development. The average value is calculated for each element of all extracted vectors; the average value of each element is the element value at the corresponding position in the target risk feature vector, ultimately forming the target risk feature vector. For example, if the project under review is a new type of comprehensive supply ship, and there are no similar historical versions of this new type of comprehensive supply ship in the database, but there is development project data for other types of comprehensive supply ships, and these projects are at the same development stage as the project under review, then the average value of each element in the risk feature vectors of these projects is calculated to construct the target risk feature vector.

[0060] In the third scenario, if the vessel project to be reviewed is a completely new type of vessel, meaning there are no historical projects of the same type in the database, then shipbuilding experts are organized to score the risk characteristics of each secondary risk category. The experts participating in the scoring must cover multiple professional fields such as power systems, navigation systems, supply chain management, and compliance review, with no fewer than five experts. Each expert, based on the technical solutions, test plans, and other information of the project to be reviewed, provides a score for the risk characteristics of each secondary risk category according to a preset scoring standard. The average of all experts' scores is calculated element by element, and the average of each element is the element value at the corresponding position in the target risk characteristic vector, thereby constructing the target risk characteristic vector.

[0061] After establishing the target risk feature vector, the cosine similarity between this target risk feature vector and the risk feature vectors of all existing ship projects in the full-cycle risk feature database for ship equipment development is calculated. The formula for calculating the cosine similarity is:

[0062] ;

[0063] Cosine similarity measures the degree of similarity between two vectors; the higher the similarity, the closer the cosine similarity value is to 1. The formula for calculating cosine similarity includes... The cosine similarity between the target risk feature vector and the risk feature vector of existing ship projects. The target risk feature vector is determined by the ship type and development stage of the project to be reviewed. Each element in the target risk feature vector corresponds to a risk feature score of a secondary risk category. i represents the i-th element of the target risk feature vector, and the range of values ​​for i is consistent with the number of elements in the target risk feature vector. A risk characteristic score corresponding to a secondary risk category. The risk feature vector representing existing ship projects is retrieved from the risk feature database of the entire life cycle of ship equipment development. The structure of the risk feature vector of existing ship projects is consistent with the target risk feature vector. The i-th element represents the risk characteristic vector of existing shipbuilding projects, each This corresponds to the risk characteristic score of a secondary risk category in the existing shipbuilding project. 'n' represents the number of elements in the risk characteristic vector, which is the same as the total number of secondary risk categories. Each element corresponds to a risk characteristic of a secondary risk category.

[0064] After calculating the cosine similarity, the K-means clustering algorithm is used to group existing shipbuilding projects with a cosine similarity greater than or equal to a preset threshold into similar project groups. The preset threshold value needs to be determined based on the accuracy requirements of project risk management to ensure that existing projects included in the similar project groups have a high degree of similarity in risk characteristics with the projects to be reviewed. In the division process, existing shipbuilding projects with a cosine similarity greater than or equal to the preset threshold are first screened out, and then these screened projects are clustered using the K-means clustering algorithm to ultimately form one or more similar project groups. The existing projects within each similar project group have strong consistency in risk characteristics.

[0065] After identifying similar project groups, the probability of occurrence and average loss amount for each secondary risk category within these groups are calculated. To calculate the probability of occurrence, the number of projects in the similar project group experiencing a specific secondary risk is first counted, then this number is divided by the total number of projects in the similar project group to obtain the probability of occurrence for that secondary risk. To calculate the average loss amount, the loss amounts of all projects in the similar project group experiencing a specific secondary risk are first collected, then the arithmetic mean of these loss amounts is calculated to obtain the average loss amount for that secondary risk.

[0066] The high-level risks identified through statistics undergo semantic processing to generate risk warning statements. High-level risks are defined as catastrophic and severe risks based on the dynamic risk index classification standard. During semantic processing, information such as the identifiers of similar project groups corresponding to high-level risks, the probability of risk occurrence, average loss amount, and average delay time must be converted into easily understandable natural language. For example, if a high-level risk corresponds to a similar project group for the development of a certain type of frigate, with a 60% probability of occurrence, an average loss amount of six million yuan, and an average delay time of fifteen days, the generated risk warning statement must include this information and provide targeted risk response suggestions, such as recommending advance high- and low-temperature cycle testing of key components, ensuring that the warning statement provides clear guidance for risk management of the projects under review.

[0067] S40: Establish a risk response plan library, select an initial plan, formulate an implementation plan, and periodically review and adjust the plan.

[0068] Specifically, generating and implementing closed-loop management of risk response plans for shipbuilding projects first requires building a dedicated risk response plan library for the shipbuilding industry. This library should be built around the risk categories and development stages of shipbuilding projects, storing risk response plans according to the correspondence between risk categories and development stages.

[0069] The risk category dimension covers six major categories: technical risk, schedule risk, cost risk, compliance risk, supply chain risk, and operation and maintenance support risk. Each major category contains corresponding secondary risk categories. The development phase dimension covers four phases: solution development, phase testing, verification, and delivery assurance. Each risk response plan must be developed for a specific secondary risk category and a specific development phase to ensure the plan's relevance. For example, for the risk of domestic substitution under technical risk, the response plan in the engineering development phase must be developed in conjunction with the component testing and verification requirements of that phase; for the risk of dependence on key suppliers under supply chain risk, the response plan in the solution phase must be developed in conjunction with the supplier selection requirements of that phase.

[0070] Each risk response plan must clearly define specific implementation steps and effectiveness verification indicators. The implementation steps should detail the operational procedures for handling risks, such as the response plan for sea state adaptability risks during the testing phase. Implementation steps may include conducting continuous testing on an indoor simulated sea state platform, followed by full-scale ship trials in different sea areas. Effectiveness verification indicators must establish quantifiable evaluation standards to ensure the measurable effectiveness of the plan. For example, the failure rate in indoor simulated sea state testing should be less than 5%, and the first-pass yield in full-scale ship trials should be greater than or equal to 80%.

[0071] After completing the construction of a dedicated risk response solution library for the shipbuilding industry, initial risk response solutions are selected from the library based on the risk level of the ship project to be reviewed and the risk data of similar project groups. The selection process prioritizes matching the secondary risk category and current development stage of the project under review, and then determines the priority of the solutions based on the risk level. For example, if a secondary risk of the project under review is a critical risk, the highest priority response solution for that risk category and development stage in the solution library should be selected. As another example, if a secondary risk of the project under review is a medium risk, a solution with a normal priority can be selected. Simultaneously, referring to the risk data of similar project groups, if a particular response solution in the similar project group has shown good implementation results, such as significantly reducing risk losses, then that solution should be prioritized as the initial risk response solution.

[0072] After determining the initial risk response plan, an implementation plan for the plan should be developed. The implementation plan must clearly define the responsible parties, timelines, and resource requirements. The responsible parties should be determined based on the professional field involved in the plan; for example, a technical engineer could be designated as the responsible party for a technical risk-related plan, while a supply chain manager could be designated as the responsible party for a supply chain risk-related plan. Timelines should be set in conjunction with the overall project timeline, clearly defining the start and expected completion dates of the plan to ensure that the plan's implementation aligns with the project schedule. Resource requirements should list the human, material, and financial resources needed to implement the plan; for example, the number of testing personnel, the types and quantities of testing equipment required to execute a particular testing plan, and the budget for the plan's implementation.

[0073] The risk status of vessel projects awaiting review should be reassessed periodically, with an assessment cycle of quarterly. During the assessment, relevant data on the implementation of the proposed solutions should be collected, such as whether the probability of risk occurrence has decreased or whether the potential losses have been reduced. Risk response plans should be adjusted based on the assessment results. If the risk level decreases by 30% or more, the current plan is considered effective and should be maintained. If the risk level increases or decreases by less than 10%, the current plan has failed to effectively control the risk, and the implementation steps or resource allocation need to be adjusted. For example, this could involve increasing the number of tests or adding more professional personnel, ensuring the plan adapts to changes in risk status.

[0074] After the shipbuilding project is completed, the data on actual risk events and the implementation status of risk response plans will be entered into the full-cycle risk characteristic database for ship equipment development, completing closed-loop risk management. The data on actual risk events must include the type of risk, the actual time of occurrence, the actual scope of impact, and the actual amount of loss. The type of risk must be consistent with the secondary risk category. The actual time of occurrence must record the specific date the risk event occurred. The actual scope of impact must clearly define the impact of the risk on project technical schedule, costs, etc. The actual amount of loss must include the direct economic losses caused by the risk, including rework costs and material waste costs.

[0075] Data on the implementation of risk response plans must include the actual implementation steps, actual implementation time, and actual implementation results. The actual implementation steps must record the specific operations performed during the implementation process, ensuring consistency with the planned steps. The actual implementation time must record the actual start and end times of the plan, and any deviations from the planned time. The actual implementation results must be evaluated against implementation effectiveness verification indicators to assess the actual achievement of the plan's goals, such as whether the actual test failure rate meets the preset standards. Entering this data into the database can provide data support for risk management of subsequent shipbuilding projects, enabling continuous accumulation of risk data and optimization of plans.

[0076] In one embodiment, such as Figure 2 As shown, a system risk monitoring device is provided, which corresponds one-to-one with the system risk monitoring method in the above embodiments. The system risk monitoring device includes: a data construction unit, a risk quantification unit, a risk prediction unit, and a risk response unit. Detailed descriptions of each functional module are as follows:

[0077] The data construction unit is used to build a risk characteristic database for the entire life cycle of ship equipment development, collect data on existing ship projects, define the categories and exclusive characteristics of six primary risks including technology, schedule, cost, compliance, supply chain, and operation and maintenance support, as well as their subordinate secondary risks, and set scoring criteria to map the risk characteristics of existing projects into vectors and store them in association.

[0078] The risk quantification unit is used to extract information about the project to be reviewed, calculate the dynamic risk index of each secondary risk category of the ship project to be reviewed using the dynamic risk index model, and classify the risk level.

[0079] The risk prediction unit is used to establish a target risk feature vector based on the ship type and development stage of the ship project to be reviewed; calculate the cosine similarity between the target risk feature vector and the risk feature vectors of all existing ship projects in the full life cycle risk feature database of ship equipment development, cluster similar project groups, and generate prompt statements based on statistical risk data.

[0080] The risk response unit is used to establish a risk response plan library, select an initial plan, formulate an implementation plan, and periodically review and adjust the plan.

[0081] Specific limitations regarding the system risk monitoring device can be found in the limitations of the system risk monitoring method described above, and will not be repeated here. Each module in the aforementioned system risk monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0082] In one embodiment, such as Figure 3 As shown, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a system risk monitoring method.

[0083] For specific limitations on computer equipment, please refer to the limitations on system risk monitoring methods mentioned above, which will not be repeated here.

[0084] In one embodiment, a computer-readable medium is provided, the computer-readable medium storing a computer program, wherein when a processor executes the computer program, it performs the following steps:

[0085] A risk characteristic database for the entire lifecycle of ship equipment development is established. Data on existing ship projects is collected, and six primary risks (technology, schedule, cost, compliance, supply chain, and operation and maintenance support) and their subordinate secondary risks are defined, along with their specific characteristics. Scoring criteria are set to map the risk characteristics of existing projects into vectors and store them in association.

[0086] Extract information on projects to be reviewed, use a dynamic risk index model to calculate the dynamic risk index of each secondary risk category of the ship projects to be reviewed, and classify the risk levels.

[0087] Based on the ship type and development stage of the ship project to be reviewed, a target risk feature vector is established; the cosine similarity between the target risk feature vector and the risk feature vectors of all existing ship projects in the full life cycle risk feature database of ship equipment development is calculated, similar project groups are clustered, and risk data is statistically analyzed to generate prompt statements;

[0088] Establish a risk response plan library, select an initial plan, formulate an implementation plan, and periodically review and adjust the plan.

[0089] For specific limitations on computer-readable media, please refer to the limitations on system risk monitoring methods mentioned above, which will not be repeated here.

[0090] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0091] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A system risk monitoring method, characterized by, The method comprises the following steps: constructing a ship equipment development full-cycle risk feature database: collecting inventory ship project data, defining six first-level risks including technology, progress, cost, compliance, supply chain and operation and maintenance support and subordinate second-level risks, and setting scoring standards to map the inventory project risk features into vectors and store them in association; calculating the dynamic risk index of each second-level risk category of the ship project to be evaluated and dividing the risk level; establishing a target risk feature vector according to the ship type and the development stage of the ship project to be evaluated; calculating the cosine similarity of the target risk feature vector and the risk feature vectors of all inventory ship projects in the ship equipment development full-cycle risk feature database, clustering similar project groups, and statistically analyzing the risk data to generate prompt statements to determine the risk category; establishing a risk response scheme library according to the risk category to select an initial scheme and execute a plan, and regularly re-evaluating and adjusting the scheme; The process of calculating the index using the dynamic risk index model is as follows: ,in, This is a dynamic risk index. Rate the probability. For severity scoring, Let be the coupling coefficient for the i-th secondary risk, with a value ranging from 1.0 to 1.

5. The determination of this coupling coefficient requires analysis of its correlation with other secondary risks; if it leads to an increase in the probability of occurrence or an expansion of the impact of other secondary risks, then... Take a value greater than 1.0; if there is no significant correlation with other secondary risks, then... β is set to 1.0; β is the stage influence coefficient of the research and development stage of the ship project to be reviewed. The specific value of the stage influence coefficient is determined according to the ship project to be reviewed. Among them, the stage influence coefficient of the scheme stage is 1.0, the stage influence coefficient of the engineering research and development stage is 1.5, and the stage influence coefficient of the test and verification stage is 2.

0.

2. The system risk monitoring method of claim 1, wherein, the subordinate second-level risks of the technical risk include system compatibility risk, localization substitution risk and sea condition adaptability risk; the exclusive features of the system compatibility risk include the data interaction delay degree of the navigation system and the communication system and the matching degree of the power system and the propulsion system.

3. The system risk monitoring method of claim 1, wherein, The target risk feature vector is established according to the ship type and the development stage of the ship project to be evaluated, specifically comprising: if there is a historical version of the same type of ship project, the risk feature vector of the latest version of the same type of ship project in the ship equipment development full-cycle risk feature database is extracted as the target risk feature vector; if there is no historical version of the same type of ship project, all risk feature vectors of the same type of ship project in the same development stage in the ship equipment development full-cycle risk feature database are extracted, the average value of the corresponding elements of each vector is calculated, and the target risk feature vector is formed; if the ship project to be evaluated is a new type of ship project, experts in the ship field are organized to score the risk features of each second-level risk category, and the target risk feature vector is established according to the scoring results.

4. The system risk monitoring method of claim 1, wherein, The calculation method of the cosine similarity is: ； wherein, represents the target risk feature vector of the ship project to be reviewed; represents the risk feature vector of any one of the inventory ship projects in the database; represents the i-th element of the target risk feature vector; represents the i-th element of the risk feature vector of the inventory ship project , and n represents the number of elements of the risk feature vector; () represents the similarity of the project risk features.

5. The system risk monitoring method of claim 1, wherein, When establishing the risk response scheme library, each risk response scheme includes implementation steps and implementation effect verification indicators; the re-evaluation cycle of the risk state of the ship project to be evaluated is every quarter, and when adjusting the risk response scheme according to the evaluation results, if the risk level decreases by more than or equal to 30%, the original risk response scheme is maintained; if the risk level increases or decreases by less than 10%, the implementation steps or resource allocation of the risk response scheme are adjusted.

6. The system risk monitoring method of claim 1, wherein, The data recorded after the project is completed includes actual risk category, occurrence time, influence range, loss amount, actual implementation steps, actual implementation time and actual implementation effect of the response scheme.

7. An apparatus risk monitoring apparatus, characterized by, The system risk monitoring method comprises the following steps: a data construction unit is configured to construct a ship equipment development full-cycle risk feature database, collect inventory ship project data, define six first-level risks including technology, progress, cost, compliance, supply chain and operation and maintenance support and subordinate second-level risks, and set scoring standards to map the inventory project risk features into vectors and store them in association; The risk quantification unit is configured to extract project information to be reviewed, calculate dynamic risk indexes of each secondary risk category of the project to be reviewed by using a dynamic risk index model, and divide risk levels. The risk prediction unit is configured to determine a target risk characteristic vector according to a ship type and a development stage of the project to be reviewed, calculate cosine similarity between the target risk characteristic vector and risk characteristic vectors of all inventory ship projects in a ship equipment development full-cycle risk characteristic database, cluster similar project groups, and statistically analyze risk data to generate prompt statements. The risk response unit is configured to establish a risk response scheme library, select an initial scheme, determine an execution plan, and periodically reevaluate and adjust the scheme.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the system risk monitoring method according to any one of claims 1 to 6.

9. A computer readable medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the system risk monitoring method according to any one of claims 1 to 6.

Images