Financial voucher generation method, medium and system based on ocean monitoring platform

Abstract

The invention provides a financial voucher generation method based on a marine monitoring platform, a medium and a financial voucher generation system, and belongs to the technical field of financial voucher generation methods. Performing time sequence change feature analysis to construct a floating change matrix, performing Bayesian model analysis to obtain a comprehensive error relation matrix, performing decomposition to obtain an error stable matrix and an error change matrix, inputting the error change matrix into an ocean equipment error classifier for classification, and establishing an ocean asset value evaluation model to predict the equipment value. Financial business events are automatically identified through a financial business event identification rule base, accounting subjects are automatically matched according to event types and error weight coefficients to generate financial voucher templates, and the financial voucher templates are automatically recorded into a financial system after compliance verification is carried out on the financial voucher templates. The technical problem that the financial accounting result is not matched with the real value change of the equipment is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of financial voucher generation methods, and in particular, relates to a financial voucher generation method, medium and system based on an ocean monitoring platform. Background Art

[0002] In the financial management of marine monitoring equipment, traditional methods for generating financial vouchers rely primarily on pre-set, fixed templates and manual operations by accountants. These methods utilize standardized depreciation calculations and regular maintenance cost allocations to manage the financial accounting of equipment assets. This approach has been widely used in conventional equipment management in terrestrial environments. However, traditional techniques exhibit significant drawbacks when dealing with marine monitoring equipment. Due to the complexity and harshness of the marine environment, the actual operating status, error characteristics, and value changes of equipment are highly dynamic and uncertain. Traditional fixed templates are unable to capture these real-time changes, resulting in a significant disconnect between the generated financial vouchers and the actual status of the equipment. In current marine monitoring equipment financial management, due to the lack of a precise assessment mechanism for actual operating errors and environmental losses, traditional methods struggle to accurately reflect the true value changes of equipment in marine environments. Consequently, existing techniques often rely on manual experience and fixed templates, failing to dynamically adjust to the actual operating status and error characteristics of marine monitoring equipment, leading to a technical problem in which financial accounting results do not match the actual value changes of the equipment. Summary of the Invention

[0003] In light of this, the present invention provides a method, medium, and system for generating financial vouchers based on an ocean monitoring platform. These methods address the existing technical issues of financial voucher generation, which often relies on manual experience and fixed templates, failing to dynamically adjust to the actual operating status and error characteristics of ocean monitoring equipment, resulting in a mismatch between financial accounting results and changes in the actual value of the equipment.

[0004] The present invention is implemented as follows: In a first aspect, the present invention provides a method for generating financial vouchers based on an ocean monitoring platform, comprising: using Internet of Things sensors to collect operating status data, environmental parameter data, and equipment measurement data of ocean monitoring equipment in real time to establish an equipment operation database, while recording maintenance history data and dynamically adjusting the data collection frequency; extracting equipment measurement data from the equipment operation database to perform time series change feature analysis to construct a floating change matrix, analyzing the floating change matrix through a Bayesian model to obtain a comprehensive error relationship matrix, performing singular value decomposition on the comprehensive error relationship matrix to obtain an error stability matrix and an error change matrix, inputting the error change matrix into an ocean equipment error classifier for classification to obtain an error classification result, and calculating an error weight coefficient based on the error classification result using a gated weight function; combining the error classification result with operating status data for status analysis and anomaly detection, calculating an equipment health index and expected maintenance cost; calculating a dynamic depreciation rate and spare parts demand; establishing an ocean asset value assessment model to calculate an equipment value assessment result; automatically identifying financial business events based on changes in the equipment health index, expected maintenance cost, equipment value assessment results, and error weight coefficients; calling accounting subject mapping rules based on financial business events to automatically match corresponding accounting subjects, generating a financial voucher template, and entering the template into a financial system.

[0005] Among them, in the step of calculating the dynamic depreciation rate and spare parts demand, the environmental loss coefficient is calculated based on the equipment health index and expected maintenance cost, combined with the operating intensity and corrosiveness index. The dynamic depreciation rate is calculated using the workload method combined with the environmental loss coefficient, and the spare parts demand is determined based on the failure frequency, expected maintenance cost and error weight coefficient.

[0006] The data acquisition frequency adjustment coefficient is a frequency adjustment parameter calculated based on the operating intensity and the corrosiveness index, and is used to dynamically adjust the data acquisition interval of the IoT sensor.

[0007] The floating change matrix is ​​a dynamic change characteristic matrix constructed by mathematically modeling the time series change characteristics of the equipment measurement data, and reflects the fluctuation law of the equipment measurement accuracy.

[0008] Among them, the Bayesian model analysis process includes taking the measurement data change pattern in the floating change matrix as observation evidence, establishing the prior probability distribution of systematic error, random error, environmental interference error and drift error, calculating the posterior impact probability of various errors on different monitoring parameters through the Bayesian inference method, and constructing a comprehensive error relationship matrix that includes the correlation strength between error type and monitoring parameter.

[0009] Among them, the marine equipment error classifier is an error type identification model built based on deep learning technology. It can automatically identify and classify different types of equipment measurement errors, and the output error classification results include the probability distribution of each error type and the final classification label.

[0010] Among them, the calculation method of the gated weight function is based on the confidence score of each error type in the error classification result. When the system error confidence exceeds 0.8, the corresponding error weight coefficient is set to 1.5; when the random error confidence exceeds 0.7, the corresponding error weight coefficient is set to 0.8; when the environmental interference error confidence exceeds 0.6, the corresponding error weight coefficient is dynamically adjusted between 1.0 and 1.3 according to the corrosive index.

[0011] Among them, the marine asset value assessment model is an asset value prediction model constructed based on the time series data analysis method. It takes the operating intensity, corrosion index, failure frequency, expected maintenance cost, error stability matrix and error change matrix as input parameters, processes the error stability matrix and error change matrix through the error feature fusion layer, and combines the time series data analysis to predict the remaining service life of the equipment.

[0012] Among them, the operating status data includes equipment usage time, operating intensity, and failure frequency; the environmental parameter data includes seawater temperature, salinity, pressure, and corrosiveness index; and the equipment measurement data includes real-time measurement values ​​of various monitoring parameters.

[0013] Among them, in the step of calculating the equipment health index, the equipment health index is calculated based on the equipment usage time, failure frequency, corrosion index and error weight coefficient, and the expected maintenance cost is calculated based on the equipment health index and maintenance history data.

[0014] The singular value decomposition is a mathematical method for decomposing the comprehensive error relationship matrix into an error stability matrix and an error variation matrix, and is used to separate systematic error and random error components.

[0015] The equipment health index is an equipment status evaluation indicator calculated by comprehensively considering the equipment usage time, failure frequency, corrosion index and error weight coefficient, and is used to evaluate the current operating status of the equipment.

[0016] The environmental loss coefficient is an adjustment parameter for environmental correction of the standard depreciation rate based on the corrosive index and operating intensity, and the dynamic depreciation rate is an equipment depreciation ratio calculated by combining the workload method with the environmental loss coefficient.

[0017] Among them, the construction process of the marine asset value assessment model includes collecting historical equipment operation data from the equipment operation database as training samples, and segmenting the historical equipment operation data according to time windows. Each training sample contains 30 consecutive days of operation status data, environmental parameter data and historical error weight coefficients as input features, and the corresponding actual depreciation amount and residual value of the equipment as label data.

[0018] The financial business events include equipment depreciation events, maintenance cost events, spare parts procurement events, and asset impairment events, and the recognition priority of the financial business events is adjusted by the error weight coefficient.

[0019] Among them, the accounting subject mapping rule is a configuration rule for automatically associating financial business events with corresponding accounting subjects, and the financial voucher template is a standardized financial voucher format generated based on the financial business event type, equipment value assessment results, dynamic depreciation rate, spare parts demand and error weight coefficient.

[0020] A second aspect of the present invention provides a computer-readable storage medium, in which program instructions are stored. When the program instructions are run in a computer, they are used to execute the above-mentioned method for generating financial vouchers based on an ocean monitoring platform.

[0021] The third aspect of the present invention provides a financial voucher generation system based on an ocean monitoring platform, which includes the above-mentioned computer-readable storage medium. The system is any one of a computer, a server, and a single-chip microcomputer. The computer-readable storage medium is arranged in the system, and the system is provided with a microprocessor for executing program instructions stored in the computer-readable storage medium.

[0022] The present invention solves the technical problem that traditional financial accounting methods cannot accurately reflect the changes in the true value of marine monitoring equipment by establishing a real-time data acquisition system and a marine equipment error classifier based on Internet of Things sensors, and combining Bayesian model analysis and singular value decomposition technology to construct a dynamic financial voucher generation mechanism. The present invention adopts error feature fusion and dynamic depreciation rate calculation methods, which can automatically adjust the financial processing strategy according to the actual operating status of the equipment, environmental parameters and error weight coefficients, overcoming the technical defects of the traditional fixed template method in poor adaptability in the marine environment, and achieving accurate matching of financial voucher generation with the actual status of the equipment. The present invention establishes a scientific financial business event recognition rule library by comprehensively considering the equipment health index, environmental loss coefficient and error classification results. From a technical principle, it ensures that the generated financial vouchers can accurately reflect the real value change trend of marine monitoring equipment in a complex marine environment, solving the core technical problem of the mismatch between financial accounting results and the actual status of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0025] like Figure 1 FIG. 1 is a flow chart of a method for generating financial vouchers based on an ocean monitoring platform according to the first aspect of the present invention. The method comprises the following steps: S01. Using IoT sensors to collect real-time operating status data, environmental parameter data, and equipment measurement data of marine monitoring equipment, and establish an equipment operation database. The operating status data includes equipment usage time, operating intensity, and failure frequency; the environmental parameter data includes seawater temperature, salinity, pressure, and corrosivity index; the equipment measurement data includes real-time measurement values ​​of various monitoring parameters; and maintenance history data is recorded in the equipment operation database. A data collection frequency adjustment coefficient is calculated based on the operating intensity and the corrosivity index, and the data collection frequency is dynamically adjusted using the data collection frequency adjustment coefficient. S02. Extracting the equipment measurement data from the equipment operation database, performing time series change feature analysis on the equipment measurement data to construct a floating change matrix, performing error analysis on the marine monitoring equipment, analyzing the floating change matrix using a Bayesian model to obtain a comprehensive error relationship matrix, performing singular value decomposition on the comprehensive error relationship matrix to obtain an error stability matrix and an error change matrix, inputting the error change matrix into a marine equipment error classifier for classification to obtain an error classification result, and calculating an error weight coefficient using a gated weight function based on the error classification result; S03. Extracting the operating status data, the environmental parameter data, and the maintenance history data from the equipment operation database, performing status analysis and anomaly detection on the operating status data in combination with the error classification result, identifying equipment operation anomalies, maintenance requirements, and fault warnings, calculating an equipment health index based on the equipment usage time, the fault frequency, the corrosiveness index, and the error weight coefficient, and calculating an expected maintenance cost based on the equipment health index and the maintenance history data; S04. Calculate an environmental loss coefficient based on the equipment health index and the expected maintenance cost, in combination with the operating intensity and the corrosiveness index; calculate a dynamic depreciation rate using the workload method in combination with the environmental loss coefficient; and determine the required quantity of spare parts based on the failure frequency, the expected maintenance cost, and the error weight coefficient; S05. Establish a marine asset value assessment model, using the operating intensity, the corrosiveness index, the failure frequency, the expected maintenance cost, the error stability matrix, and the error change matrix as input parameters, process the error stability matrix and the error change matrix through an error feature fusion layer, analyze and predict the remaining service life of the equipment in combination with time series data, and calculate the equipment value assessment result in combination with the dynamic depreciation rate; S06. Establishing a financial business event identification rule base to automatically identify financial business events based on the equipment health index change, the expected maintenance cost, the equipment value assessment result, and the error weight coefficient, and adjusting the identification priority of the financial business events using the error weight coefficient. The financial business events include equipment depreciation events, maintenance cost events, spare parts procurement events, and asset impairment events. S07. Based on the event type of the financial business event, the equipment value assessment result, and the error weight coefficient, calling the accounting account mapping rule to automatically match the corresponding accounting account, and combining the dynamic depreciation rate and the spare parts demand quantity to generate a financial voucher template; S08. Perform compliance check on the financial voucher template, verify the integrity and accuracy of the voucher elements through a rule engine, automatically enter the information into the financial system, and generate an audit trail record based on the financial business events.

[0026] The data acquisition frequency adjustment coefficient is a frequency adjustment parameter calculated based on the operating intensity and the corrosiveness index, and is used to dynamically adjust the data acquisition interval of the IoT sensor.

[0027] The maintenance history data is the historical record information of all previous maintenance operations, maintenance costs and maintenance effects of the equipment recorded in the equipment operation database.

[0028] The floating change matrix is ​​a dynamic change characteristic matrix constructed by mathematically modeling the time series change characteristics of the device measurement data, and reflects the fluctuation law of the device measurement accuracy.

[0029] The error analysis is an evaluation and analysis of the measurement accuracy of ocean monitoring equipment, and the errors include systematic errors, random errors, environmental interference errors and drift errors.

[0030] The comprehensive error relationship matrix is ​​a multidimensional correlation matrix obtained by analyzing the relationship between various errors and monitoring parameters through the Bayesian model, which describes the degree of influence of different error types on each monitoring parameter and the interaction relationship.

[0031] The singular value decomposition is a mathematical method for decomposing the comprehensive error relationship matrix into the error stability matrix and the error variation matrix, and is used to separate systematic error and random error components.

[0032] The error stability matrix is ​​a matrix reflecting systematic error characteristics obtained through the singular value decomposition, and represents the long-term stable error mode of the equipment.

[0033] The error change matrix is ​​a matrix reflecting random error characteristics obtained through the singular value decomposition, and represents the error pattern of dynamic changes in the equipment.

[0034] Among them, the marine equipment error classifier is an error type identification model built based on deep learning technology, which can automatically identify and classify different types of equipment measurement errors.

[0035] The error classification result is the error type identification and the corresponding confidence score output by the marine equipment error classifier after classifying the error change matrix.

[0036] The gating weight function is a function that calculates a weight coefficient based on the confidence score of each error type in the error classification result, and is used to quantify the degree of influence of different error types on device operation.

[0037] The error weight coefficient is a weight parameter calculated by the gated weight function according to the error classification result, and is used to adjust the importance of the error impact in subsequent analysis.

[0038] The equipment health index is an equipment status evaluation index calculated based on the equipment usage time, the failure frequency, the corrosiveness index and the error weight coefficient, and is used to evaluate the current operating status of the equipment.

[0039] The environmental loss coefficient is an adjustment parameter for making environmental corrections to the standard depreciation rate according to the corrosivity index and the operating intensity.

[0040] The dynamic depreciation rate is the equipment depreciation ratio calculated by the workload method combined with the environmental loss coefficient, reflecting the actual value loss rate of the equipment in the marine environment.

[0041] The spare parts demand is the spare parts reserve quantity calculated based on the failure frequency, the expected maintenance cost and the error weight coefficient, and is used to formulate a spare parts procurement plan.

[0042] Among them, the error feature fusion layer is a processing level for processing the error stability matrix and the error change matrix in the marine asset value assessment model, and is used to fuse the error features with the equipment operation features.

[0043] Among them, the marine asset value assessment model is an asset value prediction model constructed based on the time series data analysis method, which predicts the equipment value by analyzing the changing trends of the operating intensity, the corrosion index, the failure frequency, the expected maintenance cost, the error stability matrix and the error change matrix.

[0044] The equipment value assessment result is the equipment current value and future value change prediction data output by the marine asset value assessment model.

[0045] The financial business event is a business activity that requires financial processing and is identified based on the change in the equipment health index, the expected maintenance cost, the equipment value assessment result, and the error weight coefficient.

[0046] The accounting subject mapping rule is a configuration rule for automatically associating the financial business event with the corresponding accounting subject, thereby ensuring the accuracy of the generation of financial vouchers.

[0047] The financial voucher template is a standardized financial voucher format generated according to the financial business event type, the equipment value assessment result, the dynamic depreciation rate, the spare parts demand quantity and the error weight coefficient.

[0048] The rule engine is a software component that performs automated verification and processing based on predefined business rules, and is used to verify the compliance of the financial voucher template.

[0049] The audit trail record is complete traceability information that records the entire process from the collection of the operating status data to the generation of the financial voucher template.

[0050] The construction process of the marine asset value assessment model includes collecting historical equipment operation data from the equipment operation database as training samples, the historical equipment operation data includes the equipment usage time, the operation intensity, the failure frequency, the corrosion index, the maintenance history data and the corresponding equipment actual value change record, and the historical equipment operation data is segmented according to the time window. Each training sample includes the operation status data, the environmental parameter data and the historical error weight coefficient for 30 consecutive days as input features, and the corresponding equipment actual depreciation amount and residual value as label data. In the error feature fusion layer, the error stability matrix and the error change matrix are fused with the equipment operation features through weighted fusion. The marine asset value assessment model is trained by a regression analysis method, so that the model can predict the equipment value assessment result based on the current operation intensity, the corrosion index, the failure frequency, the expected maintenance cost, the error stability matrix and the error change matrix.

[0051] The Bayesian model analysis process includes taking the measurement data change pattern in the floating change matrix as observation evidence, establishing the prior probability distribution of systematic error, random error, environmental interference error and drift error, calculating the posterior impact probability of various errors on different monitoring parameters through the Bayesian inference method, and constructing the comprehensive error relationship matrix containing the correlation strength between error type and monitoring parameter. The rows of the comprehensive error relationship matrix represent different error types, the columns represent different monitoring parameters, and the matrix element values ​​represent the influence strength of the corresponding error type on the corresponding monitoring parameter.

[0052] The training process of the marine equipment error classifier includes collecting historical error data of marine monitoring equipment from the equipment operation database as training samples, the historical error data includes the error change matrix with labeled error types, constructing a deep neural network model for error pattern learning, and training the marine equipment error classifier through supervised learning methods to identify systematic errors, random errors, environmental interference errors and drift errors, and outputting the error classification results including the probability distribution of each error type and the final classification label.

[0053] The calculation method of the gated weight function is based on the confidence score of each error type in the error classification result. When the system error confidence exceeds 0.8, the corresponding error weight coefficient is set to 1.5 to increase the impact weight of systematic problems. When the random error confidence exceeds 0.7, the corresponding error weight coefficient is set to 0.8 to reduce the impact weight of random fluctuations. When the environmental interference error confidence exceeds 0.6, the corresponding error weight coefficient is dynamically adjusted between 1.0 and 1.3 according to the corrosive index. When the drift error confidence exceeds 0.5, the corresponding error weight coefficient is set to 1.2 and the equipment calibration recommendation is initiated.

[0054] The financial business event identification rule library includes four types of event identification rules. The equipment depreciation event identification rule automatically triggers the generation of depreciation vouchers based on the dynamic depreciation rate and accrual period. The maintenance cost event identification rule triggers the generation of cost vouchers when the expected maintenance cost exceeds the budget threshold and the error weight coefficient is greater than 1.0. The spare parts procurement event identification rule triggers the generation of procurement vouchers when the spare parts demand exceeds the inventory safety line and the error weight coefficient shows the risk of equipment failure. The asset impairment event identification rule triggers the generation of impairment vouchers when the equipment health index is lower than 0.3 and the error weight coefficient shows an unrepairable error. The error weight coefficient is used to adjust the weight of the triggering conditions of each type of financial business event to ensure that business events with a high degree of error impact are handled first.

[0055] The specific implementation of the above steps is described in detail below.

[0056] The specific implementation of step S01 is to conduct comprehensive data collection and dynamic adjustment of marine monitoring equipment through the Internet of Things sensor network. First, a distributed sensor network is established. Each sensor node collects operating status data such as equipment usage time, operating intensity and fault frequency at preset time intervals. The equipment usage time records the cumulative working time in hours, the operating intensity uses a normalized value from 0 to 1 to represent the equipment load level, and the fault frequency records the number of faults occurring per unit time. At the same time, environmental parameter data such as seawater temperature, salinity, pressure and corrosive index are collected. The seawater temperature monitoring range is -2°C to 35°C, the salinity monitoring range is 0 to 45‰, and the pressure monitoring range is 0 to 6× Pa, the corrosivity index is expressed in a quantitative scale of 0 to 10. The sensor also collects instantaneous measurement values ​​of each monitoring parameter in real time as equipment measurement data. The maintenance history data such as the time, cost and effect of all maintenance operations are synchronously recorded in the equipment operation database. In order to achieve dynamic optimization of the data acquisition frequency, the system calculates the data acquisition frequency adjustment coefficient based on the product of the operation intensity and the corrosivity index. When the product is less than 2, the adjustment coefficient is set to 0.5. When the product is between 2 and 6, the adjustment coefficient is set to 1.0. When the product is greater than 6, the adjustment coefficient is set to 1.5. The basic acquisition frequency is adjusted by this adjustment coefficient to ensure that the data acquisition density is improved under high equipment load or high corrosion environment.

[0057] The specific implementation of step S02 is to perform in-depth error analysis and intelligent classification on the equipment measurement data. The system extracts equipment measurement data from the equipment operation database, uses time series analysis methods to extract the temporal change characteristics of the data, and uses sliding window technology to construct the measurement value changes within continuous time periods into a floating change matrix. This matrix reflects the dynamic fluctuation pattern of the equipment measurement accuracy. Subsequently, a multi-dimensional error analysis is performed on the marine monitoring equipment to identify the four main error types: systematic error, random error, environmental interference error, and drift error. The floating change matrix is ​​analyzed using the Bayesian inference method, and the probabilistic correlation between each type of error and the monitoring parameters is established to generate a comprehensive error relationship matrix. This matrix is ​​decomposed using the singular value decomposition algorithm, separating the complex error relationship into an error stability matrix reflecting the characteristics of systematic errors and an error change matrix reflecting the characteristics of random errors. The error change matrix is ​​fed as input data into a marine equipment error classifier built based on a deep neural network. The classifier uses a multi-layer perceptron structure to identify different error types and output a confidence score. According to the confidence of each error type in the error classification results, the gated weight function is used to calculate the error weight coefficient. When the confidence of the systematic error exceeds 0.8, the weight coefficient is set to 1.5; when the confidence of the random error exceeds 0.7, the weight coefficient is set to 0.8; when the confidence of the environmental interference error exceeds 0.6, the weight coefficient is dynamically adjusted between 1.0 and 1.3; when the confidence of the drift error exceeds 0.5, the weight coefficient is set to 1.2.

[0058] The specific implementation of step S03 is to assess the equipment health status by integrating operational status data, environmental parameter data, and maintenance history data. The system extracts relevant data from the equipment operation database and conducts in-depth status analysis of the operational status data in combination with error classification results. Statistical analysis methods are used to identify abnormal patterns in the data and detect equipment operational anomalies by setting thresholds. A lifespan warning is triggered when the equipment's operating time exceeds 80% of its design lifespan; a fault warning is triggered when the failure frequency exceeds 150% of the historical average; and an environmental warning is triggered when the corrosion index exceeds 7. The system uses a multi-parameter fusion algorithm to calculate the equipment health index. This index comprehensively considers the time decay factor of equipment operating time, the reliability factor of the failure frequency, the environmental damage factor of the corrosion index, and the precision factor of the error weight coefficient. A weighted average method is used to obtain a health score ranging from 0 to 1. Based on the equipment health index and maintenance history data, regression analysis is used to predict future maintenance needs. The expected maintenance cost is calculated based on historical maintenance cost trend analysis and equipment health change trends. This cost consists of both preventive maintenance costs and fault repair costs.

[0059] The specific implementation method of step S04 is to calculate dynamic economic parameters based on the health status of the equipment and environmental factors. The system calculates the environmental loss coefficient based on the equipment health index and expected maintenance cost, combined with the operating intensity and corrosive index. This coefficient reflects the accelerated impact of the marine environment on the loss of equipment value. The environmental loss coefficient is calculated using a nonlinear combination of operating intensity and corrosive index. When the product of the two is less than 3, the loss coefficient is 1.0. When the product is between 3 and 8, the loss coefficient increases linearly from 1.2 to 1.8. When the product exceeds 8, the loss coefficient is 2.0. The dynamic depreciation rate is calculated using the workload method principle. This method determines the depreciation progress based on the ratio of the actual workload of the equipment to the designed workload. The standard depreciation rate is corrected in combination with the environmental loss coefficient so that the depreciation rate can truly reflect the value decay rate of the equipment in the marine environment. The demand for spare parts is determined based on the failure frequency, expected maintenance cost and error weight coefficient. The safety stock model in inventory management theory is adopted. When the failure frequency exceeds 0.1 times per day, the demand for spare parts increases by 20%. When the expected maintenance cost exceeds 5% of the original value of the equipment, the demand for spare parts increases by 30%. When the error weight coefficient is greater than 1.2, the demand for spare parts increases by an additional 15%.

[0060] The specific implementation method of step S05 is to construct a comprehensive marine asset value assessment model to predict the value of equipment. The model uses operating intensity, corrosion index, failure frequency, expected maintenance cost, error stability matrix and error change matrix as core input parameters. The error feature fusion layer in the model uses an attention mechanism to process the error stability matrix and error change matrix, and highlights the impact of important error features on asset value through adaptive weight distribution. The fusion layer integrates the error matrix features with the equipment operation features at multiple levels to form a comprehensive feature vector. The model uses a time series prediction algorithm to analyze the historical trend of equipment operation data and predict the remaining service life of the equipment. The prediction is based on the attenuation model of the equipment health index and the cumulative damage model of environmental factors. Combined with the dynamic depreciation rate and the remaining life prediction of the equipment, the model outputs the current value assessment of the equipment and the future value change trend. The value assessment results include a comprehensive assessment of the three dimensions of book value, fair value and recoverable value.

[0061] The specific implementation of step S06 involves establishing an intelligent financial business event recognition system. The system establishes a financial business event recognition rule library containing four categories of event recognition rules, each of which is optimized and adjusted based on an error weighting coefficient. The equipment depreciation event recognition rule is automatically triggered based on the dynamic depreciation rate and pre-designed depreciation cycle, with priority elevated when the monthly depreciation rate exceeds 2%. The maintenance expense event recognition rule monitors changes in expected maintenance costs and automatically triggers the generation of expense vouchers when costs exceed the budget threshold by 10% and the error weighting coefficient is greater than 1.0. The spare parts procurement event recognition rule compares spare parts demand with current inventory. When demand exceeds the inventory safety line by 30% and the error weighting coefficient indicates an increased risk of equipment failure, a purchase voucher request is triggered. The asset impairment event recognition rule monitors the equipment health index and triggers the impairment voucher request when the health index falls below 0.3 and the error weighting coefficient indicates the presence of an unrecoverable error. The system dynamically adjusts the recognition priority of various financial business events using the error weighting coefficient, ensuring that business events with high error impact receive priority processing, thereby improving the timeliness and accuracy of financial processing.

[0062] The specific implementation method of step S07 is to realize automatic matching of accounting subjects and generation of financial voucher templates based on the business rule engine. According to the identified financial business event type, the system calls the pre-configured accounting subject mapping rules for automatic matching. The mapping rules are established based on enterprise accounting standards and industry practices. Equipment depreciation events correspond to fixed asset depreciation accounts, maintenance cost events correspond to administrative expenses or operating cost accounts, spare parts procurement events correspond to raw material procurement accounts, and asset impairment events correspond to asset impairment loss accounts. The system determines the voucher amount based on the equipment value assessment results, and uses the error weight coefficient to adjust the accuracy of the amount. When the error weight coefficient is greater than 1.2, an uncertainty adjustment of 5% is added to the relevant amount. The depreciation amount is calculated based on the dynamic depreciation rate, and the purchase amount is determined based on the demand for spare parts. A standardized financial voucher template containing accounting subjects, debit and credit directions, amounts, and summaries is generated. The voucher template also contains auxiliary information such as the time of business occurrence, relevant equipment number, error impact rating, etc. to ensure the integrity and traceability of financial vouchers.

[0063] The specific implementation method of step S08 is to ensure the quality of financial vouchers and complete system integration through multi-level compliance verification. The system uses a rule engine based on predefined business rules to conduct a comprehensive verification of financial voucher templates. The verification content includes voucher element integrity verification, debit and credit balance verification, amount rationality verification and business logic consistency verification. Integrity verification ensures that the voucher contains the necessary accounting subjects, amounts and summary information, debit and credit balance verification ensures that the debit amount is equal to the credit amount, amount rationality verification ensures that the amount is within a reasonable range by comparing with historical data, and business logic verification ensures that the logical relationship between the voucher content and the triggered business event is correct. After the verification is passed, the system automatically enters the financial voucher into the enterprise financial management system and uses a standard interface protocol to ensure the security and accuracy of data transmission. At the same time, the system generates a complete audit trail record based on financial business events. The record contains information on the entire process from data collection, error analysis, event identification to voucher generation, and records the timestamp, operation content, relevant parameters and processing results of each processing link to ensure the complete traceability of the financial processing process.

[0064] The detailed structure of the Bayesian model includes four core components: a prior probability distribution establishment layer, an evidence processing layer, a posterior probability calculation layer, and a relationship matrix generation layer. The prior probability distribution establishment layer establishes initial probability distributions for systematic error, random error, environmental interference error, and drift error based on historical error statistics. The prior probability of systematic error adopts a normal distribution, random error adopts a Gaussian distribution, environmental interference error adopts a Weibull distribution, and drift error adopts an exponential distribution. The evidence processing layer uses the change pattern of the measured data in the floating change matrix as observational evidence and processes the input data through three sub-processes: data preprocessing, feature extraction, and evidence quantification. The posterior probability calculation layer uses Bayes' theorem for inference calculations, calculating the probability of each type of error affecting different monitoring parameters through a likelihood function. Combining the prior probabilities yields the posterior probability distribution. The relationship matrix generation layer converts the posterior probabilities into a matrix form, constructing a comprehensive error relationship matrix with rows representing error types and columns representing monitoring parameters. The establishment of the training dataset for this model involves collecting historical operating data from at least 1,000 marine monitoring devices for more than six months. The data includes measured values ​​of monitoring parameters such as temperature, salinity, pressure, and dissolved oxygen, as well as their corresponding true values. Various error types are identified through manual labeling, and a labeled dataset that shows the impact of error types on monitoring parameters is established. The model parameters are trained using a cross-validation method to ensure the model's generalization ability in different sea areas and different equipment types.

[0065] The detailed structure of the marine equipment error classifier adopts a deep convolutional neural network architecture, consisting of four main modules: the input layer, the feature extraction layer, the classification decision layer, and the output layer. The input layer receives the error change matrix obtained through singular value decomposition as input data. The matrix size is n×m, where n represents the time dimension and m represents the monitoring parameter dimension. The feature extraction layer consists of three convolutional layers and two pooling layers. The first convolutional layer uses 32 3×3 convolutional kernels to extract local features, the second convolutional layer uses 64 3×3 convolutional kernels to extract deep features, and the third convolutional layer uses 128 3×3 convolutional kernels to extract high-level features. Each convolutional layer is followed by a batch normalization layer and a Reluctant Unit (ReLU) activation function. The pooling layer uses 2×2 max pooling to reduce feature dimensionality. The classification decision layer consists of two fully connected layers. The first fully connected layer contains 256 neurons, and the second fully connected layer contains 4 neurons corresponding to the four error types. Softmax activation is used to output probability distributions. The output layer generates the error classification results, which include confidence scores for each error type and the final classification label. The establishment of the training data set for this classifier requires the collection of no less than 5,000 error change matrix samples. Each sample is manually labeled with the error type by marine engineers. The data sources cover error patterns in different sea areas, different equipment models and different environmental conditions. The training set, validation set and test set are divided into 8:1:1 ratios. The model is trained using the stochastic gradient descent optimization algorithm, the learning rate is set to 0.001, the batch size is set to 32, and the training cycle is set to 100 rounds. The model performance is evaluated by accuracy, precision, recall rate and F1 score.

[0066] The detailed structure of the marine asset valuation model utilizes a multi-input deep regression network architecture, consisting of five core modules: a multi-path input layer, an error feature fusion layer, a time series analysis layer, a value prediction layer, and an output layer. The multi-path input layer receives scalar inputs such as operating intensity, corrosion index, failure frequency, and expected maintenance cost, as well as matrix inputs such as the error stability matrix and the error change matrix, applying appropriate preprocessing methods for different input types. The error feature fusion layer utilizes an attention mechanism to process the error matrix inputs. A self-attention module calculates the importance weights of the matrix elements, and a cross-attention module fuses the feature information of the error stability matrix and the error change matrix. The fused features are then concatenated with the scalar input to form a comprehensive feature vector. The time series analysis layer utilizes a long short-term memory network to process time series features. An LSTM layer with 128 hidden units captures the temporal dependencies of equipment operating states. A bidirectional LSTM enhances the model's ability to model historical and future trends. The value prediction layer comprises three fully connected layers: the first layer has 256 neurons, the second layer has 128 neurons, and the third layer has 64 neurons. Each layer uses a ReLU activation function and dropout regularization to prevent overfitting. The output layer contains three output nodes, corresponding to the predicted results of the equipment's book value, fair value, and recoverable value. The model's training dataset requires the collection of data from the complete lifecycle of at least 800 marine monitoring devices over a period of more than two years. This data includes information such as equipment purchase price, historical maintenance records, operating status data, environmental parameter data, and final disposal value. A correspondence between input features and asset value changes is established, and a time window sliding method is used to generate training samples. Each sample contains 30 consecutive days of input features and corresponding value change labels. Mean squared error is used as the loss function, and the Adam optimization algorithm is used to train the model. The learning rate is set to 0.001, the batch size is set to 16, and the training cycle is set to 200 rounds. The model's prediction accuracy is evaluated using mean absolute error, root mean square error, and coefficient of determination.

[0067] It should be noted that, first, the present invention uses a Bayesian model to analyze the time series change characteristics of the measurement data of the ocean monitoring equipment, and captures the fluctuation law of the equipment measurement accuracy by constructing a floating change matrix, which has significant technical advantages over the traditional static error analysis method. Traditional methods usually use fixed error correction coefficients or simple linear regression models to deal with equipment errors, which cannot effectively identify and distinguish the complex error types and their interactions in the marine environment. The present invention establishes the prior probability distribution of systematic errors, random errors, environmental interference errors and drift errors through the Bayesian inference method, which can accurately calculate the posterior impact probability of various errors on different monitoring parameters and construct a multi-dimensional associated comprehensive error relationship matrix. Combined with the singular value decomposition technology, the comprehensive error relationship matrix is ​​decomposed into an error stability matrix and an error change matrix, which realizes the precise separation of systematic error and random error components, and provides a reliable mathematical basis for subsequent error classification and weight calculation. This error analysis method based on probability reasoning can effectively deal with the uncertainty and complexity of equipment errors in the marine environment.

[0068] Second, the present invention constructs a marine equipment error classifier based on deep learning technology, which can automatically identify and classify different types of equipment measurement errors, and has higher accuracy and consistency than traditional manual experience judgment methods. The traditional method relies on the subjective experience of technicians to judge the type and impact of equipment errors, and has problems such as strong subjectivity, poor consistency, and inability to handle complex error patterns. The present invention collects historical error data of marine monitoring equipment as training samples, and uses supervised learning methods to train error classifiers to identify systematic errors, random errors, environmental interference errors, and drift errors, and outputs the probability distribution and confidence score of each error type. Based on the error classification results, the gated weight function can dynamically calculate the error weight coefficient according to the confidence score of different error types. When the confidence of the systematic error is high, the impact weight of the systematic problem is increased, and when the confidence of the random error is high, the impact weight of the random fluctuation is reduced. This dynamic weight adjustment mechanism can ensure that the financial processing strategy is accurately matched with the actual error status of the equipment.

[0069] Third, the present invention establishes a financial business event identification rule base, and dynamically adjusts the identification priority of financial business events through error weight coefficients, which has stronger adaptability and accuracy than traditional fixed template financial processing methods. Traditional methods use preset fixed templates and standardized depreciation calculation methods, which cannot be dynamically adjusted according to the actual operating status and error characteristics of the equipment, resulting in the generated financial vouchers being out of touch with the actual value changes of the equipment. The present invention automatically identifies equipment depreciation events, maintenance cost events, spare parts procurement events and asset impairment events based on changes in equipment health index, expected maintenance costs, equipment value assessment results and error weight coefficients, and adjusts the triggering conditions of various financial business events through error weight coefficients to ensure that business events with a high degree of error impact are given priority. Financial voucher templates are generated in combination with dynamic depreciation rates and spare parts demand, realizing real-time association between financial voucher generation and the actual status of the equipment. This dynamic adjustment mechanism based on error characteristics can accurately reflect the real value change trend of marine monitoring equipment in complex environments.

[0070] The synergy of the above three key technical ideas constitutes a complete dynamic financial voucher generation system, which has significant overall advantages over traditional static financial processing methods. Bayesian model error analysis and singular value decomposition technology provide high-quality input data for the error classifier, ensuring the accuracy and reliability of error identification; the dynamic adjustment mechanism of the marine equipment error classifier and the gated weight function provides scientific weight parameters for financial voucher generation, achieving accurate matching of financial processing strategies with the actual status of the equipment; the dynamic financial voucher generation mechanism based on the error weight coefficient transforms the results of the first two technical ideas into specific financial processing solutions, forming a closed-loop automated processing flow. The three technical ideas support and promote each other, and jointly build an intelligent financial management system driven by real-time data, which can automatically adapt to the complex changes in the operating status of equipment in the marine environment, solve the limitations of the traditional fixed template method in processing the financial accounting of marine monitoring equipment, and realize the intelligent, dynamic and precise generation of financial vouchers.

[0071] A second aspect of the present invention provides a computer-readable storage medium, in which program instructions are stored. When the program instructions are run in a computer, they are used to execute the above-mentioned method for generating financial vouchers based on an ocean monitoring platform.

[0072] The third aspect of the present invention provides a financial voucher generation system based on an ocean monitoring platform, which includes the above-mentioned computer-readable storage medium. The system is any one of a computer, a server, and a single-chip microcomputer. The computer-readable storage medium is arranged in the system, and the system is provided with a microprocessor for executing program instructions stored in the computer-readable storage medium.

[0073] Specifically, the principle of the present invention is: the fundamental principle that the present invention can solve the problems of the existing technology lies in the construction of a dynamic financial voucher generation system driven by real-time data. The system collects the operating status data, environmental parameter data and equipment measurement data of marine monitoring equipment in real time through Internet of Things sensors, establishes a complete equipment operation database, and provides a reliable data basis for subsequent error analysis and value assessment. The technical solution uses a Bayesian model to analyze the time series change characteristics of equipment measurement data. By constructing a floating change matrix and a comprehensive error relationship matrix, it can accurately identify and quantify the systematic error, random error, environmental interference error and drift error of equipment in the marine environment, and separate the error into a stable matrix and a change matrix through singular value decomposition technology, providing a mathematical basis for error classification and weight calculation. The core innovation of the present invention is to establish a marine equipment error classifier and a gated weight function, which can dynamically calculate the error weight coefficient based on the error classification result, and integrate the weight coefficient into the equipment health index, dynamic depreciation rate and financial business event identification process, realizing the real-time association between financial processing strategy and actual equipment status. Through the marine asset value assessment model and the financial business event recognition rule library, the present invention can automatically identify equipment depreciation events, maintenance cost events, spare parts procurement events and asset impairment events, and adjust the priority of event recognition according to the error weight coefficient to ensure that the generated financial vouchers can accurately reflect the actual value changes of the equipment in the marine environment. This dynamic adjustment mechanism based on error characteristics and real-time status is the key to solving the limitations of the traditional fixed template method.

[0074] A specific embodiment 1 of the present invention is provided below. The specific implementation of each step in this embodiment 1 is described in detail as follows.

[0075] The specific implementation of step S01 is to conduct comprehensive data collection and dynamic adjustment of ocean monitoring equipment through the Internet of Things sensor network. The calculation of the data collection frequency adjustment coefficient is specifically expressed as follows: ; Where, is the data collection frequency adjustment factor; The device operation intensity ranges from 0 to 1; is the corrosivity index, ranging from 0 to 10; is a piecewise function.

[0076] The specific piecewise function is defined as: ; Where, for The product value of .

[0077] The parameter acquisition method is: The data is acquired by real-time monitoring using sensors, including step 1: monitoring the working current of the equipment through a current sensor; step 2: monitoring the working load of the equipment through a load sensor; and step 3: normalizing the ratio of the monitored value to the rated parameter of the equipment to obtain the operating intensity. Obtained by environmental monitoring, including step 1: Sensors monitor the pH of seawater. is the hydrogen ion concentration index; Step 2: monitor the conductivity of seawater through a conductivity sensor; Step 3: monitor the oxygen content of seawater through a dissolved oxygen sensor; Step 4: quantify the multiple parameters into a level of 0 to 10 according to the corrosion evaluation standard.

[0078] The specific implementation of step S02 is to perform deep error analysis and intelligent classification on the device measurement data. The construction of the floating change matrix is ​​specifically expressed as follows: ; Where, is the floating change matrix; For the Moment The change of a monitoring parameter; The length of the time window, in hours, is determined by the device monitoring frequency and is generally between 24 and 168 hours. is the number of monitoring parameters.

[0079] The calculation of the change is expressed as follows: ; Where, For the Moment The measured value of a monitoring parameter.

[0080] The calculation of the posterior probability during the Bayesian model analysis is specifically expressed as follows: ; Where, For the Class error The posterior impact probability of each monitoring parameter; For the Under the condition of class error The likelihood probability of each monitoring parameter is determined by the statistical relationship between the error type and the monitoring parameter deviation in the historical data; For the The prior probability of class error is determined based on historical error statistics. The prior probabilities of systematic error, random error, environmental interference error, and drift error are 0.3, 0.4, 0.2, and 0.1, respectively. For the The marginal probability of a monitored parameter is calculated by summing the probabilities of all error types.

[0081] The calculation of the comprehensive error relationship matrix is ​​specifically expressed as follows: ; Where, is the comprehensive error relationship matrix; They represent systematic error, random error, environmental interference error, and drift error respectively; Indicates the monitoring parameters.

[0082] The singular value decomposition process is specifically expressed as follows: ; Where, is a left singular matrix; is a diagonal matrix of singular values; is the transpose of a right singular matrix.

[0083] The extraction of error stability matrix and error change matrix is ​​expressed as follows: ; ; Where, is the error stabilization matrix; is the error change matrix; is the dimension number of the stable error component, which is determined by the cumulative contribution rate. When the cumulative contribution rate of the singular values ​​reaches 85%, it is determined value; express Before the Matrix List; express The front of the diagonal matrix OK column matrix; express Before the Matrix OK; express The matrix Go to the last column; express The matrix OK The submatrix from column to the last row and column; express The matrix Go to the last line.

[0084] The calculation of the gating weight function is specifically expressed as follows: ; Where, is the error weight coefficient; For the Weight factor of class error; For the confidence score of class error; is the gated activation function.

[0085] The gated activation function is defined as: ; The parameter acquisition method is: The output of the marine equipment error classifier is obtained, including step 1: the error change matrix Input classifier; Step 2: Forward propagation calculation through deep learning model; Step 3: Softmax function of output layer generates various error confidences. The default value of is determined based on the importance of the error type to the equipment operation. , the systematic error has the greatest impact so the weight is the highest, and the random error has the smallest impact so the weight is the lowest.

[0086] The specific implementation of step S03 is to evaluate the equipment health status by integrating the operating status data, environmental parameter data and maintenance history data. The calculation of the equipment health index is specifically expressed as follows: ; Where, The device health index ranges from 0 to 1. For the natural constant An exponential function with base , which is used to simulate the exponential decay law of device performance; is the attenuation coefficient; The length of time the equipment is used, in years; is the failure frequency, in times per year; is the corrosivity index; is the error weight coefficient; It is a natural constant, approximately equal to 2.71828; The error weight adjustment base is used to convert the error weight coefficient into a health correction factor.

[0087] The value of the attenuation coefficient is determined according to the aging law of equipment in the marine environment: ,in The maximum value reflects that the fault frequency has the most significant impact on health.

[0088] The calculation of expected maintenance costs is specifically expressed as follows: ; Where, is the expected maintenance cost, in ten thousand yuan; is the basic maintenance cost, in ten thousand yuan; The negative power of the equipment health index, that is, the square of the reciprocal, is used to amplify the impact of health degradation on maintenance costs. is the failure frequency impact coefficient, indicating that for every additional annual failure frequency, the maintenance cost increases by 10%; It is a random error term. Its value range is determined based on the historical statistics of maintenance cost fluctuations and is generally 5% to 15% of the basic maintenance cost.

[0089] The parameter acquisition method is: The historical data statistics are used for acquisition, including step 1: collecting equipment maintenance records for the past three years; step 2: calculating the average annual maintenance cost; step 3: adjusting by inflation rate to obtain the current basic maintenance cost. Obtained through equipment operating time records. Obtained through fault log statistics calculation.

[0090] The specific implementation of step S04 is to calculate the dynamic economic parameters based on the health status of the equipment and environmental factors. The calculation of the environmental loss coefficient is specifically expressed as follows: ; Where, is the environmental loss coefficient; The operating intensity of the equipment; is the corrosivity index; is a power exponent, which means square root operation and is used to slow down the growth rate of the impact of environmental factors; It is a sinusoidal function, which is used to simulate the periodic influence of environmental factors; is the value of pi, which is 3.14159; is the benchmark loss coefficient; is the main effect influence coefficient; is the periodic influence coefficient; It is a period adjustment parameter used to control the period length of the sine function.

[0091] The calculation of dynamic depreciation rate is as follows: ; Where, is the dynamic depreciation rate; is the actual workload in hours; is the design workload, in hours; is the standard depreciation rate; is the environmental loss coefficient; The health adjustment factor is used to adjust the depreciation rate according to the health status of the equipment; is the device health index.

[0092] The calculation of spare parts demand is as follows: ; Where, The demand for spare parts; The demand for basic spare parts; It is a step function that outputs 1 when the input is greater than 0, otherwise it outputs 0; is the original value of the equipment, in ten thousand yuan; is the failure frequency threshold, in times per year, corresponding to the situation where the annual failure rate exceeds 10%; is the maintenance cost ratio threshold, which means that the maintenance cost accounts for 5% of the original value of the equipment; is the error weight coefficient threshold; is the failure impact adjustment coefficient, which means that the spare parts demand increases by 20% when the failure frequency exceeds the standard; The maintenance cost impact adjustment coefficient indicates that the spare parts demand increases by 30% when the maintenance cost exceeds the standard; is the error impact adjustment coefficient, which means that the spare parts demand increases by 15% when the error weight exceeds the standard.

[0093] The parameter acquisition method is: The calculation is performed using inventory theory, including step 1: statistics of historical spare parts consumption; step 2: calculation of the standard deviation of spare parts consumption; step 3: determination of safety stock based on service level. Obtained through device uptime monitoring. Obtain from the device technical specification. Industry standard values ​​are used, generally ranging from 0.05 to 0.15 depending on the type of equipment, and 0.10 is usually used for marine monitoring equipment.

[0094] The specific implementation of step S05 is to construct a comprehensive marine asset value assessment model to predict the equipment value. The calculation of the equipment value assessment result is specifically expressed as follows: ; Where, is the equipment value assessment result, in ten thousand yuan; is the original value of the equipment; It is a multiplication symbol, indicating that the number of years from the 1st year to the the cumulative depreciation effect over the years; The service life; For the Dynamic depreciation rate for the year; is the error feature fusion function; is the error stabilization matrix; is the error change matrix; This is the model prediction error term. Its value range is determined by the prediction accuracy during model training, and is generally 2% to 8% of the original asset value.

[0095] The error feature fusion function is defined as: ; Where, is the Frobenius norm; is the maximum possible norm value of the corresponding matrix, which is determined by the 95% quantile of the matrix norm in historical data statistics; is the benchmark value coefficient; is the stability error influence coefficient, which indicates the adjustment intensity of the stability error on the equipment value; is the influence coefficient of the changing error, which indicates the adjustment strength of the changing error on the equipment value. Its value is smaller than the stable error coefficient, which reflects that the influence of the changing error is relatively small.

[0096] The parameter acquisition method is: Obtained from the equipment purchase contract. It is obtained through calculation using a marine asset value assessment model, which is trained using a deep learning method. The input is equipment operating parameters and an error matrix, and the output is a value correction factor.

[0097] The specific implementation of step S06 is the same as above and will not be described in detail here.

[0098] The specific implementation of step S07 is to realize automatic matching of accounting subjects and generation of financial voucher templates based on the business rule engine. The calculation of the financial voucher amount is specifically expressed as follows: ; Where, The amount of the financial voucher, in ten thousand yuan; is the basic business amount, in ten thousand yuan; is a step function; is the error weight coefficient; is the error adjustment coefficient, which indicates the uncertainty adjustment of adding 5% to the voucher amount when the error weight exceeds the threshold; This is the amount adjustment error item. The value range is determined according to the accuracy requirements of financial processing, generally 1% to 3% of the basic amount.

[0099] The basic business amount is determined according to different financial business event types: ; Where, is the unit price of spare parts, in Yuan; It is the impairment ratio, ranging from 0.1 to 0.5.

[0100] The parameter acquisition method is: Obtain quotations from suppliers. Determined based on the equipment health index and technical evaluation, including step 1: technical status evaluation of the equipment; step 2: analysis based on market price changes; step 3: determining the impairment ratio.

[0101] The specific implementation of step S08 is the same as above and will not be described in detail here.

[0102] In this embodiment, it should be noted that the data acquisition frequency adjustment coefficient formula is Using the principle of piecewise function, the data collection frequency is dynamically adjusted based on the product of the equipment's operating intensity and the corrosivity index. The formula's innovation lies in coupling environmental corrosivity with equipment load status. This automatically increases data collection density when the equipment operates at high load in a highly corrosive environment. Compared to traditional fixed-frequency data collection methods, this method can obtain more detailed equipment status information at critical moments, while conserving system resources during low-risk periods. This intelligently optimizes data collection and provides a more accurate data foundation for subsequent error analysis and financial decision-making.

[0103] Floating Change Matrix The construction principle is based on time series analysis, which calculates the changes in monitoring parameters over time to form a dynamic feature matrix. This matrix design mathematically represents the temporal fluctuation patterns of device measurement data. Compared to traditional single-point measurement analysis methods, the floating change matrix captures the dynamic evolution of device measurement accuracy, providing richer characteristic information for identifying different types of measurement errors, making subsequent error classification and analysis more accurate and reliable.

[0104] Bayesian posterior probability calculation formula Using the principles of Bayesian inference, prior knowledge is combined with observational evidence to calculate the probability of each type of error affecting the monitoring parameters. This innovative approach leverages historical error statistics as prior knowledge, combined with currently observed measurement change patterns, to dynamically update the impact assessment of each type of error. Compared to traditional error judgment methods based on empirical thresholds, the Bayesian approach provides a more scientific and quantitative error impact analysis framework, significantly improving the accuracy and reliability of error identification.

[0105] Singular Value Decomposition Method Using the principle of matrix decomposition, the complex comprehensive error relationship matrix is ​​separated into systematic error and random error components. The effectiveness of this mathematical model lies in its ability to extract stable systematic error patterns and changing random error characteristics from mixed error signals. Compared with the traditional method of treating all errors uniformly, singular value decomposition achieves precise separation of error components, providing a technical foundation for targeted processing and compensation of different types of errors, significantly improving the accuracy and depth of error analysis.

[0106] Gating weight function Using a confidence-based adaptive weight allocation principle, the weight coefficients of each error component are dynamically adjusted according to the identification confidence of different error types. The innovative effect of this function design is that it achieves intelligent quantification of the degree of error impact. When the confidence level of systematic errors is high, the weight is increased to highlight the impact of systemic problems. When the confidence level of random errors is high, the weight is reduced to reduce the interference of random fluctuations. Compared with traditional fixed-weight error processing methods, the gated weight function can dynamically adjust the analysis strategy according to the actual error type, significantly improving the accuracy and adaptability of error assessment.

[0107] Equipment Health Index Formula This model utilizes a multi-factor exponential decay model to comprehensively consider the impacts of aging, failure frequency, environmental corrosion, and measurement error on equipment health. This model's effectiveness lies in its ability to fully reflect the true health of equipment in marine environments. The exponential decay function accurately simulates the nonlinear decay of equipment performance as a function of various factors. The introduction of error weight coefficients allows health assessments to account for measurement uncertainty. Compared to traditional health assessment methods based on single parameters or linear models, this formula provides a more scientific and comprehensive evaluation of equipment status, laying a solid foundation for subsequent maintenance decisions and asset value assessments.

[0108] Environmental loss coefficient formula Combining the composite modeling principles of main and cyclical effects, the square root function reflects the diminishing marginal impact of environmental factors, while the sine function simulates the cyclical changes in the marine environment. The innovative effect of this formula lies in accurately reflecting the complex impact of the marine environment on equipment value loss. Compared to the traditional method of using a fixed depreciation rate, the environmental loss coefficient can dynamically adjust the equipment's value decay rate based on actual operating intensity and corrosion level, making depreciation calculations more consistent with the actual use of marine monitoring equipment and providing a scientific basis for accurate financial accounting.

[0109] Equipment Value Assessment Formula This model employs a comprehensive modeling principle that integrates cumulative depreciation with error characteristics, reflecting the cumulative effect of depreciation through a multiplication method. The error characteristic fusion function incorporates measurement uncertainty into the valuation process. The model's remarkable effectiveness lies in achieving precise asset valuation based on actual operating status and measurement quality. Compared to traditional, simple depreciation methods based on time or output, this formula comprehensively considers multiple factors, including the actual health of the equipment, environmental impacts, and measurement errors. This significantly improves the accuracy and credibility of asset valuations, providing a more scientific quantitative tool for asset management and financial decision-making in marine monitoring platforms.

[0110] It should be noted that the detailed explanations of the variables involved in the present invention are shown in Tables 1-1 and 1-2.

[0111] Table 1-1 Variable Explanation Table

[0112] Table 1-2 Variable Explanation Table

[0113] To better understand and implement the present invention, Example 2 of a specific application scenario is provided below: A research team deployed a marine environment monitoring platform in a certain sea area. The platform was equipped with multiple marine monitoring devices, including temperature sensors, salinity meters, pressure sensors, dissolved oxygen meters, and other key equipment. The main technical challenge faced by the research team was how to accurately assess the operating status and value changes of these devices in the marine environment and automatically generate corresponding financial vouchers to improve the accuracy and efficiency of asset management.

[0114] During the implementation process, the research team first established a distributed IoT sensor network to collect real-time data from each monitoring device. Taking one of the key multi-parameter water quality monitors as an example, the basic data collection frequency of the device is set to once every 10 minutes. Through real-time monitoring, the operating intensity of the device can be The corrosive index is 0.75. is 6.8. According to the calculation formula of data acquisition frequency adjustment coefficient, ,Since the product value is between 2 and 6, the data acquisition frequency adjustment coefficient α is set to 1.0, keeping the original acquisition frequency unchanged.

[0115] During 30 days of continuous monitoring, the research team collected operational data on the equipment. The equipment accumulated 18,520 hours of use, with a failure rate of 0.12 per year. The primary parameters measured by the equipment included seawater temperature, salinity, pressure, and dissolved oxygen content. By analyzing the temporal variation characteristics, a 96×4-dimensional floating variation matrix was constructed, reflecting the variation patterns of the four monitored parameters at 96 time points.

[0116] The research team used a Bayesian model to analyze the floating change matrix and established a correlation between error types and monitoring parameters. Based on historical data statistics, the prior probabilities of systematic error, random error, environmental interference error, and drift error were set to 0.3, 0.4, 0.2, and 0.1, respectively. Through Bayesian inference calculations, a 4×4-dimensional comprehensive error relationship matrix was obtained. Using singular value decomposition, this matrix was decomposed into an error stability matrix and an error change matrix. The cumulative contribution of the first two singular values ​​reached 87%, confirming that the stable error component dimension k=2.

[0117] The error change matrix is ​​input into the pre-trained marine equipment error classifier, which is trained based on 5,000 historical error samples. The classification results show that the confidence level of the system error is 0.85, the confidence level of the random error is 0.72, the confidence level of the environmental interference error is 0.63, and the confidence level of the drift error is 0.48. According to the gated weight function, since the confidence level of the system error exceeds 0.8, the corresponding error weight coefficient is set to 1.5; the confidence level of the random error exceeds 0.7, and the weight coefficient is set to 0.8; the confidence level of the environmental interference error exceeds 0.6, combined with the corrosion index of 6.8, the weight coefficient is adjusted to 1.0+0.3×6.8 / 10=1.204. The final error weight coefficient is obtained by comprehensive calculation. =1.32.

[0118] Based on the collected operating status data, the research team calculated the equipment health index. =2.11 years (18520 hours), failure frequency =0.12 times per year, corrosive index =6.8, error weight coefficient =1.32. Using the equipment health index calculation formula, we get =0.73, indicating that the overall condition of the equipment is good but there is a certain degree of performance degradation.

[0119] Combining the equipment health index and maintenance history data, the research team predicted future maintenance needs. According to the maintenance records of the past three years, it is RMB 85,000. Using the expected maintenance cost calculation formula, we get = 142,000 yuan, indicating that as the equipment health declines and the impact of errors increases, the maintenance cost increases significantly.

[0120] In terms of dynamic economic parameter calculation, the environmental loss coefficient calculation result is: =1.26, reflecting the accelerated impact of the marine environment on the loss of equipment value. The design workload of the equipment is 87,600 hours, the actual workload is 18,520 hours, and the standard depreciation rate is 0.10. According to the dynamic depreciation rate calculation formula, the current dynamic depreciation rate is obtained =0.029.

[0121] Based on the failure frequency, expected maintenance cost and error weight coefficient, the research team determined the spare parts demand. According to historical consumption statistics, the number is 25. Since the failure frequency of 0.12 exceeds the threshold of 0.1, the expected maintenance cost accounts for the original value of the equipment, which is 14.2 / 280=0.051, which exceeds the threshold of 0.05, and the error weight coefficient of 1.32 exceeds the threshold of 1.2, the spare parts demand is adjusted to =25×1.2×1.3×1.15=44.85≈45 pieces.

[0122] As shown in Table 2, the equipment operating parameter statistics record in detail the changes in key indicators during the monitoring period.

[0123] Table 2 Statistical data of equipment operating parameters

[0124] The marine asset value assessment model constructed by the research team was trained using historical data from 800 devices over two years. The model takes operating intensity, corrosion index, failure frequency, expected maintenance cost, error stability matrix, and error change matrix as input parameters. After processing the error feature fusion layer and combining it with time series data analysis, the remaining service life of the equipment is predicted to be 6.3 years. The original value of the equipment is 2.8 million yuan. After calculation by the value assessment model, the current equipment value assessment result is =2.468 million yuan.

[0125] Based on changes in the equipment health index, expected maintenance costs, equipment value assessment results, and error weight coefficients, the financial business event recognition rule library automatically identifies three types of financial business events. The first is the equipment depreciation event. Since the current dynamic depreciation rate is 0.029, it triggers the need to generate monthly depreciation vouchers. The second is the maintenance cost event. The expected maintenance cost of 142,000 yuan exceeds the budget threshold of 120,000 yuan, and the error weight coefficient of 1.32 is greater than 1.0, triggering the generation of maintenance cost vouchers. The third is the spare parts procurement event. The spare parts demand of 45 pieces exceeds the current inventory of 35 pieces, and the error weight coefficient shows an increased risk of equipment failure, triggering the need to generate procurement vouchers.

[0126] As shown in Table 3, the financial business event recognition results record various financial processing requirements automatically identified by the system.

[0127] Table 3 Financial business event recognition results

[0128] During the automatic accounting account matching process, the system invokes preconfigured accounting account mapping rules. The equipment depreciation event corresponds to the fixed asset depreciation account, with a voucher amount of 246.8 × 0.029 = 71,500 yuan. The maintenance expense event corresponds to the administrative expense account. Because the error weight coefficient of 1.32 exceeds 1.2, a 5% uncertainty adjustment is added to the base amount of 142,000 yuan, resulting in a final voucher amount of 149,100 yuan. The spare parts procurement event corresponds to the raw materials procurement account. The spare parts unit price is 620 yuan, the required quantity is 45 pieces, and the total amount is 27,900 yuan.

[0129] Generated financial voucher templates undergo a multi-level compliance check using a rules engine. This includes voucher element integrity verification, confirming that all required accounting subjects, amounts, and summary information are present; debit / credit balance verification, ensuring that the debit amount on each voucher equals the credit amount; amount rationality verification, confirming that the amount is within a reasonable range by comparing it with historical data; and business logic consistency verification, ensuring that the voucher content and the triggering business event are logically linked.

[0130] As shown in Table 4, the compliance verification results show the passing status of various verification indicators.

[0131] Table 4 Compliance verification results

[0132] After verification, the system automatically enters the financial voucher into the company's financial management system. A complete audit trail is also generated, documenting the entire process from data collection, error analysis, event identification, to voucher generation. This audit trail includes the timestamp, operation details, relevant parameters, and results of each processing step, ensuring complete traceability of the financial processing process. The entire processing took 42 minutes, significantly improving efficiency compared to the four hours required for manual processing.

[0133] This invention addresses the core technical issues of asset management and financial processing for marine monitoring equipment. Traditional methods rely primarily on manual inspections and subjective judgment to assess equipment status, using a fixed depreciation rate to calculate asset value, and relying on manual experience to determine maintenance needs and spare parts procurement timing. Financial voucher generation relies entirely on manual operations by accountants. This invention offers significant improvements over traditional methods: In terms of equipment status assessment accuracy, multidimensional error analysis improves assessment accuracy from 76% to 89% using traditional methods. In asset value calculation, a dynamic depreciation rate reduces valuation deviation from 18% to 6% compared to a fixed depreciation rate. In terms of maintenance cost prediction, prediction accuracy improves from 68% based on traditional empirical judgment to 83%. In terms of financial processing efficiency, automated voucher generation reduces processing time from 4 hours to 0.7 hours, and improves processing accuracy from 92% with manual operations to 98%. These technological advances make asset management of marine monitoring equipment more accurate and efficient, providing more reliable technical support for marine scientific research and monitoring.

[0134] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A method for generating financial vouchers based on an ocean monitoring platform, characterized in that: include: IoT sensors collect real-time operating status data, environmental parameter data, and equipment measurement data from ocean monitoring equipment to establish an equipment operation database. This database also records maintenance history data and dynamically adjusts data collection frequency. Extracting equipment measurement data from the equipment operation database to analyze the time series change characteristics and construct a floating change matrix. Analyzing the floating change matrix using a Bayesian model to obtain a comprehensive error relationship matrix. Singular value decomposition is performed on the comprehensive error relationship matrix to obtain an error stability matrix and an error change matrix. The error change matrix is ​​input into a marine equipment error classifier for classification to obtain an error classification result. Based on the error classification result, an error weight coefficient is calculated using a gated weight function. Combined with the error classification results, the operating status data is analyzed and anomaly detected to calculate the equipment health index and expected maintenance cost; the dynamic depreciation rate and spare parts demand are calculated; a marine asset value assessment model is established to calculate the equipment value assessment results; financial business events are automatically identified based on changes in the equipment health index, expected maintenance costs, equipment value assessment results, and error weight coefficients; based on financial business events, the accounting subject mapping rules are called to automatically match the corresponding accounting subjects, generate financial voucher templates, and enter them into the financial system.

2. The method for generating financial vouchers based on an ocean monitoring platform according to claim 1, characterized in that: In the step of calculating the dynamic depreciation rate and spare parts demand, the environmental loss coefficient is calculated based on the equipment health index and expected maintenance cost, combined with the operating intensity and corrosiveness index. The dynamic depreciation rate is calculated using the workload method combined with the environmental loss coefficient. The spare parts demand is determined based on the failure frequency, expected maintenance cost and error weight coefficient.

3. The method for generating financial vouchers based on an ocean monitoring platform according to claim 2, characterized in that: The data acquisition frequency adjustment coefficient is a frequency adjustment parameter calculated based on the operating intensity and the corrosiveness index, and is used to dynamically adjust the data acquisition interval of the IoT sensor.

4. The method for generating financial vouchers based on an ocean monitoring platform according to claim 3, characterized in that: The floating change matrix is ​​a dynamic change characteristic matrix constructed by mathematically modeling the time series change characteristics of the device measurement data, and reflects the fluctuation law of the device measurement accuracy.

5. The method for generating financial vouchers based on an ocean monitoring platform according to claim 4, characterized in that: The Bayesian model analysis process includes taking the measurement data change pattern in the floating change matrix as observation evidence, establishing the prior probability distribution of systematic error, random error, environmental interference error and drift error, calculating the posterior impact probability of various errors on different monitoring parameters through the Bayesian inference method, and constructing a comprehensive error relationship matrix that includes the correlation strength between error type and monitoring parameter.

6. The method for generating financial vouchers based on an ocean monitoring platform according to claim 5, characterized in that: The marine equipment error classifier is an error type recognition model built based on deep learning technology. It is used to automatically identify and classify different types of equipment measurement errors. The output error classification results include the probability distribution of each error type and the final classification label.

7. The method for generating financial vouchers based on an ocean monitoring platform according to claim 6, characterized in that: The calculation method of the gated weight function is based on the confidence score of each error type in the error classification result. When the system error confidence exceeds 0.8, the corresponding error weight coefficient is set to 1.5; when the random error confidence exceeds 0.7, the corresponding error weight coefficient is set to 0.8; when the environmental interference error confidence exceeds 0.6, the corresponding error weight coefficient is dynamically adjusted between 1.0 and 1.3 according to the corrosive index.

8. The method for generating financial vouchers based on an ocean monitoring platform according to claim 7, characterized in that: The marine asset value assessment model is an asset value prediction model constructed based on the time series data analysis method. It takes the operating intensity, corrosion index, failure frequency, expected maintenance cost, error stability matrix and error change matrix as input parameters, processes the error stability matrix and error change matrix through the error feature fusion layer, and combines time series data analysis to predict the remaining service life of the equipment.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program instructions, and when the program instructions are run in a computer, they are used to execute the method for generating financial vouchers based on an ocean monitoring platform according to any one of claims 1 to 8.

10. A financial voucher generation system based on an ocean monitoring platform, characterized in that: The computer-readable storage medium according to claim 9 is included, the system is any one of a computer, a server, and a single-chip microcomputer, the computer-readable storage medium is arranged in the system, and the system is provided with a microprocessor for executing program instructions stored in the computer-readable storage medium.

Images