Accounting method and system based on ocean multi-source business data, and medium

Abstract

The invention provides an accounting bookkeeping method based on ocean multi-source business data, a medium and a system, and belongs to the technical field of financial processing based on business data. Constructing a business data analysis engine to perform structured processing on the data to form standardized business event data, establishing an accounting rule knowledge base to store accounting processing rules and voucher generation templates, and introducing a fuzzy business event recognition mechanism to construct a clear business data classification system; calculating an ambiguity value, calling a subject association optimization function to optimize an accounting subject association network structure, performing compliance verification and logic auditing on the voucher draft to form a to-be-confirmed voucher list, pushing the to-be-confirmed voucher list to financial staff for auditing and confirming, and automatically writing the to-be-confirmed voucher list into an accounting information system to finish accounting. And finally generating a business data bookkeeping processing report recording processing track and a voucher generation result. The technical problem that automatic accurate bookkeeping based on a specific business scene cannot be realized at present is solved.

Description

Technical Field

[0001] This invention belongs to the field of financial processing technology based on business data. Specifically, it relates to an accounting method, medium, and system based on marine multi-source business data. Background Technology

[0002] In the financial management of marine monitoring, traditional accounting methods primarily rely on manual identification of business events, generating vouchers through manual entry or simple data import. This approach is inefficient and prone to errors when handling large amounts of complex business data. Existing automated accounting technologies mostly focus on standardized reimbursement approval processes and fund payment stages, employing fixed account mapping rules and template-based processing methods, lacking a deep understanding and adaptive capability for specific business scenarios. Current technologies struggle to effectively handle the intelligent matching of complex business information such as marine monitoring equipment operation data and maintenance records with accounting accounts, especially when faced with ambiguous business event classification boundaries and complex account relationships. Traditional methods cannot accurately identify and process this uncertain business data. In other words, existing technologies suffer from a lack of deep coupling between business data and accounting systems, hindering the achievement of automated and accurate accounting based on specific business scenarios. Summary of the Invention

[0003] In view of this, the present invention provides an accounting method, medium and system based on marine multi-source business data, which can solve the technical problem in the prior art that the business data and the accounting system lack deep coupling and cannot achieve automated and accurate accounting based on specific business scenarios.

[0004] The present invention is implemented as follows: The first aspect of the present invention provides an accounting method based on multi-source marine business data, comprising the following steps: collecting business data generated by monitoring equipment in a marine monitoring platform as the basic data source, and establishing a mapping relationship between business data and accounting subjects; constructing a business data parsing engine to perform structured processing and classification of business data, forming standardized business event data; establishing an accounting rule knowledge base to store accounting processing rules and voucher generation templates corresponding to different business events; introducing a fuzzy business event identification mechanism to construct a clear business data classification system, calculating the fuzziness value of matching business events with subjects, calling a subject association optimization function to optimize the accounting subject association network structure, automatically matching the standardized business event data with the accounting processing rules in the accounting rule knowledge base, and generating corresponding draft accounting vouchers; performing compliance verification and logical review on the generated draft accounting vouchers to form a list of vouchers to be confirmed; pushing the verified list of vouchers to be confirmed to financial personnel for final review and confirmation; after confirmation by financial personnel, the system automatically writes the voucher data into the accounting information system, completing the automatic accounting process; and generating a business data accounting processing report.

[0005] The business data includes equipment operating parameters, monitoring result data, and equipment maintenance records. The standardized business event data includes event type, amount information, timestamp, and associated account code.

[0006] The business data parsing engine refers to a software module used to convert raw data generated by marine monitoring equipment into structured data that can be recognized and processed by the financial system. The business data parsing engine achieves data standardization processing through data format conversion and field mapping.

[0007] The accounting rules knowledge base refers to a database system that stores accounting processing standards and voucher generation rules under various business scenarios. The accounting rules knowledge base includes account correspondence, calculation logic and audit standards, providing a decision-making basis for automatic bookkeeping.

[0008] The standardized business event data refers to structured data formed by organizing the original business data according to a unified format and standard. Standardized business event data facilitates subsequent automated processing and rule matching.

[0009] The fuzzy business event identification mechanism refers to an identification method used to handle uncertain and ambiguous features in business data. The fuzzy business event identification mechanism uses fuzzy set theory to quantify the degree of uncertainty of event attributes and solves the problem of unclear business event classification boundaries.

[0010] The aforementioned explicit business data classification system refers to a classification system that establishes a precise correspondence between business data and accounting subjects. An explicit business data classification system ensures that each business event can find a unique corresponding accounting treatment method, eliminating ambiguity in the data processing process.

[0011] The game theory model construction includes an upper-level model aimed at maximizing the accuracy of accounting information and a lower-level model aimed at minimizing processing costs. The objective function of the upper-level model mainly consists of the accuracy index of the business data classification system, the accuracy level of fuzzy business event identification, the weight coefficient of accounting information accuracy, and coupling terms.

[0012] The aforementioned draft accounting voucher refers to the preliminary voucher information automatically generated by the system based on business data and accounting rules. The draft accounting voucher needs to be verified and confirmed before it can be formally entered into the accounts.

[0013] The accounting rules include debit and credit account matching rules, amount calculation formulas, and voucher summary generation rules. The business data accounting processing report includes data source, processing time, and generated voucher number.

[0014] The fuzziness value refers to a numerical indicator that quantifies the degree of matching between business events and accounting subjects. The fuzziness value ranges from 0 to 1, and the closer the value is to 1, the higher the degree of matching. The fuzziness value is used to determine the accuracy of the attribution of business events.

[0015] The subject association optimization function is used to optimize the relationship between accounting subjects and construct the optimal network structure. The input includes the set of accounting subject nodes, the inter-subject association weight matrix, business event frequency statistics, and network connectivity constraints. The output is the optimized subject association network topology. The subject association optimization function finds the minimum weight path connecting each subject node through the minimum spanning tree algorithm.

[0016] The compliance verification step specifically involves checking the accounting standards compliance of the generated draft accounting vouchers. The verification includes debit and credit balance verification, account code validity check, and amount reasonableness judgment. The compliance verification ensures that the voucher content complies with financial regulations and prevents vouchers that violate accounting systems from entering the system.

[0017] The processing trajectory refers to detailed information on the processing status of each stage of the entire process from data collection to the final generation of accounting vouchers. The processing trajectory includes data flow path, processing time nodes, operator identification, and processing result status.

[0018] The upper-level model has clearly defined constraints that limit the total accuracy of the business data classification system to no more than the maximum allowable value and ensure that the accuracy levels of each item are non-negative. The lower-level model's objective function is mainly composed of fuzzy value calculation cost, subject association optimization function execution cost, processing activity unit cost, execution intensity, and coupling terms.

[0019] The lower-level model constraints require that the total intensity of the processing activities be no less than the minimum requirement and that the intensity of each activity be non-negative. The coupling term represents the mutual influence between accuracy and cost by clarifying the correlation coefficient between the business data classification system and the fuzzy business event identification mechanism, and quantifies the degree of coordination and optimization between the two objectives and the degree of influence of the fuzziness value on the decision result.

[0020] A second aspect of the present invention provides a computer-readable storage medium storing program instructions that, when executed in a computer, are used to perform the aforementioned accounting method based on multi-source marine business data.

[0021] A third aspect of the present invention provides an accounting system based on business data, comprising the aforementioned computer-readable storage medium, wherein the system is any one of a computer, a server, or a microcontroller, the computer-readable storage medium is disposed within the system, and the system is provided with a microprocessor for executing program instructions stored in the computer-readable storage medium.

[0022] This invention establishes an intelligent mapping relationship between business data and accounting subjects by constructing a business data parsing engine and an accounting rule knowledge base, combined with a fuzzy business event recognition mechanism and a subject association optimization function. This solves the technical problem of the lack of deep coupling between business data and the accounting system. The invention employs standardized business event data processing and fuzziness value calculation methods, enabling accurate identification and classification of business events with uncertain characteristics. By clarifying the business data classification system, it eliminates the ambiguity problems that traditional methods encounter when handling complex business scenarios, significantly improving the accuracy and adaptability of automated bookkeeping. Furthermore, this invention optimizes the balance between accuracy and cost through a two-layer game model, achieving automated and accurate bookkeeping based on specific business scenarios. This completely changes the limitations of traditional bookkeeping methods that rely on manual judgment and fixed templates, providing an effective technical solution for financial automation in the field of marine monitoring. Attached Figure Description

[0023] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

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

[0025] like Figure 1 The diagram shown is a flowchart of an accounting method based on multi-source marine business data provided by the first aspect of the present invention. This method includes the following steps: S01. Collect business data generated by monitoring equipment in the marine monitoring platform as the basic data source, and establish a mapping relationship between business data and accounting subjects. Business data includes equipment operating parameters, monitoring result data, and equipment maintenance records. S02. Construct a business data parsing engine to perform structured processing and classification of the business data to form standardized business event data, wherein the standardized business event data includes event type, amount information, timestamp, and associated account code; S03. Establish an accounting rules knowledge base to store accounting processing rules and voucher generation templates corresponding to different business events. The accounting processing rules include debit and credit account matching rules, amount calculation formulas, and voucher summary generation rules. S04. Introduce a fuzzy business event recognition mechanism, construct a clear business data classification system, calculate the fuzziness value of matching business events with accounts, call the account association optimization function to optimize the accounting account association network structure, automatically match standardized business event data with accounting processing rules in the accounting rule knowledge base, and generate corresponding accounting voucher drafts. S05. Perform compliance verification and logical review on the generated draft accounting vouchers. The verification includes debit and credit balance verification, account code validity check, and amount reasonableness judgment, and form a list of vouchers to be confirmed. S06. The list of vouchers that have passed the verification and are pending confirmation will be pushed to the finance staff for final review and confirmation. After the finance staff confirms, the system will automatically write the voucher data into the accounting information system and complete the automatic accounting process. S07. Generate a business data accounting processing report, which records the processing trajectory and voucher generation results of each business data transaction, providing data support for subsequent auditing and querying. The business data accounting processing report includes the data source, processing time, and generated voucher number.

[0026] Among them, the business data parsing engine is a software module used to convert the raw data generated by marine monitoring equipment into structured data that can be recognized and processed by the financial system. The business data parsing engine achieves data standardization processing through data format conversion and field mapping.

[0027] The accounting rules knowledge base is a database system that stores accounting processing standards and voucher generation rules for various business scenarios. The accounting rules knowledge base includes account correspondence, calculation logic and audit standards, providing a basis for decision-making for automatic bookkeeping.

[0028] Standardized business event data is structured data formed by organizing raw business data according to a unified format and standard. Standardized business event data facilitates subsequent automated processing and rule matching.

[0029] Among them, the draft accounting voucher is the preliminary voucher information automatically generated by the system based on business data and accounting processing rules. The draft accounting voucher needs to be verified and confirmed before it can be officially entered into the accounts.

[0030] Among them, the fuzzy business event identification mechanism is an identification method used to handle the uncertainty and ambiguity in business data. The fuzzy business event identification mechanism uses fuzzy set theory to quantify the degree of uncertainty of event attributes and solves the problem of unclear business event classification boundaries.

[0031] Among them, clarifying the business data classification system is a classification system that establishes a precise correspondence between business data and accounting subjects. Clarifying the business data classification system ensures that each business event can find a unique corresponding accounting treatment method, eliminating ambiguity in the data processing process.

[0032] The fuzziness value is a numerical indicator that quantifies the degree of matching between business events and accounting subjects. The fuzziness value ranges from 0 to 1. The closer the value is to 1, the higher the degree of matching. The fuzziness value is used to determine the accuracy of the attribution of business events.

[0033] The subject association optimization function is used to optimize the relationship between accounting subjects and construct the optimal network structure. The input includes the set of accounting subject nodes, the inter-subject association weight matrix, business event frequency statistics, and network connectivity constraints. The output is the optimized subject association network topology. The subject association optimization function uses the minimum spanning tree algorithm to find the minimum weight path connecting each subject node.

[0034] Among them, compliance verification is the process of checking the accounting standards compliance of the generated draft accounting vouchers. Compliance verification ensures that the content of the vouchers meets the requirements of financial regulations and prevents vouchers that violate accounting systems from entering the system.

[0035] The processing track records detailed information about the processing of business data at each stage from data collection to the final generation of accounting vouchers. The processing track includes data flow path, processing time nodes, operator identification, and processing result status.

[0036] The game theory model consists of an upper-level model aimed at maximizing the accuracy of accounting information and a lower-level model aimed at minimizing processing costs. The objective function of the upper-level model is mainly composed of the accuracy index of the explicit business data classification system, the accuracy level of fuzzy business event identification, the weighting coefficient of accounting information accuracy, and coupling terms. The constraints limit the total accuracy of the explicit business data classification system to not exceed the maximum allowable value and the accuracy levels of each item to be non-negative. The objective function of the lower-level model is mainly composed of the cost of fuzziness value calculation, the execution cost of the account association optimization function, the unit cost of processing activities, execution intensity, and coupling terms. The constraints require that the total execution intensity of processing activities not be less than the minimum required value and that the execution intensity of each item to be non-negative. The coupling terms represent the mutual influence between accuracy and cost through the correlation coefficient between the explicit business data classification system and the fuzzy business event identification mechanism, quantifying the degree of coordination and optimization between the two objectives and the degree of influence of fuzziness values ​​on the decision results.

[0037] The specific implementation methods of the above steps are described in detail below.

[0038] The specific implementation of step S01 involves establishing a real-time data connection between the data acquisition interface module and various monitoring devices of the marine monitoring platform. A polling mechanism is used to periodically collect device operating parameters at preset time intervals, ranging from 30 to 300 seconds, to ensure data real-time performance and integrity. The system employs multi-threaded concurrent processing technology to simultaneously acquire business data from multiple monitoring devices, including equipment operating status parameters such as physical quantities like temperature, pressure, and current, and monitoring result data such as seawater salinity and dissolved oxygen concentration. The system stores chemical indicators such as pH values, as well as equipment maintenance records such as maintenance time, repair costs, and replacement parts information. Raw business data is stored in a relational database, and a mapping table between business data and accounting subjects is established. This mapping table uses a key-value pair structure, associating each type of business data with its corresponding accounting subject code. The mapping accuracy threshold is set to above 95%. When the mapping accuracy falls below this threshold, the system automatically triggers a manual review mechanism.

[0039] The specific implementation of step S02 involves constructing a business data parsing engine based on rule engine and pattern recognition technology. This engine first cleanses the collected raw business data, identifying and filtering data points outside the normal range using an outlier detection algorithm. Outlier determination uses a 3-standard-deviation criterion; data points deviating from the mean by more than 3 standard deviations are marked as outliers. Next, a data format conversion module unifies the raw data of different formats into a standard structured data format, including timestamp standardization, numerical precision unification, and character encoding standardization. A field mapping algorithm establishes a correspondence between the fields of the raw data and the target fields of the standardized event data, forming standardized business event data containing four core elements: event type, monetary information, timestamp, and associated account code. Event type classification uses a hierarchical clustering algorithm to group similar business events into the same category, with a classification accuracy requirement of over 90%.

[0040] The specific implementation of step S03 involves establishing an accounting rule knowledge base based on knowledge graph technology. This knowledge base adopts a three-layer architecture: a bottom layer for data storage, a middle layer for rule processing, and a top layer for interface services. The data storage layer uses a graph database to store the relationships and processing rules between accounting subjects. Nodes represent accounting subjects, edges represent the relationships between subjects, and edge weights represent the strength of the relationship. The rule processing layer implements the logical processing of debit and credit account matching rules. It uses a semantic similarity-based matching algorithm to calculate the similarity score between business events and accounting subjects. The similarity threshold is set at 0.8; matching results higher than this threshold are considered valid matches. The amount calculation formula is implemented using an expression parser, supporting complex mathematical operations and conditional judgment logic. The voucher summary generation rules are based on template matching and natural language processing technology. Through predefined summary templates and a dynamic parameter replacement mechanism, it automatically generates voucher summary text that conforms to accounting standards.

[0041] The specific implementation of step S04 involves introducing a business event recognition mechanism based on fuzzy set theory. This mechanism first constructs a clear business data classification system covering all business scenarios. A recursive classification algorithm is used to classify business data at multiple levels according to dimensions such as business nature, amount range, and time characteristics. The classification depth is set to 3 to 5 levels to ensure fine-grained and accurate classification. Fuzziness value calculation uses a fuzzy membership function. Input parameters include the feature vector of the business event and the attribute vector of the accounting subject. The initial matching degree is obtained by calculating the cosine similarity between the two vectors, and then corrected by combining the weight coefficients of the business rules, ultimately obtaining a fuzziness value between 0 and 1. The subject association optimization function uses a minimum spanning tree algorithm. Accounting subjects are used as nodes in the graph, and the reciprocal of the frequency of business associations between subjects is used as the edge weight. The Kruskal algorithm is used to find the minimum weight spanning tree connecting all subject nodes, constructing the optimal subject association network structure. The automatic matching process uses a greedy algorithm, prioritizing the matching scheme with the highest fuzziness value. When multiple matching schemes with similar fuzziness values ​​exist, the scheme with the highest historical usage frequency is selected, generating the corresponding accounting voucher draft.

[0042] Step S05 involves performing multi-level compliance checks and logical audits on the generated draft accounting vouchers. The verification process employs an automated checking mechanism driven by a rule engine. Debit / credit balance verification calculates the difference between the total debit amount and the total credit amount for each voucher. The absolute value of this difference must be less than 0.01 yuan; otherwise, the system marks it as an unbalanced voucher and requires regeneration. Account code validity checks verify the existence and validity of account codes by querying the master data table of accounting accounts, while also checking the account usage status and permission settings to ensure that the used account codes comply with current accounting regulations. Amount reasonableness judgment uses statistical analysis methods, calculating the historical amount distribution of similar business events to identify abnormal amounts exceeding the normal range. The abnormal threshold is set at twice the standard deviation of the historical mean; amounts exceeding this range require manual confirmation. Logical audits include business logic consistency checks and time logic reasonableness verification, ensuring that the business content of the voucher matches the actual business process and that the voucher date is within a reasonable timeframe. Vouchers that pass verification form a list of vouchers awaiting confirmation; vouchers that fail verification are returned to the reprocessing process.

[0043] The specific implementation of step S06 involves establishing a human-machine collaboration mechanism for financial personnel review and confirmation. The system categorizes and sorts the list of vouchers to be confirmed according to business type and amount, prioritizing the display of high-value and high-risk vouchers for financial personnel to review. The review interface adopts a visual design, providing functions such as voucher details display, business data traceability, and viewing related attachments. Financial personnel can confirm, modify, or reject vouchers through the interface. The confirmation process uses digital signature technology to ensure the non-repudiation and data integrity of the operation. Each confirmation operation records the operator's identity, operation time, and operation content. The system automatically writes the voucher data confirmed by financial personnel into the accounting information system through a standardized interface. The writing process uses a transaction processing mechanism to ensure data consistency and integrity. When the writing fails, the system automatically retryes, with the number of retries set to 3. If it still fails, it proceeds to the exception handling process. After automatic posting is completed, the system sends a confirmation notification to relevant personnel and updates the voucher status to "posted."

[0044] The specific implementation of step S07 involves generating a business data accounting processing report covering the entire processing flow. This report uses a structured data format and includes key information such as data source identifier, processing time node, generated voucher number, processing status, and exception information. Report generation employs template engine technology, automatically generating a uniformly formatted processing report through predefined report templates and a dynamic data filling mechanism. The processing trajectory record uses a chained storage structure, recording the complete processing process of each business data item from acquisition to final generation of accounting vouchers in chronological order, including each stage of data flow, processing time point, operator identifier, intermediate processing results, and final processing status. The system assigns a unique processing number to each business data item, allowing for the tracing of the complete processing history and supporting subsequent audit queries and problem investigation. The report data uses compressed storage technology to reduce storage space usage, while an indexing mechanism improves query efficiency. The report retention period is set at 7 years to meet the regulatory requirements for accounting record management.

[0045] The specific implementation of the game theory model involves constructing a two-layer optimization model to find the optimal balance between the accuracy of accounting information and processing costs. The upper-layer model aims to maximize the accuracy of accounting information. The input parameters of the objective function include the accuracy index of the explicit business data classification system, the accuracy level of fuzzy business event identification, the weight coefficient of accounting information accuracy, and the coupling term coefficient representing the degree of correlation between the upper and lower-layer models. The constraint condition requires that the sum of all accuracy indices does not exceed the preset maximum allowable value of 1.0, and that all index values ​​are non-negative. The lower-layer model aims to minimize processing costs. The input parameters of the objective function include the unit cost of fuzzy value calculation, the execution cost of the account association optimization function, the unit cost of various processing activities, the corresponding execution intensity parameters, and the coupling term coefficient. The constraint condition requires that the sum of the execution intensity of various processing activities is not less than the preset minimum requirement value of 0.6, and that all execution intensity values ​​are non-negative. The coupling term is represented by the correlation coefficient between the explicit business data classification system and the fuzzy business event recognition mechanism. This coefficient quantifies the impact of improved accuracy on increased costs and the impact of changes in fuzziness values ​​on the final decision result. The correlation coefficient ranges from 0.1 to 0.9, with a larger value indicating a stronger coupling between the two objectives. The model solution employs a hybrid optimization algorithm combining genetic algorithms and gradient descent. First, the genetic algorithm searches for an approximate region of the global optimum in the solution space. Then, gradient descent is used to solve for the exact solution within this region, ultimately yielding the parameter configuration scheme that optimizes the overall system performance.

[0046] It should be noted that the fuzzy business event identification mechanism adopted in this invention has significant technical advantages over traditional deterministic classification methods. Traditional methods, when processing complex business data generated by marine monitoring equipment, often employ fixed threshold judgments and rigid classification rules. This approach is prone to misjudgment and classification errors when faced with ambiguous business event boundaries and overlapping features. This invention, by introducing fuzzy set theory, quantifies the uncertain characteristics of business events and evaluates the matching degree between business events and accounting subjects by calculating fuzziness values. This method effectively addresses the ambiguity and uncertainty issues present in business data. The fuzzy business event identification mechanism not only identifies clearly attributed business events but, more importantly, can reasonably handle fuzzy events at classification boundaries. By continuously evaluating fuzziness values, it avoids the limitations of traditional binary classification methods, significantly improving the accuracy and adaptability of business event identification.

[0047] The subject association optimization function employs the minimum spanning tree algorithm to construct the optimal accounting subject association network structure, demonstrating significant technical advantages over traditional static subject mapping methods. Traditional methods typically use pre-defined subject correspondence tables and fixed mapping rules. This static mapping approach cannot adapt to changes in business scenarios and the dynamic adjustment requirements of subject relationships, and is prone to mapping errors or omissions when handling complex cross-subject business events. The subject association optimization function of this invention, by constructing an optimization model that includes a set of accounting subject nodes, an inter-subject association weight matrix, business event frequency statistics, and network connectivity constraints, can dynamically adjust the association relationships between subjects, finding the minimum weight path connecting all subject nodes, thereby constructing the optimal subject association network topology. This dynamic optimization mechanism not only improves the accuracy of subject matching but also adapts to the needs of subject relationship adjustments brought about by business development and changes in accounting regulations, achieving intelligent management and continuous optimization of subject association relationships.

[0048] The synergistic effect of the fuzzy business event identification mechanism and the account association optimization function forms the core competitive advantage of this invention compared to existing technologies. The combination of the two creates a complete intelligent processing chain from business event identification to account matching. The fuzzy business event identification mechanism is responsible for accurately identifying and quantifying the uncertainty characteristics of business events, providing high-quality input data for the account association optimization function. The account association optimization function, based on this precise business event information, constructs the optimal account association network, providing the best matching path for the fuzzy identification results. This synergistic mechanism achieves a balance between accuracy and cost through a two-layer game model. The fuzzy identification mechanism ensures the accuracy of business event classification, while the account association optimization function guarantees the optimality of the matching results. The two achieve mutual feedback and continuous optimization through coupling terms. Compared to the single processing mode of traditional methods, this synergy can handle more complex business scenarios, adapt to more diverse accounting needs, and achieve deep coupling between business data and the accounting system, providing a reliable technical guarantee for automated and accurate bookkeeping.

[0049] A second aspect of the present invention provides a computer-readable storage medium storing program instructions that, when executed in a computer, are used to perform the aforementioned accounting method based on multi-source marine business data.

[0050] A third aspect of the present invention provides an accounting system based on business data, comprising the aforementioned computer-readable storage medium, wherein the system is any one of a computer, a server, or a microcontroller, the computer-readable storage medium is disposed within the system, and the system is provided with a microprocessor for executing program instructions stored in the computer-readable storage medium.

[0051] Specifically, the principle of this invention is as follows: The core of this invention's solution to the problem of insufficient deep coupling between business data and accounting systems lies in establishing a full-chain intelligent processing mechanism from business data to accounting vouchers. First, the business data parsing engine transforms the raw operational data of marine monitoring equipment into standardized business event data containing event type, amount information, timestamps, and associated account codes through structured processing. This standardization lays the data foundation for subsequent automated matching. Second, the accounting rule knowledge base stores accounting processing rules and voucher generation templates for different business scenarios. Through the organic combination of debit / credit account matching rules, amount calculation formulas, and voucher summary generation rules, a deep integration of business logic and accounting logic is achieved. The fuzzy business event identification mechanism is a key innovation of this invention. By quantifying the uncertainty of event attributes using fuzzy set theory and calculating the fuzziness value of business event and account matching, it effectively solves the problem of unclear business event classification boundaries. The account association optimization function uses the minimum spanning tree algorithm to optimize the association relationship between accounting accounts, constructing an optimal network structure to ensure the accuracy and systematic nature of account matching. The two-level game model achieves coordinated optimization of accounting accuracy and processing efficiency by maximizing the accuracy objective in the upper level and minimizing the cost objective in the lower level, as well as designing coupling terms between the two. This ensures the stable operation of the system and accurate accounting capabilities in complex business environments.

[0052] The following provides a specific embodiment 1 of the present invention, and the specific implementation of each step in this embodiment 1 is described in detail below.

[0053] The specific implementation of step S01 involves establishing a real-time data connection between the data acquisition interface module and various monitoring devices of the marine monitoring platform, and establishing a mapping relationship between business data and accounting subjects. The mapping accuracy calculation formula is as follows: In the formula, For mapping accuracy; The number of data rows that are correctly mapped; This represents the total number of mapped data entries. When... At this time, the system automatically triggers a manual review mechanism. The parameter acquisition method is as follows: The data is obtained through manual verification, including step 1: randomly selecting mapping result samples for manual verification; and step 2: counting the number of correctly verified samples. It is obtained through automatic counting by the system.

[0054] The specific implementation of step S02 involves building a business data parsing engine to perform structured processing on the business data. Outlier detection uses a 3-standard-deviation criterion, and the judgment formula is as follows: In the formula, For the first data points; This represents the data mean. Let be the standard deviation of the data. The formula for data standardization is as follows: In the formula, These are the standardized data values. The formula for calculating the accuracy of event type classification is as follows: In the formula, For classification accuracy; The number of events that are correctly classified; Given the total number of categorized events, the requirement is... The parameter acquisition method is as follows: Obtained through statistical calculations of historical data; Obtained through historical data variance calculation; The results were obtained through a classification algorithm.

[0055] The specific implementation of step S03 involves establishing an accounting rules knowledge base and employing a semantic similarity matching algorithm. The similarity calculation formula is as follows: In the formula, Score the semantic similarity. For business event feature vectors; For accounting subject feature vectors; This represents the vector dot product operation; and Let represent the magnitudes of the vectors, respectively. When When the matching result is valid, the feature vector is constructed as follows: ; In the formula, For the first business event Each feature component; For the first accounting subject Each feature component; This refers to the number of feature dimensions, typically ranging from 50 to 100; superscript This represents the vector transpose operation. The parameters are obtained as follows: Obtained through quantitative analysis of business event attributes; Obtained through quantitative analysis of accounting subject attributes.

[0056] The specific implementation of step S04 involves introducing a fuzzy business event recognition mechanism. The fuzziness value is calculated using a fuzzy membership function, and the calculation formula is as follows: In the formula, This is the final ambiguity value, ranging from 0 to 1; The aforementioned semantic similarity score; For business rule matching degree; Normalized value for historical usage frequency; Let be the weighting coefficient, satisfying and The formula for calculating the matching degree of business rules is as follows: In the formula, The number of rules to be matched; This represents the total number of rules. The subject association optimization function uses the minimum spanning tree algorithm, and the weight matrix is ​​defined as follows: In the formula, Subject With subjects The weights between them; and These are subject number indexes; Subject With subjects The frequency of business associations; To avoid small constants that divide by zero, a value of 0.001 is used. The parameter is obtained as follows: Obtained through matching and calculation by the rule engine; Obtained through statistical normalization of historical data; Obtained through business data statistics. Weighting coefficients. The default values ​​are 0.5, 0.3, and 0.2, respectively.

[0057] The specific implementation of step S05 involves verifying the compliance of the draft accounting voucher. The debit-credit balance verification formula is as follows: In the formula, For the first Amount of each debit account; For the first Amount of each credit item; The debit account number, ranging from 1 to... ; The credit account number, with values ​​ranging from 1 to... ; Number of debit accounts; Number of credit accounts; To balance the tolerance, a value of 0.01 yuan is set. The reasonableness of the amount is judged using statistical analysis methods; the formula for judging abnormal amounts is as follows: In the formula, This is the current voucher amount; This is the historical average amount for similar business transactions; The standard deviation of historical amounts for similar business transactions. The comprehensive compliance score is calculated using the following formula: In the formula, A comprehensive compliance score; These are indicator functions for loan balance, account coding, amount reasonableness, and logical consistency, respectively. They take the value 1 when the check passes and 0 otherwise. Let be the weighting coefficient, satisfying The parameter acquisition method is as follows: and Obtained through statistical calculation of historical business data; weighting coefficient The default values ​​are 0.4, 0.2, 0.2, and 0.2, respectively.

[0058] The specific implementation methods for steps S06-S07 are the same as those described above, and will not be repeated in detail here.

[0059] The specific implementation of the game theory model involves constructing a two-layer optimization model. The objective function of the upper-layer model is as follows: In the formula, This represents the objective function value of the upper-level model. To clarify the accuracy indicators of the business data classification system; To improve the accuracy level of fuzzy business event recognition; This is a weighting coefficient for the accuracy of accounting information. For coupling terms; These are the weight parameters for the upper-level model; This represents the upper-level coupling coefficient. The upper-level constraint conditions are: ; The objective function of the lower-level model is as follows: In the formula, The objective function value of the lower-level model; Calculate the cost for the ambiguity value; Optimize the execution cost of the subject association function; To handle the unit cost of the activity; For execution strength; These are the weight parameters for the lower-level model; This represents the lower-level coupling coefficient. The lower-level constraint conditions are: ; In the formula, To handle the total number of activity types; For the first The execution intensity of class processing activities. The formula for calculating coupling terms is as follows: In the formula, To clarify the correlation coefficient between the business data classification system and the fuzzy business event identification mechanism, the value ranges from 0.1 to 0.9; The ambiguity value influence coefficient ranges from 0.05 to 0.15. The two-layer model is solved using a hybrid optimization algorithm combining genetic algorithm and gradient descent. The fitness function of the genetic algorithm is defined as follows: In the formula, This is the fitness value; To constrain the penalty coefficient for violations, a value of 10 is set. For the first The degree of violation of a constraint; Let be the total number of constraints. The gradient descent update formula is as follows: In the formula, and The first Step and the first The parameter vector of the step; This represents the number of iteration steps. The learning rate, ranging from 0.001 to 0.01; This represents the gradient of the loss function with respect to the parameters. The loss function is defined as follows: The parameter acquisition method is as follows: The accuracy is obtained through classification accuracy testing, including step 1: constructing a test dataset; step 2: running the classification algorithm; and step 3: calculating the accuracy. The accuracy is obtained through accuracy testing, including step 1: setting benchmark data; step 2: running the recognition algorithm; and step 3: calculating the accuracy index. Cost accounting is used to obtain the data, including step 1: calculating the time required; step 2: calculating hardware resource consumption; and step 3: converting the cost to monetary value. Weighting parameters are also included. The default values ​​are 0.4, 0.35, and 0.25 respectively; The default values ​​are 0.5, 0.3, and 0.2 respectively; correlation coefficient The default value is 0.5; influence coefficient The default value is 0.1.

[0060] In this embodiment, it should be noted that the formula for calculating mapping accuracy is... Based on the principle of statistical accuracy assessment, this formula achieves precise control over the quality of automatic classification of marine monitoring data by quantifying the correctness of the mapping relationship between business data and accounting subjects. Compared with the traditional method of manual item-by-item verification, this formula can monitor the mapping quality in real time and automatically trigger a review mechanism when the accuracy rate is lower than the threshold, thereby significantly improving the reliability and processing efficiency of converting marine business data into accounting information.

[0061] Outlier detection formula By adopting the three-standard-deviation criterion in normal distribution theory, this method automatically identifies abnormal data points generated by monitoring equipment through statistical methods. Compared with the existing technology that relies on human experience for judgment, this formula provides an objective and quantitative standard for identifying outliers. It can effectively filter out erroneous data caused by equipment failure or environmental interference, ensuring that subsequent accounting processing is based on reliable business data sources and significantly reducing accounting information errors caused by data quality issues.

[0062] Data standardization formula Based on the Z-score standardization principle, marine monitoring data with different dimensions and numerical ranges are converted into a unified standardized format. Compared with the practice in traditional accounting systems that requires manual adjustment of different data formats, this formula realizes the automatic unified processing of multi-source heterogeneous business data, eliminates the impact of data scale differences on subsequent analysis and matching processes, and lays a solid foundation for establishing standardized business event data.

[0063] Semantic similarity calculation formula By adopting the cosine similarity principle in the vector space model, the cosine value of the angle between the feature vector of a business event and the feature vector of an accounting subject is calculated to quantify their similarity. Compared with the simple correspondence method based on keyword matching in the existing technology, this formula can more accurately capture the deep semantic relationship between business events and accounting subjects, realize more accurate automatic matching, and significantly improve the accuracy and intelligence level of accounting subject selection.

[0064] Formula for calculating ambiguity value Based on fuzzy set theory and multi-attribute decision-making principle, this method comprehensively evaluates the matching degree between business events and accounting subjects by weightedly integrating information from three dimensions: semantic similarity, business rule matching degree, and historical usage frequency. Compared with the limitations of traditional methods that only consider a single matching standard, this formula achieves the organic combination of multi-dimensional information, can handle the uncertainty and ambiguity in business data, and significantly improves the processing accuracy and adaptability in complex business scenarios.

[0065] Subject-related optimization weight matrix formula Based on the weight design principle of the minimum spanning tree algorithm in graph theory, the optimal network structure is constructed by using the reciprocal of the frequency of business associations as the connection weight between accounts. Compared with the static approach of using fixed account associations in existing technologies, this formula can dynamically adjust the association strength between accounts according to actual business data, realizing adaptive optimization of the accounting account association network and significantly improving the accuracy of account matching and the flexibility of the system.

[0066] Lending-Loan Balance Verification Formula Based on the fundamental requirement of double-entry bookkeeping that debits and credits must be equal, this formula verifies the balance of vouchers by calculating the absolute value of the difference between the total debit amount and the total credit amount. Compared to the problem of calculation errors that are prone to occur in traditional manual bookkeeping, this formula provides an automated and accurate verification mechanism that can detect and correct imbalances in real time during the voucher generation stage, fundamentally eliminating the risk of accounting imbalances caused by human error.

[0067] Formula for judging the reasonableness of the amount Based on the anomaly detection theory in statistics, this method identifies abnormal amounts by comparing the deviation of the current voucher amount from the historical amount distribution of similar transactions. Compared with the subjective method in existing technologies that rely on the experience of auditors, this formula establishes an objective quantitative judgment standard, which can automatically identify abnormal amounts that may contain errors or fraud, and significantly improves the automation level and accuracy of accounting information quality control.

[0068] Upper-level objective function in a two-level game model and lower-level objective function Based on the theoretical framework of bi-level optimization in game theory, this model seeks the optimal balance by simultaneously considering two mutually constraining objectives: maximizing the accuracy of accounting information and minimizing processing costs. Compared to the limitations of traditional methods that simply pursue one objective, this model achieves coordinated optimization of accuracy and efficiency. It can minimize system operating costs while ensuring the quality of accounting information, and significantly improves the overall performance and practicality of the entire automated accounting system.

[0069] To better understand and implement this invention, the following is a specific application scenario example 2: A marine research team faced the technical challenge of converting a large amount of operational data generated by monitoring equipment into accounting vouchers during its deep-sea monitoring project. Traditional manual bookkeeping methods could not effectively handle the massive amounts of equipment operation data, monitoring result data, and maintenance record data generated daily. The research team decided to adopt an accounting method based on multi-source marine operational data to solve this technical problem. This method can achieve automated conversion from operational data to accounting vouchers.

[0070] The research team first collected operational data generated by various devices in the monitoring platform as the basic data source, including operating parameters of 15 deep-sea monitoring devices, detection results data from 3 water quality monitoring systems, and maintenance records for all devices. Equipment operating parameters included temperature sensor readings, pressure sensor values, current and voltage indices, etc. Water quality monitoring data included key indicators such as dissolved oxygen concentration, pH value, salinity, and turbidity. Maintenance records covered detailed information such as equipment maintenance time, replacement parts information, and maintenance costs. The research team established a mapping relationship between operational data and accounting categories, mapping electricity consumption generated by equipment operation to the manufacturing expenses category, data processing costs for monitoring results to the research and development expenditure category, and equipment maintenance costs to the administrative expenses category.

[0071] The construction of the business data parsing engine is a key technical component of the entire system. The research team designed a complete data processing architecture to achieve structured processing and classification of business data. Raw business data undergoes standardization processing through a data format conversion module, uniformly converting device data of different formats into structured data in JSON format. The field mapping module is responsible for mapping raw data fields to standard business event fields, ensuring data consistency and integrity. The processed standardized business event data includes clear event type identifiers, precise monetary information, accurate timestamp records, and corresponding associated account codes, laying a solid data foundation for subsequent automated matching.

[0072] The research team established a comprehensive accounting rules knowledge base, storing accounting processing rules and voucher generation templates corresponding to various business scenarios in marine monitoring projects. Debit and credit account matching rules define the specific accounts that should be debited and credited for different business events; amount calculation formulas specify the methods for extracting and calculating accounting amounts from business data; and voucher summary generation rules ensure that a standardized accounting voucher summary can be generated for each transaction. The research team entered 126 accounting processing rules into the knowledge base, covering accounting standards for various business processes such as equipment procurement, operation and maintenance, data processing, and personnel salaries.

[0073] The implementation of a fuzzy event identification mechanism is the core innovation of this method. The research team uses fuzzy set theory to handle the uncertainty and ambiguity in business data. For cross-category business events frequently occurring in marine monitoring projects, such as comprehensive events involving both equipment maintenance and data processing, traditional hard classification methods often fail to accurately categorize them. The research team designed a fuzzy membership function to quantify the degree to which a business event belongs to different categories, and determined the final classification result by calculating the membership values ​​for each category. The calculation of the fuzziness value considers multiple attribute characteristics of the business event, including cost, duration, resource consumption, and technical complexity.

[0074] The clearly defined business data classification system ensures that each business event can find a unique corresponding accounting treatment. The research team established a three-level classification system to eliminate ambiguity in the data processing process. The first-level classification is divided into four categories based on business nature: equipment operation, monitoring data, maintenance, and management support. The second-level classification is divided into two subcategories based on cost attribution: direct costs and indirect costs. The third-level classification is further refined according to accounting subject attribution. Each category in the classification system corresponds to clear accounting treatment rules and subject codes, ensuring the accuracy and consistency of the conversion process from business data to accounting vouchers. (See Table 1.) Table 1. Comparison of Business Event Classification and Ambiguity Values

[0075] The implementation of the account association optimization function employs the minimum spanning tree algorithm to optimize the relationships between accounting accounts. The research team treats all related accounting accounts as nodes in a graph theory, with the association strength between accounts serving as the edge weights. The algorithm's input includes 35 accounting account nodes, an inter-account association weight matrix, business event frequency statistics for the past three months, and network connectivity constraints. The weight matrix calculation considers multiple factors such as business relevance, usage frequency, and monetary correlation between accounts, and the association weight values ​​between each pair of accounts are derived through historical data analysis. The minimum spanning tree algorithm finds the minimum weight path connecting all account nodes, constructing the optimal account association network topology to ensure the accuracy and efficiency of account matching. As shown in Table 2: Table 2. Relationship Weight Matrix of Major Accounting Items

[0076] After automatically matching standardized business event data with accounting rules in the accounting rules knowledge base, the system automatically generates corresponding draft accounting vouchers. During a one-month testing period, the research team processed 1847 business data entries, and the system successfully generated 1823 draft accounting vouchers, achieving an automatic matching success rate of 98.7%. The generated draft vouchers contain complete accounting information, including all necessary fields such as voucher number, accounting subject, debit / credit direction, amount, summary, preparer, and preparation date.

[0077] The compliance verification and logical review process conducted a comprehensive quality check on the generated draft accounting vouchers. The verification included multiple aspects such as debit / credit balance verification, account code validity check, and amount reasonableness assessment. Debit / credit balance verification ensured that the debit and credit amounts of each voucher were exactly equal. Account code validity check verified whether the account codes used existed in the company's accounting system. Amount reasonableness assessment identified abnormal amounts by comparing with historical data. The resulting list of vouchers to be confirmed eliminated non-compliant drafts, ensuring the reliability of the voucher quality. (See Table 3.) Table 3. Statistical Table of Compliance Verification Results

[0078] Finance staff conduct a final review and confirmation of the list of vouchers that have passed verification. During the confirmation process, finance staff can view detailed information about each voucher, the original business data, and the system's processing logic. During the testing period, finance staff confirmed 1785 vouchers, achieving a confirmation rate of 97.9%. Unconfirmed vouchers were mainly due to special cases requiring manual judgment due to complex business logic. After confirmation by finance staff, the system automatically writes the voucher data into the accounting information system, completing the entire automated accounting process.

[0079] The system-generated business data accounting processing report details the processing trajectory and voucher generation results for each business data transaction. The report includes key information such as data source, processing time, generated voucher number, processing status, and any anomalies. The processing trajectory records the complete process of business data from collection to final generation of accounting vouchers, including the data flow path, processing time nodes at each stage, operator identification, and processing result status. This provides crucial data support for subsequent auditing work and system optimization.

[0080] The game theory model played a crucial role in practical applications. The upper-level model aimed to maximize the accuracy of accounting information by optimizing parameters such as the accuracy index of the explicit business data classification system and the accuracy level of fuzzy business event recognition. The lower-level model aimed to minimize processing costs by controlling factors such as the calculation cost of fuzziness values ​​and the execution cost of the account association optimization function to reduce system operating costs. The coupling term between the two models quantified the mutual influence between accuracy and cost by clarifying the correlation coefficient between the business data classification system and the fuzzy business event recognition mechanism, thus achieving coordinated optimization of system performance. As shown in Table 4: Table 4 Comparison of Game Theory Model Optimization Results

[0081] Traditional accounting for marine monitoring projects relies heavily on manual identification of business event types by financial personnel, who then manually input data according to a pre-defined accounting subject correspondence table. This method is inefficient and prone to errors when handling large amounts of complex business data. Financial personnel need to analyze the nature of each business data entry, determine its appropriate accounting subject, and then manually prepare accounting vouchers. This process is not only time-consuming but also frequently results in classification errors when dealing with ambiguous business boundaries. This invention represents a significant technological advancement over traditional methods. Automated processing capabilities reduce the processing time for a single business data entry from an average of 15 minutes to less than 2 minutes, improving efficiency by approximately 87%. The introduction of a fuzzy business event identification mechanism increases the classification accuracy of complex business events from 78% to 94.5%, significantly reducing human error. The subject association optimization function dynamically adjusts subject association relationships, increasing the accuracy of subject matching from 85% with traditional static mapping to 98.7%, essentially eliminating matching errors caused by changes in subject relationships. The overall processing capacity and accuracy of the system represent a qualitative leap compared to traditional methods, providing a reliable technical solution for financial automation in professional fields such as marine monitoring.

[0082] It should be noted that the variables involved in this invention are explained in detail in Tables 5 and 6.

[0083] Table 5. Variable Explanation Table (Part 1)

[0084] Table 6. Variable Explanation Table (Part Two)

[0085] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. An accounting method based on multi-source marine business data, characterized in that, The process includes the following steps: First, collecting business data generated by monitoring equipment on a marine monitoring platform as the basic data source and establishing a mapping relationship between business data and accounting subjects. Second, constructing a business data parsing engine to perform structured processing and classification of business data, forming standardized business event data. Third, establishing an accounting rule knowledge base to store accounting processing rules and voucher generation templates corresponding to different business events. Fourth, introducing a fuzzy business event identification mechanism to construct a clear business data classification system, calculating the fuzziness value of matching business events with subjects, calling a subject association optimization function to optimize the accounting subject association network structure, automatically matching standardized business event data with accounting processing rules in the accounting rule knowledge base, and generating corresponding draft accounting vouchers. Fifth, performing compliance verification and logical review on the generated draft accounting vouchers to form a list of vouchers to be confirmed. Sixth, pushing the verified list of vouchers to be confirmed to finance personnel for final review and confirmation. After confirmation by finance personnel, the system automatically writes the voucher data into the accounting information system, completing the automatic accounting process. Finally, generating a business data accounting processing report.

2. The accounting method based on multi-source marine business data according to claim 1, characterized in that, The business data includes equipment operating parameters, monitoring result data, and equipment maintenance records. The standardized business event data includes event type, amount information, timestamp, and associated account code.

3. The accounting method based on multi-source marine business data according to claim 2, characterized in that, The business data parsing engine refers to a software module used to convert raw data generated by marine monitoring equipment into structured data for identification and processing by the financial system. The business data parsing engine achieves data standardization through data format conversion and field mapping.

4. The accounting method based on multi-source marine business data according to claim 3, characterized in that, The accounting rules knowledge base refers to a database system that stores accounting processing standards and voucher generation rules under various business scenarios. The accounting rules knowledge base includes account correspondence, calculation logic and audit standards, providing a decision-making basis for automatic bookkeeping.

5. The accounting method based on multi-source marine business data according to claim 4, characterized in that, The standardized business event data refers to structured data formed by organizing the original business data according to a unified format and standard. Standardized business event data facilitates subsequent automated processing and rule matching.

6. The accounting method based on multi-source marine business data according to claim 5, characterized in that, The fuzzy business event identification mechanism refers to an identification method used to handle uncertain and ambiguous features in business data. The fuzzy business event identification mechanism uses fuzzy set theory to quantify the degree of uncertainty of event attributes and solves the problem of unclear business event classification boundaries.

7. The accounting method based on multi-source marine business data according to claim 6, characterized in that, The aforementioned clear business data classification system refers to a classification system that establishes a precise correspondence between business data and accounting subjects. A clear business data classification system ensures that each business event can find a unique corresponding accounting treatment method, eliminating ambiguity in the data processing process.

8. The accounting method based on multi-source marine business data according to claim 7, characterized in that, The game theory model is constructed by including an upper-level model aimed at maximizing the accuracy of accounting information and a lower-level model aimed at minimizing processing costs. The objective function of the upper-level model mainly consists of the accuracy index of the business data classification system, the accuracy level of fuzzy business event identification, the weighting coefficient of accounting information accuracy, and coupling terms.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program instructions, which, when executed in a computer, are used to perform an accounting method based on marine multi-source business data as described in any one of claims 1-8.

10. An accounting and bookkeeping system based on business data, characterized in that, The system includes the computer-readable storage medium of claim 9, wherein the system is any one of a computer, a server, or a microcontroller, the computer-readable storage medium is disposed within the system, and the system is provided with a microprocessor that executes the program instructions stored in the computer-readable storage medium.

Images