CN115578167A - Finance and tax accounting processing system based on big data - Google Patents
Finance and tax accounting processing system based on big data Download PDFInfo
- Publication number
- CN115578167A CN115578167A CN202210915505.5A CN202210915505A CN115578167A CN 115578167 A CN115578167 A CN 115578167A CN 202210915505 A CN202210915505 A CN 202210915505A CN 115578167 A CN115578167 A CN 115578167A
- Authority
- CN
- China
- Prior art keywords
- data
- tax
- attribute
- analysis
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/123—Tax preparation or submission
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Technology Law (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a financial and tax accounting processing system based on big data, which relates to the technical field of data processing, and is characterized in that the financial and tax data is subjected to attribute and source classification, and relevance analysis is carried out on the financial and tax data according to the attribute and source classification result; constructing a multi-layer relation and tax network according to the relevance analysis result and the attribute labels and source labels of each property and tax data; acquiring a related finance and tax data chain based on a finance and tax multi-layer related network; and carrying out data chain financial and tax accounting according to the associated financial and tax data chain to obtain a financial and tax accounting result. The method solves the technical problems that in the prior art, financial and tax accounting only focuses on the accuracy and reliability of data, the influence of the interrelation between the data is ignored, reliable analysis is lacked for the influence of a data bottom layer, and the financial and tax accounting management level is not favorably improved effectively. The effects of comprehensively accounting according to the explicit accounting requirement of data accounting and the implicit accounting requirement of data relation and improving the reliability of financial and tax accounting are achieved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a financial and tax accounting processing system based on big data.
Background
Accounting and tax accounting is the important content of enterprise economic accounting, and according to the original certificate after auditing, the accounting subjects are used, accounting certificates are filled, accounting books are registered, and the economic activities, financial and tax accounting processes of each accounting unit or accounting project are continuously, systematically and comprehensively recorded by taking money as the accounting scale. The method can reflect and supervise the live labor consumption, the material consumption and the capital occupation of enterprises and the production and operation processes of each accounting unit in the enterprises and the economic effects of the enterprises in a value form. With the continuous development and progress of society and science and technology, we have entered the big data era. Under the background, a lot of new challenges and new requirements are brought to financial accounting management of enterprises, traditional financial accounting management mainly utilizes financial accounting report data to collect required information, and after the big data era, the financial accounting management of the enterprises can not only collect information from financial accounting reports, but also collect and mine required data and information from the aspects of related business, clients and the like through big data technology.
In the prior art, the financial and tax accounting only pays attention to the accuracy and reliability of data, the influence of the mutual relation among the data is ignored, the influence on the data bottom layer is lack of reliable analysis, and the financial and tax accounting management level is not favorably improved.
Disclosure of Invention
In order to solve the problems, the application provides a financial and tax accounting processing system based on big data, and solves the technical problems that in the prior art, financial and tax accounting only focuses on the accuracy and reliability of data, the influence of the interrelation between the data is ignored, the influence on a data bottom layer is lack of reliable analysis, and the effective improvement of the financial and tax accounting management level is not facilitated. The technical effects of comprehensively accounting according to the explicit accounting requirement of data accounting and the implicit accounting requirement of data relation and improving the financial and tax accounting reliability are achieved.
In view of the above, the present application provides a fiscal accounting processing system based on big data.
In a first aspect, the present application provides a big data-based financial and tax accounting processing system, comprising: the attribute analysis module is used for performing attribute analysis on the property tax data, performing attribute classification on the property tax data based on an attribute analysis result, and creating an attribute label for each property tax data by using an attribute classification result; the source analysis module is used for determining the data source of the finance and tax data, acquiring data source information, classifying the finance and tax data based on the data source information to obtain a source classification result, and creating a source label based on the source classification result; the relevance analysis module is used for carrying out relevance analysis on the property and tax data according to the attribute classification result and the source classification result to obtain a relevance analysis result of the property and tax data; the multi-layer correlation and networking module is used for constructing a multi-layer correlation and networking of the finance and tax according to the correlation analysis result, the attribute labels and the source labels of the finance and tax data; the data chain extraction module is used for obtaining a related finance and tax data chain based on the finance and tax multi-layer relation network; and the accounting module is used for carrying out data chain financial and tax accounting according to the associated financial and tax data chain to obtain a financial and tax accounting result.
In a second aspect, the present application provides a fiscal accounting processing method based on big data, the method including: performing attribute analysis on the property and tax data, performing attribute classification on the property and tax data based on the attribute analysis result, and creating an attribute label for each property and tax data by using the attribute classification result; determining the data source of the fiscal data, obtaining data source information, classifying the fiscal data based on the data source information to obtain a source classification result, and creating a source label based on the source classification result; performing relevance analysis on the finance and tax data according to the attribute classification result and the source classification result to obtain a relevance analysis result of the finance and tax data; constructing a multi-layer tariff network according to the relevance analysis result and the attribute tags and source tags of each tariff data; acquiring an associated finance and tax data chain based on the finance and tax multi-layer networking; and carrying out data chain financial and tax accounting according to the associated financial and tax data chain to obtain a financial and tax accounting result.
In a third aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the contents of the system of the first aspect.
The technical scheme provided in the application at least has the following technical effects:
the application provides a financial and tax accounting processing system based on big data, which performs attribute analysis on financial and tax data, performs attribute classification on the financial and tax data based on an attribute analysis result, and creates an attribute label on each financial and tax data by using an attribute classification result; determining the data source of the fiscal data, obtaining data source information, classifying the fiscal data based on the data source information to obtain a source classification result, and creating a source label based on the source classification result; performing relevance analysis on the fiscal data according to the attribute classification result and the source classification result to obtain a relevance analysis result of the fiscal data; constructing a multi-layer tax-related network according to the relevance analysis result and the attribute labels and source labels of each tax data; acquiring an associated finance and tax data chain based on the finance and tax multi-layer networking; and carrying out data chain financial and tax accounting according to the associated financial and tax data chain to obtain a financial and tax accounting result. The reliability of the nodes of the data is checked by using the relation of the checking data, the checking requirement that the checking of the surface amount number is considered as dominant is met, the mutual influence relation between the data is considered as recessive, the condition that closed-loop transaction is abnormal and the property tax cannot be effectively checked is avoided, so that the reliability of property tax checking is improved, and the technical effect of effectively improving the property tax management level is effectively ensured. Therefore, the technical problems that in the prior art, financial and tax accounting only focuses on the accuracy and reliability of data, the influence of the mutual relation between the data is ignored, the influence on the data bottom layer is lack of reliable analysis, and the financial and tax accounting management level is not favorably improved are solved.
Drawings
Fig. 1 is a schematic flow chart of a big data-based fiscal accounting processing method according to an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating accounting of fiscal data in a fiscal accounting processing method based on big data according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a big-data-based fiscal accounting processing system according to an embodiment of the present application.
Detailed Description
This application is through providing a financial and taxation accounting processing system based on big data for solve in the prior art financial and taxation accounting and only concern the accurate reliability of data itself, neglected the influence of interrelation between the data, lack reliable analysis to the influence of data bottom, be unfavorable for the technical problem that financial and taxation accounting management level effectively promoted.
The following detailed description of the embodiments of the present invention is made with reference to specific examples.
Example one
Fig. 1 is a schematic flow chart of a fiscal accounting processing method based on big data according to an embodiment of the present application, and referring to fig. 1, an embodiment of the present application provides a fiscal accounting processing method based on big data, where the method includes:
s1: and performing attribute analysis on the fiscal data, performing attribute classification on the fiscal data based on an attribute analysis result, and creating an attribute label for each fiscal data by using an attribute classification result.
Further, attribute analysis is performed on the fiscal data, and attribute classification is performed on the fiscal data based on the attribute analysis result, wherein the S1 includes: s101: carrying out multi-dimensional characteristic analysis on the fiscal data to obtain multi-dimensional characteristic information; s102: clustering according to the multi-dimensional characteristic information to determine a multi-dimensional data clustering result; s103: and performing clustering attribute analysis based on the multi-dimensional data clustering result, and determining the attribute analysis result.
Further, performing multidimensional feature analysis on the fiscal data to obtain multidimensional feature information, where S101 includes: s1011: carrying out tax payment characteristic analysis on the fiscal data by using tax payment rule information to obtain tax payment characteristics; s1012: carrying out asset and liability characteristic analysis on the fiscal data by using the asset and liability characteristics to obtain asset and liability characteristics; s1013: carrying out periodic characteristic analysis on the fiscal data by using a fund period rule to obtain fiscal data periodic characteristics; s1014: carrying out target characteristic analysis on the fiscal data by utilizing the attribute characteristics of the fund-related main body to obtain target main body characteristics; s1015: and acquiring the multi-dimensional characteristic information according to the tax payment characteristic, the asset liability characteristic, the fiscal data cycle characteristic and the target subject characteristic.
Specifically, the fiscal data is a set of all fiscal data that need to be checked, and the fiscal data is analyzed for data attributes, that is, whether tax payment is needed, which type of fiscal data, asset data, liability data, and the like, and the attribute classification of the fiscal data is a traditional attribute classification according to industry requirements and rules of the fiscal data, and can also be set by a user according to special enterprise requirements, and the setting can be adjusted by increasing acquisition dimensions.
The embodiment of the application aims at the accounting requirement of the common fiscal data: the method comprises the steps of carrying out attribute analysis on attributes of property tax data according to a plurality of dimensions such as tax payment requirements, assets and liabilities, capital periods, capital related subjects and the like according to attribute requirements corresponding to an asset liability statement, profits, a cash flow statement, an owner equity change statement and the like, carrying out feature extraction on the property tax data according to the set multi-dimensional requirements and carrying out multi-dimensional feature information corresponding to the property tax data.
Clustering is carried out according to multi-dimensional characteristic information of each property and tax data, the clustering means comprises common clustering algorithms such as K-means, KNN algorithm, gaussian clustering and the like, each characteristic data is clustered, namely data with the same characteristic is combined, each label of property and tax data is clustered to obtain a clustering result of each characteristic data, a characteristic with the highest overlapping degree of each data in the clustering result is used as a classification result of the clustering, for example, fixed asset data, the attribute of the data in the clustering result is a fixed asset data attribute, if the data in the clustering result is long-term and liability characteristic, the data corresponding to the clustering is a long-term liability attribute, and the data is classified.
And creating attribute labels for the fiscal data according to the attribute classification result, and rapidly extracting the data with the same label by using the attribute labels, so that the data is conveniently classified and managed, and a foundation is laid for effective data screening and corresponding accounting in the follow-up process.
S2: determining the data source of the fiscal data, obtaining data source information, classifying the fiscal data based on the data source information to obtain a source classification result, and creating a source label based on the source classification result.
Specifically, the data source is the collection way of finance and tax data, along with the arrival of the big data era, currency circulation is also gradually electronized, a lot of finance and tax data can be obtained through the big data, different sources can exist according to the attributes and characteristics of different finance and tax data, such as a partner port, an e-commerce platform, internet bank, a third party platform, bills and the like, the finance and tax data are subjected to source classification and marking according to different data sources, the source labels are utilized in the same way, the data can be quickly searched, counted, extracted and the like, and data integration and financial accounting are facilitated. Meanwhile, different data reliability degrees are also corresponded according to different data sources, for example, the data reliability degree of the online bank is high, the reliability degree of bills and third-party platforms is low, different fiscal data can be classified according to the reliability degree by using different data source labels, and during fiscal accounting, important accounting is determined according to different data labels, so that the accounting work is conveniently carried out, and the accounting efficiency is improved.
S3: and performing relevance analysis on the fiscal data according to the attribute classification result and the source classification result to obtain a relevance analysis result of the fiscal data.
Further, performing relevance analysis on the fiscal data according to the attribute classification result and the source classification result to obtain a relevance analysis result of the fiscal data, wherein the step S3 includes:
s301: data attribute feature tracing is carried out according to the attribute classification result, and data attribute features are determined; s302: performing attribute relevance analysis based on the data attribute characteristics to obtain an attribute relevance result; s303: source feature tracing is carried out according to the source classification result, and data source features are determined; s304: and performing relevance analysis according to the data source characteristics to obtain a source relevance result.
Specifically, the relevance analysis is performed on the fiscal and tax data, the relevance exists among the fiscal and tax data, the result data of the attribute is formed like the data of the attribute, the profit, the income, the indication and the like are related, the influence relation of each feature is analyzed by using the data attribute features, when the relevance analysis is performed, the processing can be performed by using a computer model, training data is constructed by using a large number of data attribute features and identification information identifying the relevance result through the learning of each attribute feature of the fiscal and tax data, the deep learning is performed on the training data through the model of the neural network to obtain the relation between the data attribute features and the relevance result, the computer model has the characteristics of performing operation processing on the input data attribute features through repeated learning and feedback optimization to obtain the corresponding relevance result, the relevance analysis on the fiscal and tax data is realized, and the influence degree among the data is larger if the relevance is larger. In performing the data accounting, it is necessary to perform the comprehensive accounting in consideration of data which has a relevance to the data and satisfies a relevance degree setting requirement, and to ensure the reliability of the accounting result.
When the relevance analysis is carried out, the relevance analysis of the attribute characteristics and the source is included, the reliability between the fiscal data is mainly considered by the data source characteristics, the relevance is the largest if the data source characteristics are the same, certain relevance exists if the data source characteristics are overlapped in source ways of different sources, or certain relevance exists when the third-party platform and other third-party platforms have the same money attribute in transaction, and the reliability of the data is evaluated and calculated through the relevance of the source.
And carrying out relevance analysis on the fiscal data from all aspects, and mining the surface, bottom layer, cross and invisible relations of various fund transactions so as to ensure the reliability of fiscal data accounting and provide reliable fiscal accounting management for enterprises.
S4: and constructing a multi-layer tariff network according to the relevance analysis result, and the attribute tags and source tags of each tariff data.
Further, according to the correlation analysis result, the attribute labels and the source labels of the property tax data, a property tax multi-layer correlation network is constructed, and S4 includes: s401: determining relevance data and relevance results based on the relevance analysis results, labeling the relevance data and the relevance results with corresponding finance and tax data, and generating relevance labels; s402: establishing a data connection relation according to the relevance data in the relevance tag; s403: and constructing the multi-level relation network of the finance and tax by using a knowledge graph semantic network by taking the finance and tax data as nodes, taking the data connection relation as an edge, taking the attribute labels and the source labels as node attributes.
Specifically, a multi-level relationship network of the finance and tax is established by using the correlation analysis result and the attribute label and the source label of the finance and tax data through a knowledge map technology, the relation among the finance and tax data in all aspects of attribute, source and multiple dimensions is established, the finance and tax data of the source is used for accounting, and the precision of finance and tax accounting is improved. It should be understood that the knowledge graph is a relationship network obtained by connecting all kinds of information together, semantic analysis and deep mining are carried out on various relationships among data, and all layers of explicit and implicit relationships among the data are established. The traditional keyword-base search model is generally used for the current search engine and is upgraded to the search based on semantics.
The embodiment of the application utilizes the property characteristics, the source characteristics, the relevance and the like of each data as the attributes, and establishes the knowledge graph of the fiscal data, namely the fiscal multi-layer relationship networking.
S5: and obtaining an associated finance and tax data chain based on the finance and tax multi-layer relation networking.
S6: and carrying out data chain financial and tax accounting according to the associated financial and tax data chain to obtain a financial and tax accounting result.
Further, as shown in fig. 2, performing data chain fiscal accounting according to the associated fiscal data chain to obtain a fiscal accounting result, and S6 includes: s601: acquiring a node data influence factor and a data chain correlation result according to the correlation fiscal data chain; s602: constructing a Markov chain model according to the node data influence factor and the data chain relevance result; s603: performing data trend relationship conformity analysis on the associated fiscal data chain based on the Markov chain model; s604: and accounting the fiscal data according to the trend relation conformity analysis result.
Specifically, for data to be subjected to financial and tax accounting, fiscal data related to the data is searched and extracted from a fiscal multi-layer relationship network, a transaction data chain where the fiscal data to be accounted is located is obtained, or data related to the transaction content currently required to be accounted is extracted from the relationship chain, a related fiscal data chain is obtained, a markov chain is constructed by utilizing the front and back transaction sequence of each node in the related fiscal data chain, influence relationship analysis is carried out on numerical values of each node, which influence the fiscal data of the node, so as to obtain state information of the node, wherein the influence data of the node can be a single attribute and a single source, or another related fiscal data chain, the state result of the node is ensured by analyzing the relationship data of each node, and the node state is the reliability (accounting result) of the fiscal data of the node, the reliability is a quantitative result of the reliability of the finance and tax data, if the influence relationship of each node ensures the reliability of the finance and tax data of the node, the data in the related finance and tax data chain is accurate, the accounting result is through accounting, if the node has the characteristic which influences the reliability of the data, the related characteristic analysis of the reliability is continuously carried out on the characteristic, the reliability of the previous node is utilized to influence the reliability of the next node, the reliability probability of each node is determined by utilizing a Markov chain model, if the reliability probability of the node is large, the reliability of the node is determined, the reliability analysis is carried out on the data in each node in the same related finance and tax data chain in sequence to obtain the reliability of the node of the last related finance and tax data chain, if the reliability of the data in the whole related finance and tax data chain meets the requirement, and confirming that the associated fiscal data chain is passed through accounting, performing closed-loop accounting on the relationship between each node and each node in the associated fiscal data chain by using a Markov chain model, and if one node has a problem, directly influencing the reliability of other data in the data chain to ensure the data reliability of each node and the whole associated fiscal data chain. The reliability of the nodes of the data is checked by using the relation of the checking data, the checking of the surface amount number is considered, namely, the explicit checking requirement, the mutual influence relation between the data is considered, namely, the implicit checking requirement, the closed-loop transaction is avoided to be abnormal, the condition that the fiscal is fake and the effective checking cannot be carried out is avoided, the reliability of fiscal accounting is improved, and the effective improvement of the fiscal management level is effectively guaranteed. The method solves the technical problems that in the prior art, financial and tax accounting only focuses on the accuracy and reliability of data, the influence of the interrelation between the data is ignored, reliable analysis is lacked for the influence of a data bottom layer, and the financial and tax accounting management level is not favorably improved effectively.
Further, the system further comprises: s605: carrying out trend prediction on the associated finance and tax data chain by using a Markov chain model to obtain a trend prediction result; s606: and when the trend prediction result does not accord with the node data characteristics, sending trend reminding information.
Specifically, because risk management is an important content of enterprise financial and tax accounting and is often ignored at present, so that the financial and tax accounting management level is limited, the trend prediction function of the koku chain model is utilized in the embodiment of the application, trend analysis of financial and tax data is performed on the basis of the associated financial and tax data chain, if the financial and tax data is abnormal in the trend prediction result, reminding is performed, the abnormality includes the abnormality of data accounting and also includes the abnormality in aspects of enterprise financial and tax state, project development and the like, and the comprehensive data relationship analysis is performed by utilizing a multi-layer association network of financial and tax through the data connection relationship in the associated financial and tax data chain.
Optionally, during the trend prediction, according to the requirement of the trend prediction analysis, the attribute range of the fiscal data is determined, that is, the item needing the trend prediction or the data of a certain attribute is selected, and if the obtained data needing the trend prediction is less, the trend prediction analysis can be directly performed on the data chain. If the obtained data needing to be analyzed is multiple and the relation is complex, partitioning operation can be carried out on the data, attribute partitioning is carried out on the selected fiscal data needing to be analyzed based on a fiscal multi-layer relation networking, the partitions can be partitioned according to the influence degree required by trend prediction, optionally, the influence degree of the influence data of each node data and the quantity of the data are comprehensively evaluated, if the influence is high and the quantity is large, the comprehensive evaluation is high, the comprehensive evaluation results are ranked, the node with the highest ranking is selected as a partition node, the data with the relation of the node is taken as a partition, different related fiscal data chains are constructed by dividing the data into a plurality of areas, each partition is set as a partition node, node trend prediction is carried out through the multi-layer relation networking of each partition, the trend prediction of all the partition nodes is constructed to carry out overall trend prediction, the overall trend prediction result is obtained, the fiscal data is comprehensively analyzed by utilizing the fiscal multi-layer relation networking between the fiscal data, the hidden relation of the mining data is used for realizing prediction and decomposition of the fiscal data, and the level of accounting and the fiscal data is improved.
Example two
Based on the same inventive concept as the fiscal accounting processing method based on big data in the foregoing embodiment, an embodiment of the present application provides a fiscal accounting processing system based on big data, as shown in fig. 3, the system includes:
the attribute analysis module is used for carrying out attribute analysis on the fiscal data, carrying out attribute classification on the fiscal data based on an attribute analysis result, and creating an attribute label for each fiscal data by using an attribute classification result;
the source analysis module is used for determining the data source of the fiscal data, acquiring data source information, classifying the fiscal data based on the data source information to obtain a source classification result, and creating a source label based on the source classification result;
the relevance analysis module is used for carrying out relevance analysis on the property and tax data according to the attribute classification result and the source classification result to obtain a relevance analysis result of the property and tax data;
the multi-layer correlation and networking module is used for constructing a multi-layer correlation and networking of the finance and tax according to the correlation analysis result, the attribute labels and the source labels of the finance and tax data;
the data chain extraction module is used for obtaining an associated property and tax data chain based on the property and tax multi-layer correlation network;
and the accounting module is used for performing data chain financial and tax accounting according to the associated financial and tax data chain to obtain a financial and tax accounting result.
The method solves the technical problems that in the prior art, financial and tax accounting only focuses on the accuracy and reliability of data, influence of interrelation between data is neglected, influence on a data bottom layer is lack of reliable analysis, and the financial and tax accounting management level is not favorably improved effectively.
Further, the attribute analysis module further includes:
the multi-dimensional analysis unit is used for carrying out multi-dimensional characteristic analysis on the fiscal data to obtain multi-dimensional characteristic information;
the clustering unit is used for clustering according to the multi-dimensional characteristic information and determining a multi-dimensional data clustering result;
and the attribute processing unit is used for carrying out clustering attribute analysis based on the multi-dimensional data clustering result and determining the attribute analysis result.
Further, the multidimensional analysis unit is further configured to:
carrying out tax payment characteristic analysis on the fiscal data by using tax payment rule information to obtain tax payment characteristics;
carrying out asset and liability characteristic analysis on the fiscal data by using the asset and liability characteristics to obtain asset and liability characteristics;
carrying out periodic characteristic analysis on the fiscal data by using a fund period rule to obtain fiscal data periodic characteristics;
carrying out target characteristic analysis on the fiscal data by utilizing the attribute characteristics of the fund-related main body to obtain target main body characteristics;
and acquiring the multi-dimensional characteristic information according to the tax payment characteristic, the asset liability characteristic, the fiscal data cycle characteristic and the target subject characteristic.
Further, the relevance analysis module is further configured to:
data attribute feature tracing is carried out according to the attribute classification result, and data attribute features are determined;
performing attribute relevance analysis based on the data attribute characteristics to obtain an attribute relevance result;
source feature tracing is carried out according to the source classification result, and data source features are determined;
and performing relevance analysis according to the data source characteristics to obtain a source relevance result.
Further, the multi-layer networking module is further configured to:
determining relevance data and relevance results based on the relevance analysis results, labeling the relevance data and the relevance results with corresponding finance and tax data, and generating a relevance label;
establishing a data connection relation according to the relevance data in the relevance tag;
and constructing the multi-level relation network of the finance and tax by using a knowledge graph semantic network by taking the finance and tax data as nodes, taking the data connection relation as an edge, taking the attribute labels and the source labels as node attributes.
Further, the accounting module is further configured to:
acquiring a node data influence factor and a data chain correlation result according to the correlation fiscal data chain;
constructing a Markov chain model according to the node data influence factor and the data chain relevance result;
performing data trend relationship conformity analysis on the associated fiscal data chain based on the Markov chain model;
and accounting the fiscal data according to the trend relationship conformity analysis result.
Further, the accounting module is further configured to:
carrying out trend prediction on the associated finance and tax data chain by using a Markov chain model to obtain a trend prediction result;
and when the trend prediction result does not accord with the node data characteristics, sending trend reminding information.
The fiscal accounting processing system based on big data provided in the embodiment of the present application can implement the fiscal accounting processing method based on big data in the first embodiment, please refer to the detailed contents of the first embodiment, which is not described herein again.
The specification and drawings are merely exemplary of the application and various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Such modifications and variations of the present application are within the scope of the claims of the present application and their equivalents, and it is intended that the present application include such modifications and variations.
Claims (9)
1. A financial and tax accounting processing system based on big data, comprising:
the attribute analysis module is used for carrying out attribute analysis on the fiscal data, carrying out attribute classification on the fiscal data based on an attribute analysis result, and creating an attribute label for each fiscal data by using an attribute classification result;
the source analysis module is used for determining the data source of the fiscal data, acquiring data source information, classifying the fiscal data based on the data source information to obtain a source classification result, and creating a source label based on the source classification result;
the relevance analysis module is used for carrying out relevance analysis on the fiscal data according to the attribute classification result and the source classification result to obtain a relevance analysis result of the fiscal data;
the multi-layer correlation networking module is used for constructing a multi-layer correlation networking of the finance and tax according to the correlation analysis result, the attribute tags and the source tags of each finance and tax data;
the data chain extraction module is used for obtaining a related finance and tax data chain based on the finance and tax multi-layer relation network;
and the accounting module is used for carrying out data chain financial and tax accounting according to the associated financial and tax data chain to obtain a financial and tax accounting result.
2. The system of claim 1, wherein the attribute analysis module further comprises:
the multi-dimensional analysis unit is used for carrying out multi-dimensional characteristic analysis on the property and tax data to obtain multi-dimensional characteristic information;
the clustering unit is used for clustering according to the multi-dimensional characteristic information and determining a multi-dimensional data clustering result;
and the attribute processing unit is used for carrying out clustering attribute analysis based on the multi-dimensional data clustering result and determining the attribute analysis result.
3. The system of claim 2, wherein the multi-dimensional analysis unit is further to:
carrying out tax payment characteristic analysis on the fiscal data by using tax payment rule information to obtain tax payment characteristics;
carrying out asset and liability characteristic analysis on the fiscal data by using the asset and liability characteristics to obtain asset and liability characteristics;
carrying out periodic characteristic analysis on the fiscal data by using a fund period rule to obtain fiscal data periodic characteristics;
carrying out target characteristic analysis on the fiscal data by utilizing the attribute characteristics of the fund-related main body to obtain target main body characteristics;
and acquiring the multi-dimensional characteristic information according to the taxation characteristic, the asset liability characteristic, the fiscal data cycle characteristic and the target subject characteristic.
4. The system of claim 3, wherein the relevance analysis module is further to:
tracing the data attribute features according to the attribute classification result to determine the data attribute features;
performing attribute relevance analysis based on the data attribute characteristics to obtain an attribute relevance result;
source feature tracing is carried out according to the source classification result, and data source features are determined;
and performing relevance analysis according to the data source characteristics to obtain a source relevance result.
5. The system of claim 4, wherein the multi-tiered networking module is further to:
determining relevance data and relevance results based on the relevance analysis results, labeling the relevance data and the relevance results with corresponding finance and tax data, and generating a relevance label;
establishing a data connection relation according to the relevance data in the relevance tag;
and constructing the multi-level relation network of the finance and tax by using a knowledge graph semantic network by taking the finance and tax data as nodes, taking the data connection relation as an edge, taking the attribute labels and the source labels as node attributes.
6. The system of claim 1, wherein the accounting module is further to:
acquiring a node data influence factor and a data chain correlation result according to the correlation fiscal data chain;
constructing a Markov chain model according to the node data influence factor and the data chain relevance result;
performing data trend relationship conformity analysis on the associated fiscal data chain based on the Markov chain model;
and accounting the fiscal data according to the trend relation conformity analysis result.
7. The system of claim 6, wherein the accounting module is further to:
carrying out trend prediction on the associated finance and tax data chain by using a Markov chain model to obtain a trend prediction result;
and when the trend prediction result does not accord with the node data characteristics, sending trend reminding information.
8. A financial and tax accounting processing method based on big data is characterized by comprising the following steps:
performing attribute analysis on the property and tax data, performing attribute classification on the property and tax data based on the attribute analysis result, and creating an attribute label for each property and tax data by using the attribute classification result;
determining the data source of the fiscal data, obtaining data source information, classifying the fiscal data based on the data source information to obtain a source classification result, and creating a source label based on the source classification result;
performing relevance analysis on the fiscal data according to the attribute classification result and the source classification result to obtain a relevance analysis result of the fiscal data;
constructing a multi-layer tax-related network according to the relevance analysis result and the attribute labels and source labels of each tax data;
acquiring an associated finance and tax data chain based on the finance and tax multi-layer correlation network;
and carrying out data chain financial and tax accounting according to the associated financial and tax data chain to obtain a financial and tax accounting result.
9. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, implements the contents of the system of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210915505.5A CN115578167A (en) | 2022-08-01 | 2022-08-01 | Finance and tax accounting processing system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210915505.5A CN115578167A (en) | 2022-08-01 | 2022-08-01 | Finance and tax accounting processing system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115578167A true CN115578167A (en) | 2023-01-06 |
Family
ID=84578942
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210915505.5A Pending CN115578167A (en) | 2022-08-01 | 2022-08-01 | Finance and tax accounting processing system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115578167A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116245670A (en) * | 2023-05-12 | 2023-06-09 | 辽联(北京)数据科技开发有限公司 | Method, device, medium and equipment for processing financial tax data based on double-label model |
| CN116934430A (en) * | 2023-09-19 | 2023-10-24 | 深圳美云集网络科技有限责任公司 | Information complement method and ERP system |
| CN117592973A (en) * | 2024-01-11 | 2024-02-23 | 金华青鸟计算机信息技术有限公司 | Data-based management method and device, storage medium and electronic equipment |
-
2022
- 2022-08-01 CN CN202210915505.5A patent/CN115578167A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116245670A (en) * | 2023-05-12 | 2023-06-09 | 辽联(北京)数据科技开发有限公司 | Method, device, medium and equipment for processing financial tax data based on double-label model |
| CN116934430A (en) * | 2023-09-19 | 2023-10-24 | 深圳美云集网络科技有限责任公司 | Information complement method and ERP system |
| CN117592973A (en) * | 2024-01-11 | 2024-02-23 | 金华青鸟计算机信息技术有限公司 | Data-based management method and device, storage medium and electronic equipment |
| CN117592973B (en) * | 2024-01-11 | 2024-04-02 | 金华青鸟计算机信息技术有限公司 | Data-based management method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Amani et al. | Data mining applications in accounting: A review of the literature and organizing framework | |
| US11526579B1 (en) | System and methods for performing automatic data aggregation | |
| CN115578167A (en) | Finance and tax accounting processing system based on big data | |
| US20060122849A1 (en) | Technique evaluating device, technique evaluating program, and technique evaluating method | |
| Ibanez et al. | Cluster methods for assessing research performance: exploring Spanish computer science | |
| Akerkar | Advanced data analytics for business | |
| Shen et al. | Combining DRSA decision-rules with FCA-based DANP evaluation for financial performance improvements | |
| Li et al. | RETRACTED ARTICLE: Data mining optimization model for financial management information system based on improved genetic algorithm | |
| Zhou et al. | Study on a storage location strategy based on clustering and association algorithms | |
| Andreu et al. | Efficiency of the strategic style of pension funds: an application of the variants of the slacks-based measure in DEA | |
| Zhang et al. | Analysis and research on library user behavior based on apriori algorithm | |
| CN110310012A (en) | Data analysing method, device, equipment and computer readable storage medium | |
| Sirikulvadhana | Data mining as a financial auditing tool | |
| Hasheminejad et al. | Data mining techniques for analyzing bank customers: A survey | |
| Boonsiritomachai | Enablers affecting the adoption of Business Intelligence: a study of Thai small and medium-sized enterprises | |
| Rofi'i | Analysis of E-Commerce Purchase Patterns Using Big Data: An Integrative Approach to Understanding Consumer Behavior | |
| Polamuri et al. | Prediction of stock price growth for novel greedy heuristic optimized multi-instances quantitative (NGHOMQ) | |
| Wang | Research on Financial Cost Accounting and Control of Small-and Medium-Sized Enterprises under the Background of Data Mining | |
| Li | Parallel bookkeeping path of accounting in government accounting system based on deep neural network | |
| Guan et al. | Improving accuracy of financial distress prediction by considering volatility: an interval-data-based discriminant model | |
| Oliveira | ETL for Data Science?: A Case Study | |
| AU2021103329A4 (en) | The investigation technique of object using machine learning and system. | |
| Chaudhary | Data mining system, functionalities and applications: a radical review | |
| Biglari et al. | Big data applications in accounting: Implications for the tropics | |
| Tudor et al. | Clustering analysis for credit default probabilities in a retail bank portfolio |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |