CN117726463A

CN117726463A - Enterprise tax risk early warning method, system and medium

Info

Publication number: CN117726463A
Application number: CN202311837886.0A
Authority: CN
Inventors: 陈�胜; 仇庆宇; 陈燕云; 罗思
Original assignee: Shenzhen Aisino Corp
Current assignee: Shenzhen Aisino Corp
Priority date: 2023-12-28
Filing date: 2023-12-28
Publication date: 2024-03-19

Abstract

The embodiment of the application provides an enterprise tax risk early warning method, system and medium. The method comprises the following steps: acquiring business account records and tax activity log information of enterprises, extracting data such as loan accounts, account outer fund flows, goods account records, tax optimal qualification, payment tax, asset tax support and the like, evaluating the data to obtain relevant evaluation result data such as corresponding loan account overscale, account outer fund reflux degree, goods account deviation degree, invoice business deviation degree, ticket-free business overscaling degree and the like, performing tax risk evaluation to obtain an enterprise tax risk early warning evaluation index, and combining a plurality of historical tax actual warning values and historical enterprise tax risk early warning evaluation average index to obtain an enterprise tax risk early warning correction index, and comparing and judging enterprise tax risk conditions in time by a rear threshold; therefore, the tax risk evaluation early warning result is obtained by processing the plurality of pieces of monitoring information data of the enterprise, and the enterprise tax risk early warning technology is realized.

Description

Enterprise tax risk early warning method, system and medium

Technical Field

The application relates to the field of enterprise tax, in particular to an enterprise tax risk early warning method, system and medium.

Background

The tax risk of enterprises is mainly tax check risk caused by internal accounting caused by tax, expenditure, inventory, tax ticket, rewards and the like related to enterprise operation activities and tax check risk caused by loopholes of external cashing transactions, the tax risk is influenced by various aspects of enterprise activities, financial tax management capacity, fund circulation, salary, assets and the like, and enterprises often have various tax risks caused by various financial elements, insufficient monitoring capacity and incomplete tax management system, so that how to effectively monitor and evaluate the tax of the enterprises to early warn risk states has important significance to the enterprises, and the technical means for comprehensively and effectively monitoring and evaluating the operation behavior of the enterprises to obtain dynamic evaluation and early warning of the tax risk of the enterprises are lacking at present.

In view of the above problems, an effective technical solution is currently needed.

Disclosure of Invention

The embodiment of the application aims to provide an enterprise tax risk early warning method, system and medium, which can obtain an evaluation early warning result of tax risk by processing a plurality of pieces of monitoring information data of an enterprise, so as to realize the technology of carrying out risk early warning on enterprise tax.

The embodiment of the application also provides an enterprise tax risk early warning method, which comprises the following steps:

acquiring business account record information and tax activity log information of enterprises in a preset time period, wherein the business account record information comprises loan account record information, financial report data information and inventory account record information, and the tax activity log information comprises invoice issuing monitoring information, tax optimal execution status information, payment tax monitoring information and asset tax supporting status information;

respectively extracting the loan account characteristic data, the extra-account fund flow monitoring data and the goods account record deviation data according to the loan account record information, the financial report data information and the inventory account record information;

extracting invoice business comparison information and non-invoice business record information according to the invoice issuing monitoring information, and respectively extracting tax optimal execution deviation condition data, payment tax monitoring data and asset tax control error data according to the tax optimal execution condition information, payment tax monitoring information and asset tax control condition information;

performing the lending account superscale evaluation according to the lending account characteristic data to obtain lending account superscale data, performing the account outer fund reflux degree evaluation according to the account outer fund flow monitoring data to obtain account outer fund reflux degree data, performing the goods account deviation degree evaluation according to the goods account record deviation data to obtain goods account deviation degree evaluation data;

Respectively carrying out invoice service comparison deviation degree evaluation and non-invoice service overstock degree evaluation according to the invoice service comparison information and the non-invoice service record information to respectively obtain invoice service deviation degree data and non-invoice service overstock degree data;

performing tax optimal execution deviation degree evaluation according to the tax optimal execution deviation condition data to obtain tax optimal execution deviation degree data, performing payment tax difference degree evaluation according to the payment tax monitoring data to obtain payment tax difference evaluation data, performing asset tax error degree evaluation according to the asset tax error degree data to obtain asset tax error degree evaluation data;

performing risk evaluation processing through a preset enterprise tax risk evaluation model according to the statement overscale data, the statement outstation price return data, the goods statement deviation evaluation data and the invoice business deviation data, and combining the ticket-free business overscaling data, the tax optimal execution deviation data, the payment tax difference evaluation data and the asset tax tolerance evaluation data to obtain an enterprise tax risk early warning evaluation index;

acquiring a plurality of historical tax actual alarm values of the enterprise in the same period of history and historical enterprise tax risk early warning evaluation average indexes of the enterprise with the same type of attribute enterprise through a preset enterprise tax execution monitoring database, and correcting the enterprise tax risk early warning evaluation indexes to acquire enterprise tax risk early warning correction indexes;

And comparing the threshold value according to the enterprise tax risk early warning correction index and a preset enterprise tax risk early warning threshold value corresponding to the enterprise type attribute, and judging the tax risk condition of the enterprise in a preset time period.

Optionally, in the method for early warning tax risk of an enterprise according to the embodiment of the present application, extracting the loan account feature data, the foreign fund flow monitoring data and the goods account record deviation data according to the loan account record information, the financial report data information and the inventory account record information respectively includes:

extracting the feature data of the lending account according to the record information of the lending account, wherein the feature data comprises the identity identification data of the lending account, the borrowing amount data and the borrowing period data;

extracting account external fund flow monitoring data according to the financial data information, wherein the account external fund flow monitoring data comprises account external fund flow period data and payable fund amount data;

and extracting goods account record deviation data according to the inventory account record information, wherein the goods account record deviation data comprises account and goods comparison difference data, gap account and goods value data and account and goods gap duration data.

Optionally, in the enterprise tax risk early warning method according to the embodiment of the present application, extracting invoice business comparison information and ticketless business record information according to the invoice issuing monitoring information, and respectively extracting tax optimal execution deviation condition data, payment tax monitoring data and asset tax support error data according to the tax optimal execution condition information, payment tax monitoring information and asset tax support condition information, including:

Extracting invoice business comparison information and non-invoice business record information according to the invoice issuing monitoring information;

the invoice business comparison information comprises invoice amount comparison difference rate data, invoice business detail comparison deviation rate data and invoice information comparison total error rate data, and the ticketless business record information comprises ticketless business occupation ratio data, ticketless business amount ratio data and ticketless expenditure business grade data;

extracting tax optimal execution deviation condition data according to the tax optimal execution condition information, wherein the tax optimal execution deviation condition data comprises tax rate optimization mismatch rate data, tax preferential qualification error rate data and tax ticket deduction mismatch rate data;

extracting payment tax monitoring data according to the payment tax monitoring information, wherein the payment tax monitoring data comprises social security payment non-compliance data, payment tax breach limit data and payment tax benefit repeated payment tax limit data;

and extracting asset tax control error data according to the asset tax control status information, wherein the asset tax control error data comprises asset adjustment tax leakage amount data, asset allocation deduction super-rating data and asset repeated tax calculation amount data.

Optionally, in the enterprise tax risk early warning method according to the embodiment of the present application, the performing, according to the lending account feature data, lending account superscale data is obtained, performing, according to the account outer fund flow monitoring data, account outer fund return degree evaluation, obtaining account outer fund return degree data, performing, according to the account record deviation data, account deviation evaluation, obtaining account deviation evaluation data, including:

Performing the credit-out account superscale evaluation according to the credit-out account identity data, the borrowing amount data and the borrowing period data to obtain credit-out account superscale data;

performing account external fund reflux degree evaluation according to the account external fund flow period data and the payable fund amount data to obtain account external fund reflux degree data;

carrying out goods account deviation degree evaluation according to the account and goods comparison difference degree data, the gap account and goods value data and the account and goods gap duration data to obtain goods account deviation degree evaluation data;

the calculation formulas of the statement super-scale data, the extra-account fund return degree data and the goods account deviation degree evaluation data are respectively as follows:

C _g ＝μ ₁ s _t ×lgμ ₂ u _h p _w ；

wherein C is _g To lend account super-scale data, F _e For the data of the return degree of the extra-account fund, L _z Evaluating data for a cargo account deviation s _t 、u _h 、p _w Respectively, identity data of the lending account, borrowing amount data and borrowing period data, d _e 、m _s Respectively, account external fund flow period data and payable fund amount data, h _q 、y _e 、k _o Respectively account and goods comparison difference data, gap account and goods value data, account and goods gap duration data, mu,Is a preset characteristic coefficient.

Optionally, in the enterprise tax risk early warning method according to the embodiment of the present application, performing invoice business comparison deviation degree evaluation and non-invoice business overscaling evaluation according to the invoice business comparison information and the non-invoice business record information respectively, and obtaining invoice business deviation degree data and non-invoice business overscaling data respectively includes:

Performing invoice business comparison deviation degree assessment according to the invoice amount comparison difference rate data, the invoice business detail comparison deviation rate data and the invoice information comparison total error rate data to obtain invoice business deviation degree data;

performing the non-ticket business oversaturation evaluation according to the non-ticket business duty ratio data, the non-ticket business amount ratio data and the non-ticket expenditure business grade data to obtain non-ticket business oversaturation data;

the calculation formulas of the invoice business deviation degree data and the non-invoice business oversubstance degree data are respectively as follows:

wherein B is _k For invoice business deviation degree data, Y _z Is non-ticket business oversubstance data, a _d 、g _s 、o _t Respectively comparing invoice amount with difference rate data, invoice business detail with deviation rate data and invoice information with total error rate data, f _r 、e _u 、w _y The system is respectively ticketless service duty ratio data, ticketless service amount ratio data and ticketless expenditure service grade data, and lambda and upsilon are characteristic coefficients.

Optionally, in the enterprise tax risk early warning method according to the embodiment of the present application, performing tax optimal execution deviation degree assessment according to the tax optimal execution deviation condition data to obtain tax optimal execution deviation degree data, performing payment tax payment difference degree assessment according to the payment tax monitoring data to obtain payment tax payment difference assessment data, performing asset tax offset error degree assessment according to the asset tax offset error data to obtain asset tax offset error degree assessment data, including:

Performing tax optimal execution deviation degree assessment according to the tax rate optimization mismatch rate data, tax preferential qualification error rate data and tax receipt deduction mismatch rate data to obtain tax optimal execution deviation degree data;

performing payment tax difference assessment according to the social security payment non-compliance data, the payment tax breach limit data and the payment payroll benefit repeated payment tax limit data to obtain payment tax difference assessment data;

performing asset tax-fighting error degree evaluation according to the asset adjustment tax leakage amount data, the asset allocation deduction excess amount data and the asset repetition tax calculation amount data to obtain asset tax-fighting error degree evaluation data;

the calculation formulas of the tax optimal execution deviation degree data, the payment tax difference evaluation data and the asset tax offset error degree evaluation data are respectively as follows:

wherein Q is _x For tax best execution deviation degree data, T _y Evaluation data for payment tax difference, A _q Evaluating data for asset tax-protection error degree, c _d 、n _p 、t _c Optimizing mismatch rate data, tax preferential qualification error rate data, tax ticket deduction mismatch rate data, x for tax rates, respectively _r 、r _w 、z _a Repeated tax payment amount data, j for social security payment non-compliance data, payroll payment tax breach amount data and payroll benefit _m 、b _v 、h _w The asset adjustment tax leakage data, the asset allocation deduction excess data and the asset repetition tax calculation data are respectively used for the asset adjustment tax leakage data,sigma, psi and rho are preset characteristic coefficients.

Optionally, in the method for early warning of tax risk of an enterprise according to the embodiment of the present application, the processing of risk assessment is performed by a preset enterprise tax risk assessment model according to the statement overscale data, the statement outsource return data, the statement deviation assessment data, the invoice business deviation data, the ticketless business overscaling data, the tax optimal execution deviation data, the payment tax difference assessment data and the asset tax tolerance assessment data, to obtain an enterprise tax risk early warning assessment index, including:

performing risk evaluation processing through a preset enterprise tax risk evaluation model according to the lending account super-scale data, the account outer fund return degree data, the goods account deviation degree evaluation data, the invoice business deviation degree data, the ticketless business super-scale data, the tax optimal execution deviation degree data, the payment tax difference evaluation data and the asset tax deviation error degree evaluation data to obtain an enterprise tax risk early warning evaluation index in the preset time period;

The calculation formula of the enterprise tax risk early warning evaluation index is as follows:

wherein R is _φ C, early warning and evaluating index for enterprise tax risk _g To lend account super-scale data, F _e For the data of the return degree of the extra-account fund, L _z For evaluating data of deviation degree of goods account, B _k For invoice business deviation degree data, Y _z Is non-ticket business oversubscription data, Q _x For tax best execution deviation degree data, T _y Evaluation data for payment tax difference, A _q And (5) evaluating data for the tax-resisting error degree of the asset, wherein eta, epsilon, gamma and zeta are preset characteristic coefficients.

Optionally, in the method for early warning of tax risk of an enterprise according to the embodiment of the present application, the obtaining, by a preset enterprise tax execution monitoring database, a plurality of historical tax actual alarm values of the enterprise in a history synchronization and an average index of historical enterprise tax risk early warning evaluation of the enterprise with the same type of attribute as the enterprise, and then correcting the enterprise tax risk early warning evaluation index to obtain an enterprise tax risk early warning correction index includes:

acquiring a plurality of historical tax actual alarm values of an enterprise in the same period of history through a preset enterprise tax execution monitoring database;

acquiring an average index of historical enterprise tax risk early warning and evaluating of enterprises of the same type as the enterprise;

Correcting the enterprise tax risk early warning evaluation index according to the plurality of historical tax actual warning values and the historical enterprise tax risk early warning evaluation average index to obtain an enterprise tax risk early warning correction index;

the correction calculation formula of the enterprise tax risk early warning correction index is as follows:

wherein,for enterprise tax risk early warning correction index, R _φ K is an enterprise tax risk early warning and evaluating index _fi For the i-th historical tax actual alarm value, < +.>And (3) evaluating an average index for historical enterprise tax risk early warning, wherein pi, beta and theta are preset characteristic coefficients.

In a second aspect, an embodiment of the present application provides an enterprise tax risk early warning system, including: the system comprises a memory and a processor, wherein the memory comprises a program of an enterprise tax risk early warning method, and the program of the enterprise tax risk early warning method realizes the following steps when being executed by the processor:

In a third aspect, an embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium includes an enterprise tax risk early warning method program, where the enterprise tax risk early warning method program, when executed by a processor, implements the steps of the enterprise tax risk early warning method according to any one of the foregoing embodiments.

As can be seen from the foregoing, according to the enterprise tax risk early warning method, system and medium provided in the embodiments of the present application, by acquiring the business accounting record and tax activity log information of an enterprise, extracting the accounting feature data, the account outer resource flow monitoring data, the account accounting record deviation data, the tax optimal execution deviation status data, the payment tax monitoring data and the asset tax support error data, evaluating each data to obtain the accounting overscale data, the account outer resource return data, the payment deviation evaluation data, the invoice business deviation data, the ticketless business overscaling data, the tax optimal execution deviation data, the payment tax difference evaluation data and the asset tax support error evaluation data, then performing tax risk evaluation to obtain an enterprise tax risk early warning index, and then combining a plurality of historical enterprise tax actual alarm values and historical enterprise tax risk early warning average index correction indexes to obtain an enterprise tax risk early warning correction index, and comparing and judging enterprise tax risk conditions in a later threshold; therefore, the tax risk evaluation early warning result is obtained by processing the plurality of pieces of monitoring information data of the enterprise, and the enterprise tax risk early warning technology is realized.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the application. The objects and other advantages of the present application may be realized and attained by the structure particularly pointed out in the written description and drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flowchart of an enterprise tax risk early warning method provided in an embodiment of the present application;

fig. 2 is a flowchart of obtaining loan account feature data, account foreign material flow monitoring data and goods account record deviation data in the enterprise tax risk early warning method provided in the embodiment of the present application;

FIG. 3 is a flowchart of obtaining tax optimal execution deviation status data, payment tax monitoring data and asset tax error data of the enterprise tax risk early warning method provided in the embodiment of the present application;

Fig. 4 is a flowchart of obtaining the super-scale data of the loan account, the return data of the foreign funds, and the deviation evaluation data of the goods account in the enterprise tax risk early warning method provided in the embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.

It should be noted that like reference numerals and letters refer to like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.

Referring to fig. 1, fig. 1 is a flowchart of an enterprise tax risk early warning method according to some embodiments of the present application. The enterprise tax risk early warning method is used in terminal equipment, such as computers, mobile phone terminals and the like. The enterprise tax risk early warning method comprises the following steps:

s11, acquiring business account record information and tax activity log information of an enterprise in a preset time period, wherein the business account record information comprises loan account record information, financial report data information and inventory account record information, and the tax activity log information comprises invoice issuing monitoring information, tax optimal execution status information, payment tax monitoring information and asset tax supporting status information;

s12, respectively extracting the loan account characteristic data, the account foreign fund flow monitoring data and the goods account record deviation data according to the loan account record information, the financial report data information and the inventory account record information;

s13, extracting invoice business comparison information and non-invoice business record information according to the invoice issuing monitoring information, and respectively extracting tax optimal execution deviation condition data, payment tax monitoring data and asset tax control error data according to the tax optimal execution condition information, payment tax monitoring information and asset tax control condition information;

S14, performing lending account superscale evaluation according to the lending account characteristic data to obtain lending account superscale data, performing account outer fund reflux degree evaluation according to the account outer fund flow monitoring data to obtain account outer fund reflux degree data, performing goods account deviation degree evaluation according to the goods account record deviation data to obtain goods account deviation degree evaluation data;

s15, respectively carrying out invoice business comparison deviation degree evaluation and non-ticket business oversaturation degree evaluation according to the invoice business comparison information and the non-ticket business record information to respectively obtain invoice business deviation degree data and non-ticket business oversaturation degree data;

s16, performing tax optimal execution deviation degree evaluation according to the tax optimal execution deviation condition data to obtain tax optimal execution deviation degree data, performing payment tax payment difference degree evaluation according to the payment tax monitoring data to obtain payment tax difference evaluation data, performing asset tax support error degree evaluation according to the asset tax support error data to obtain asset tax support error degree evaluation data;

s17, carrying out risk evaluation processing according to the lending account super-scale data, the account external fund return degree data, the goods account deviation degree evaluation data, the invoice business deviation data, the ticketless business super-scale data, the tax optimal execution deviation degree data, the reward tax payment difference evaluation data and the asset tax support error degree evaluation data through a preset enterprise tax risk evaluation model to obtain an enterprise tax risk early warning evaluation index;

S18, acquiring a plurality of historical tax actual alarm values of the enterprise in the same period of history and historical enterprise tax risk early warning evaluation average indexes of the enterprise with the same type of attribute enterprise through a preset enterprise tax execution monitoring database, and then correcting the enterprise tax risk early warning evaluation indexes to acquire enterprise tax risk early warning correction indexes;

and S19, comparing the threshold value according to the enterprise tax risk early warning correction index and a preset enterprise tax risk early warning threshold value corresponding to the enterprise type attribute, and judging the tax risk condition of the enterprise in a preset time period.

Wherein, in order to evaluate the dynamic tax evaluation status in the enterprise business to perform result early warning, the operation accounting record information and tax activity log information affecting the tax risk status of the enterprise are acquired, wherein, the operation accounting record information comprises the loan accounting record information, the financial return data information and the inventory accounting record information, the tax activity log information comprises the invoice issuing monitoring information, the tax optimal execution status information, the payment tax monitoring information and the asset tax abutting status information, namely, the loan accounting, the financial report fund flow, the inventory and the account comparison record in the enterprise operation activity, and the invoice issuing condition, the tax qualification deviation condition, the payment benefit and the asset tax abutting condition in the tax record have an influence on the tax risk of the enterprise, then, corresponding data extraction is carried out on the information to respectively obtain the borrowing account feature data, the account outer fund flow monitoring data, the goods account record deviation data, the tax optimal execution deviation condition data, the payment tax monitoring data and the asset tax-fighting error data, then, each data is evaluated to obtain the borrowing account overscale data, the account outer fund reflux degree data, the goods account deviation degree evaluation data, the invoice business deviation degree data, the ticketless business overscaling degree data, the tax optimal execution deviation degree data, the payment tax difference evaluation data and the asset tax-fighting error degree evaluation data, namely, the evaluation results of the deviation error condition of each item having influence on the enterprise tax risk are obtained, then, the tax risk evaluation is carried out according to the evaluation results of each item to obtain the enterprise tax risk early warning evaluation index, in order to improve the accuracy of the enterprise tax risk condition evaluation, and correcting the historical tax actual alarm values and the historical enterprise tax risk early warning evaluation average index to obtain an enterprise tax risk early warning correction index, finally comparing the enterprise tax risk early warning threshold value corresponding to the attribute of the type of the enterprise with a threshold value, judging the tax risk condition of the enterprise in a preset time period through a threshold value comparison result, if the threshold value comparison result meets the threshold value comparison requirement, controlling the tax risk of the surface enterprise in the time period, otherwise, carrying out early warning on the tax risk in excess of the time period, and further obtaining the tax risk evaluation early warning result through processing a plurality of monitoring information data of the enterprise, thereby realizing the enterprise tax early warning.

Referring to fig. 2, fig. 2 is a flowchart of obtaining loan account feature data, extra-account fund flow monitoring data, and goods account record deviation data in an enterprise tax risk early warning method according to some embodiments of the present application. According to an embodiment of the present invention, the extracting, according to the loan account record information, the financial report data information and the inventory account record information, the loan account feature data, the account foreign fund flow monitoring data and the inventory account record deviation data respectively includes:

s21, extracting the lending account characteristic data according to the lending account record information, wherein the lending account characteristic data comprises lending account identity identification data, borrowing amount data and borrowing period data;

s22, extracting account external fund flow monitoring data according to the financial data information, wherein the account external fund flow monitoring data comprises account external fund flow period data and payable amount data;

s23, extracting goods account record deviation data according to the inventory account record information, wherein the goods account record deviation data comprises account and goods comparison difference data, gap account and goods value data and account and goods gap duration data.

Wherein the lending account record information is account record generated by paying money to enterprises by stakeholders or stakeholders, the excessive lending number and time length in the accounts can possibly lead to suspected evasion of registered capital or equivalent reddening, thereby bringing about the risk of enterprise tax violation, the lending account characteristic data comprise borrower identity identification importance data, borrowing amount and borrowing period data of the lending account, the financial data information is financial related data information which is easily recognized as the risk of tax compensation and fine caused by the return of extra-account funds due to the excessive amount or period of borrowing of a stockholder or a boss by an enterprise, the fund flow monitoring data comprises data of a circulation period of extra-account funds and a payable fund amount, the inventory account record information comprises inventory account record information of tax check risk caused by inconsistent account inventory and actual warehouse inventory of the enterprise, and the inventory record deviation data comprises data of account and goods comparison difference degree, gap account and goods price number and account and goods gap duration.

Referring to fig. 3, fig. 3 is a flowchart of obtaining tax optimal execution deviation status data, payment tax monitoring data and asset tax support error data according to an enterprise tax risk early warning method in some embodiments of the present application. According to the embodiment of the invention, the invoice service comparison information and the ticketless service record information are extracted according to the invoice issuing monitoring information, and the tax optimal execution deviation condition data, the payment tax monitoring data and the asset tax error data are respectively extracted according to the tax optimal execution condition information, the payment tax monitoring information and the asset tax error information, specifically:

s31, extracting invoice business comparison information and non-invoice business record information according to the invoice issuing monitoring information;

s32, the invoice business comparison information comprises invoice amount comparison difference rate data, invoice business detail comparison deviation rate data and invoice information comparison total error rate data, and the ticketless business record information comprises ticketless business duty ratio data, ticketless business amount ratio data and ticketless expenditure business grade data;

s33, extracting tax optimal execution deviation condition data according to the tax optimal execution condition information, wherein the tax optimal execution deviation condition data comprises tax rate optimization mismatch rate data, tax preferential qualification error rate data and tax receipt deduction mismatch rate data;

S34, extracting payment tax monitoring data according to the payment tax monitoring information, wherein the payment tax monitoring data comprise social security payment non-compliance data, payment tax breach limit data and payment benefit repeated payment tax amount data;

s35, extracting asset tax-fighting error data according to the asset tax-fighting status information, wherein the asset tax-fighting error data comprises asset adjustment tax-leaking amount data, asset allocation deduction excess amount data and asset repeated tax-counting amount data.

The invoice issuing condition is one of important cores for causing enterprise tax risk, invoice issuing monitoring information mainly covers information comparison of invoice issuing operation and related information of non-ticket operation, invoice issuing information refers to whether commodity names, amounts, unit price, quantity and purchasing and selling goods are consistent with actual goods or not in tax, tax risk is easy to generate if the invoice information is inconsistent, tax evasion caused by the deficiency is caused, invoice operation comparison information comprises comparison difference rate of invoice amount counted in period, comparison deviation rate of invoice operation detail and data of comparison total error rate of invoice information, non-ticket operation record information refers to recording information of tax risk caused by non-ticket operation total occupation rate, non-ticket operation amount and importance level data of the non-ticket operation expenditure, and priority execution information refers to tax priority monitoring information which is caused by tax fact that tax is controlled by a priority policy, operation condition is changed, tax loss is adjusted, tax is not matched with tax account information, tax priority is matched with tax payment information, tax priority is matched with tax priority information, tax priority is matched with tax payment ratio of an enterprise, and tax payment risk is not matched with tax payment information, and tax priority is matched with tax priority ratio of an enterprise, tax operation is matched with tax payment ratio, the asset tax-fighting status information refers to tax-fighting status information of tax risk caused by the non-compliance behavior of enterprise asset tax-fighting tax return, and the asset tax-fighting error data comprises related data of tax amount generated by asset adjustment, excessive allowance of asset allocation and repeated tax-paying of the asset.

Referring to fig. 4, fig. 4 is a flowchart of obtaining the super-scale data of the loan account, the return data of the extra-account funds, and the deviation evaluation data of the goods account according to some embodiments of the present application. According to an embodiment of the present invention, the performing the lending account superscale evaluation according to the lending account feature data to obtain the lending account superscale data, performing the account outer fund reflux degree evaluation according to the account outer fund flow monitoring data to obtain the account outer fund reflux degree data, and performing the goods account deviation degree evaluation according to the goods account record deviation data to obtain the goods account deviation degree evaluation data, specifically:

s41, performing the superscale assessment of the lending account according to the identity data, the borrowing amount data and the borrowing period data of the lending account to obtain superscale data of the lending account;

s42, performing account external fund reflux degree evaluation according to the account external fund flow period data and the payable fund amount data to obtain account external fund reflux degree data;

s43, carrying out cargo account deviation degree assessment according to the account and cargo comparison difference degree data, the gap account and cargo value data and the account and cargo gap duration data to obtain cargo account deviation degree assessment data;

C _g ＝μ ₁ s _t ×lgμ ₂ u _h p _w ；

wherein C is _g To lend account super-scale data, F _e For the data of the return degree of the extra-account fund, L _z Evaluating data for a cargo account deviation s _t 、u _h 、p _w Respectively, identity data of the lending account, borrowing amount data and borrowing period data, d _e 、m _s Respectively, account external fund flow period data and payable fund amount data, h _q 、y _e 、k _o Respectively account and goods comparison difference data, gap account and goods value data, account and goods gap duration data, mu,And (5) obtaining the characteristic coefficient for the preset characteristic coefficient (the characteristic coefficient is obtained through inquiring a preset enterprise tax execution monitoring database platform).

After the characteristic data of the enterprise loan account, the flow monitoring data of the account outer fund and the deviation data of the goods account record are obtained, corresponding tax-related evaluation calculation of the super-scale of the loan account, the return degree of the account outer fund and the deviation degree of the goods account is carried out according to each item of data, and the super-scale data of the loan account, the return degree data of the account outer fund and the deviation degree evaluation data of the goods account are respectively obtained.

According to the embodiment of the invention, according to the invoice service comparison information and the non-invoice service record information, respectively performing invoice service comparison deviation degree evaluation and non-invoice service oversaturation degree evaluation to respectively obtain invoice service deviation degree data and non-invoice service oversaturation degree data, specifically:

wherein B is _k For invoice business deviation degree data, Y _z Is non-ticket business oversubstance data, a _d 、g _s 、o _t Respectively comparing invoice amount with difference rate data, invoice business detail with deviation rate data and invoice information with total error rate data, f _r 、e _u 、w _y The system is characterized in that the system comprises ticketless service duty ratio data, ticketless service amount ratio data and ticketless expenditure service grade data, wherein lambda and upsilon are characteristic coefficients (the characteristic coefficients are obtained by inquiring a preset enterprise tax execution monitoring database platform).

And the invoice business deviation degree data and the non-ticket business oversaturation data related to tax are respectively obtained.

According to the embodiment of the invention, the tax optimal execution deviation degree evaluation is performed according to the tax optimal execution deviation condition data to obtain tax optimal execution deviation degree data, the payment tax payment difference degree evaluation is performed according to the payment tax monitoring data to obtain payment tax difference evaluation data, the asset tax offset error degree evaluation is performed according to the asset tax offset error data to obtain asset tax offset error degree evaluation data, specifically:

Wherein Q is _x For tax best execution deviation degree data, T _y Evaluation data for payment tax difference, A _q Evaluating data for asset tax-protection error degree, c _d 、n _p 、t _c Optimizing mismatch rate data, tax preferential qualification error rate data, tax ticket deduction mismatch rate data, x for tax rates, respectively _r 、r _w 、z _a Repeated tax payment amount data, j for social security payment non-compliance data, payroll payment tax breach amount data and payroll benefit _m 、b _v 、h _w The asset adjustment tax leakage data, the asset allocation deduction excess data and the asset repetition tax calculation data are respectively used for the asset adjustment tax leakage data,sigma, psi and ρ are preset characteristic coefficients (the characteristic coefficients are obtained by querying a preset enterprise tax execution monitoring database platform).

After tax optimal execution deviation status data, payment tax monitoring data and asset tax support error data are obtained, evaluation processing calculation of tax optimal execution deviation degree, payment tax difference degree and asset tax support error degree corresponding to tax is carried out according to each item data, and tax optimal execution deviation degree data, payment tax difference evaluation data and asset tax support error degree evaluation data are respectively obtained.

According to the embodiment of the invention, the risk evaluation processing is performed through a preset enterprise tax risk evaluation model according to the lending account super-scale data, the account outer fund return degree data, the goods account deviation evaluation data, the invoice business deviation data, the ticketless business super-scale data, the tax optimal execution deviation data, the reward tax payment difference evaluation data and the asset tax offset error evaluation data, so as to obtain an enterprise tax risk early warning evaluation index, which is specifically as follows:

wherein R is _φ C, early warning and evaluating index for enterprise tax risk _g To lend account super-scale data, F _e For the data of the return degree of the extra-account fund, L _z For evaluating data of deviation degree of goods account, B _k For the invoice industryData of business deviation degree, Y _z Is non-ticket business oversubscription data, Q _x For tax best execution deviation degree data, T _y Evaluation data for payment tax difference, A _q And evaluating data for the tax support error degree of the asset, wherein eta, epsilon, gamma and zeta are preset characteristic coefficients (the characteristic coefficients are obtained by inquiring a preset enterprise tax execution monitoring database platform).

And finally, calculating and evaluating through a calculation formula of a preset enterprise tax risk evaluation model according to the obtained evaluation result data of each item related to the enterprise tax, and obtaining an enterprise tax risk early warning evaluation index in a preset time period.

According to the embodiment of the invention, the method comprises the steps of acquiring a plurality of historical tax actual alarm values of the enterprise in the same period of history and a historical enterprise tax risk early warning evaluation average index of the enterprise with the same type of attribute enterprise through a preset enterprise tax execution monitoring database, and then correcting the enterprise tax risk early warning evaluation index to acquire an enterprise tax risk early warning correction index, wherein the method comprises the following specific steps:

wherein,early warning and correction for tax risk of enterprisesIndex, R _φ K is an enterprise tax risk early warning and evaluating index _fi For the i-th historical tax actual alarm value, < +.>And (3) evaluating average indexes for historical enterprise tax risk early warning, wherein pi, beta and theta are preset characteristic coefficients (the characteristic coefficients are obtained by inquiring a preset enterprise tax execution monitoring database platform).

In order to improve accuracy of enterprise tax risk condition assessment, a plurality of historical tax actual alarm values of enterprises in the same period of history are obtained through a preset enterprise tax execution monitoring database, the enterprise tax execution monitoring database is a preset database for carrying out information collection and data monitoring on tax execution conditions of each enterprise in each historical period, alarm values corresponding to actual alarm conditions of the enterprises in tax execution in the same historical period are extracted through the database, average indexes of historical enterprise tax risk early warning evaluation results of sample enterprises with the same type of enterprise attributes are obtained through the database, correction processing is carried out on the enterprise tax risk early warning evaluation indexes of the enterprises through the plurality of historical tax actual alarm values and the average indexes, enterprise tax risk early warning correction indexes are obtained, and accuracy of the enterprise tax risk assessment results in the time period is improved through obtaining of correction indexes.

The invention also discloses an enterprise tax risk early warning system, which comprises a memory and a processor, wherein the memory comprises an enterprise tax risk early warning method program, and the enterprise tax risk early warning method program realizes the following steps when the processor executes sign abnormal correction data:

According to an embodiment of the present invention, the extracting, according to the loan account record information, the financial report data information and the inventory account record information, the loan account feature data, the account foreign fund flow monitoring data and the inventory account record deviation data respectively includes:

According to the embodiment of the invention, the invoice service comparison information and the ticketless service record information are extracted according to the invoice issuing monitoring information, and the tax optimal execution deviation condition data, the payment tax monitoring data and the asset tax error data are respectively extracted according to the tax optimal execution condition information, the payment tax monitoring information and the asset tax error information, specifically:

According to an embodiment of the present invention, the performing the lending account superscale evaluation according to the lending account feature data to obtain the lending account superscale data, performing the account outer fund reflux degree evaluation according to the account outer fund flow monitoring data to obtain the account outer fund reflux degree data, and performing the goods account deviation degree evaluation according to the goods account record deviation data to obtain the goods account deviation degree evaluation data, specifically:

C _g ＝μ ₁ s _t ×lgμ ₂ u _h p _w ；

wherein R is _φ C, early warning and evaluating index for enterprise tax risk _g To lend account super-scale data, F _e For the data of the return degree of the extra-account fund, L _z For evaluating data of deviation degree of goods account, B _k For invoice business deviation degree data, Y _z Is non-ticket business oversubscription data, Q _x For tax best execution deviation degree data, T _y Evaluation data for payment tax difference, A _q And evaluating data for the tax support error degree of the asset, wherein eta, epsilon, gamma and zeta are preset characteristic coefficients (the characteristic coefficients are obtained by inquiring a preset enterprise tax execution monitoring database platform).

wherein,for enterprise tax risk early warning correction index, R _φ K is an enterprise tax risk early warning and evaluating index _fi For the i-th historical tax actual alarm value, < +.>And (3) evaluating average indexes for historical enterprise tax risk early warning, wherein pi, beta and theta are preset characteristic coefficients (the characteristic coefficients are obtained by inquiring a preset enterprise tax execution monitoring database platform).

A third aspect of the present invention provides a computer readable storage medium, where the readable storage medium includes an enterprise tax risk early warning method program, where the enterprise tax risk early warning method program, when executed by a processor, implements the steps of the enterprise tax risk early warning method according to any one of the above.

The invention discloses an enterprise tax risk early warning method, system and medium, which are characterized in that financial account management records and tax activity log information of an enterprise are obtained, financial account characteristic data, account outer data flow monitoring data, goods account record deviation data, tax optimal execution deviation condition data, reward tax payment monitoring data and asset tax support error data are extracted, each data is evaluated to obtain financial account overscale data, account outer data return data, goods account deviation evaluation data, invoice business deviation data, ticketless business overscaling data, tax optimal execution deviation data, reward tax payment difference evaluation data and asset tax support error evaluation data, tax risk evaluation is carried out to obtain enterprise tax risk early warning index, and enterprise tax risk early warning correction index is obtained by combining a plurality of historical tax actual warning values and historical enterprise tax risk early warning average index correction, and enterprise tax risk early warning correction conditions are compared in a later threshold value judgment time; therefore, the tax risk evaluation early warning result is obtained by processing the plurality of pieces of monitoring information data of the enterprise, and the enterprise tax risk early warning technology is realized.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.

Alternatively, the above-described integrated units of the present invention may be stored in a readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solution of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.

Claims

1. The enterprise tax risk early warning method is characterized by comprising the following steps of:

2. The method of claim 1, wherein extracting the loan account feature data, the foreign fund flow monitoring data, and the ledger record deviation data according to the loan account record information, the financial data information, and the ledger record information, respectively, comprises:

3. The method of claim 2, wherein extracting invoice business comparison information and ticketless business record information according to the invoice issue monitoring information, extracting tax optimal execution deviation status data, payment tax monitoring data and asset tax control error data according to the tax optimal execution status information, payment tax monitoring information and asset tax control status information respectively, comprises:

4. The enterprise tax risk pre-warning method of claim 3, wherein the performing the lending account superscale evaluation according to the lending account feature data to obtain lending account superscale data, performing the account outer fund reflux evaluation according to the account outer fund flow monitoring data to obtain account outer fund reflux data, performing the goods account deviation evaluation according to the goods account record deviation data to obtain goods account deviation evaluation data, comprising:

C _g ＝μ ₁ s _t ×lgμ ₂ u _h p _w ；

wherein C is _g To lend account super-scale data, F _e For the data of the return degree of the extra-account fund, L _z Evaluating data for a cargo account deviation s _t 、u _h 、p _w Respectively, identity data of the lending account, borrowing amount data and borrowing period data, d _e 、m _s Respectively, account external fund flow period data and payable fund amount data, h _q 、y _e 、k _o Respectively account and goods contrast difference data, gap account and goods value data and account and goods gap duration data,is a preset characteristic coefficient.

5. The method for enterprise tax risk early warning according to claim 4, wherein the performing invoice business comparison deviation degree evaluation and non-invoice business overscaling evaluation according to the invoice business comparison information and non-invoice business record information respectively, obtaining invoice business deviation degree data and non-invoice business overscaling data, comprises:

6. The method of claim 5, wherein performing tax bias evaluation according to the tax bias condition data to obtain tax bias data, performing tax bias evaluation according to the tax payment monitoring data to obtain tax payment difference evaluation data, performing asset tax bias error evaluation according to the asset tax bias error data, and obtaining asset tax bias error evaluation data, and comprising:

7. The method for early warning of tax risk of enterprises according to claim 6, wherein the processing of risk assessment according to the lending account overscale data, the extra-account fund return data, the goods account deviation assessment data, the invoice business deviation data combined with the ticketless business overscaling data, the tax optimal execution deviation data, the tax payment difference assessment data and the asset tax support error assessment data by a preset enterprise tax risk assessment model to obtain an enterprise tax risk early warning assessment index comprises:

8. The method for pre-warning the tax risk of the enterprise according to claim 7, wherein the obtaining, by the preset enterprise tax execution monitoring database, the plurality of historical tax actual warning values of the enterprise in the same period of history and the average index of historical enterprise tax risk pre-warning evaluations of the enterprise of the same type of attribute, and then performing correction processing on the index of the tax risk pre-warning evaluations to obtain a corrected index of the tax risk pre-warning of the enterprise comprises:

9. An enterprise tax risk early warning system, comprising: the system comprises a memory and a processor, wherein the memory comprises a program of an enterprise tax risk early warning method, and the program of the enterprise tax risk early warning method realizes the following steps when being executed by the processor:

10. A computer readable storage medium, characterized in that it comprises an enterprise tax risk pre-warning method program, which, when executed by a processor, implements the steps of the enterprise tax risk pre-warning method according to any one of claims 1 to 8.