Logistics tax intelligent management method and device, equipment and storage medium

Abstract

The invention relates to the technical field of information processing, in particular to a logistics tax intelligent management method, device and equipment and a storage medium, and aims to match tax types corresponding to transportation data and storage data, perform tax auditing calculation according to the tax types by using a tax calculation model to obtain a tax calculation result, automatically calculate logistics tax, and improve the management efficiency of the logistics tax. Tediousness and errors of manual accounting are avoided, the efficiency and accuracy of tax management are improved, risk early warning analysis is performed according to a tax fee calculation result by using a tax risk assessment model to obtain a risk early warning analysis result, and when the risk early warning analysis result exceeds a preset early warning threshold value, risk early warning information is generated according to the risk early warning analysis result, so that the risk management efficiency is improved. And the risk early warning information is sent to the management terminal, real-time monitoring and early warning are carried out on tax risks, potential tax risks are found in time, and an enterprise can be helped to take measures to correct the tax risks in time and reduce the tax risks.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a logistics tax intelligent management method, device, equipment and storage medium. Background Art

[0002] In the logistics industry, tax management has always been an important link. Different types of logistics businesses correspond to different types of taxes and fees, including transportation tax and warehousing tax. Traditional tax management methods mainly rely on manual accounting and declaration, which are inefficient, inaccurate and prone to tax risks. Therefore, it is impossible to monitor and warn of tax risks in real time, and it is impossible to discover potential tax risks in time, and it is difficult to help enterprises take measures to correct them in time. It is impossible to achieve the effect of intelligent management of logistics taxes, which reduces the efficiency and accuracy of tax management and increases tax risks. Summary of the invention

[0003] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a logistics tax intelligent management method, device, equipment and storage medium that automatically calculates logistics taxes and fees, avoids the tediousness and errors of manual calculations, improves the efficiency and accuracy of tax management, conducts real-time monitoring and early warning of tax risks, promptly discovers potential tax risks, and helps enterprises take measures to promptly correct and reduce tax risks.

[0004] The first aspect of the present invention provides a method for intelligent management of logistics taxation, including: collecting logistics process data, preprocessing the logistics process data to obtain logistics process preprocessing data; classifying the logistics process preprocessing data to obtain transportation data and warehousing data, and calling a preset tax calculation model and a tax risk assessment model; matching the tax types corresponding to the transportation data and the warehousing data respectively, and performing tax audit calculations according to the tax types using the tax calculation model to obtain tax calculation results; performing risk warning analysis according to the tax calculation results using the tax risk assessment model to obtain risk warning analysis results, and judging whether the risk warning analysis results exceed a preset warning threshold; if so, generating risk warning information based on the risk warning analysis results, and sending the risk warning information to a management terminal.

[0005] Optionally, in a first implementation method of the first aspect of the present invention, the logistics process data is collected and pre-processed to obtain logistics process pre-processed data, including: collecting logistics process data, parsing the logistics process data to obtain logistics process parsed data; cleaning the logistics process parsed data to obtain logistics process cleaned data; correcting erroneous data in the logistics process cleaned data using regular expressions to obtain logistics process corrected data; filling missing values ​​in the logistics process corrected data to obtain logistics process filled data; and formatting the logistics process filled data based on a preset target standard format to obtain logistics process pre-processed data.

[0006] Optionally, in a second implementation method of the first aspect of the present invention, the logistics process preprocessing data is classified to obtain transportation data and warehousing data, and a preset tax calculation model and a tax risk assessment model are called, including: identifying all data tags in the logistics process preprocessing data; classifying the logistics process preprocessing data according to the data tags to obtain transportation data and warehousing data; and calling a preset tax calculation model and a tax risk assessment model.

[0007] Optionally, in a third implementation method of the first aspect of the present invention, the matching of the tax types corresponding to the transportation data and the warehousing data respectively, and using the tax calculation model to perform tax audit calculation according to the tax types to obtain a tax calculation result, includes: matching the tax types corresponding to the transportation data and the warehousing data respectively, the tax types including the transportation tax corresponding to the transportation data and the warehousing tax corresponding to the warehousing data; based on a weighted average algorithm, using the tax calculation model to perform tax audit calculation on the transportation tax to obtain a first calculation result; based on a linear regression algorithm, using the tax calculation model to perform tax audit calculation on the warehousing tax to obtain a second calculation result; integrating the first calculation result and the second calculation result to obtain a tax calculation result.

[0008] Optionally, in a fourth implementation method of the first aspect of the present invention, the tax risk assessment model is used to perform a risk warning analysis based on the tax calculation results to obtain a risk warning analysis result, and whether the risk warning analysis result exceeds a preset warning threshold value, including: dividing the tax risk assessment problem into multiple levels, and comparing the relative importance of each factor in the same level; establishing a judgment matrix based on the relative importance, and solving the maximum eigenvalue and corresponding eigenvector of the judgment matrix based on the hierarchical analysis method to obtain the weight of each risk indicator; using the tax risk assessment model to perform a risk warning analysis based on the weights and the tax calculation results to obtain a risk warning analysis result; identifying the comprehensive risk score of the risk warning analysis result; and judging whether the comprehensive risk score exceeds the preset warning threshold value.

[0009] Optionally, in a fifth implementation method of the first aspect of the present invention, if so, risk warning information is generated according to the risk warning analysis results, and the risk warning information is sent to a management terminal, including: if so, risk warning information is generated according to the risk warning analysis results; processing suggestion plan information having a mapping relationship with the risk warning information is obtained from a preset risk processing plan library; the risk warning information and the processing suggestion plan information are merged to obtain merged information; and the merged information is sent to a management terminal.

[0010] Optionally, in a sixth implementation method of the first aspect of the present invention, if so, risk warning information is generated according to the risk warning analysis results, and after the risk warning information is sent to the management terminal, it also includes: encrypting the risk warning information to obtain encrypted information, and uploading the encrypted information to the blockchain; creating a listener, and using the listener to listen to real-time tax and fee policy information; when the listener listens to the real-time tax and fee policy information, obtaining the current real-time tax and fee policy information; and dynamically adjusting the tax rate range of the corresponding tax in the tax calculation model according to the real-time tax and fee policy information.

[0011] The second aspect of the present invention provides a logistics tax intelligent management device, including: a collection and processing module, which is used to collect logistics process data, pre-process the logistics process data, and obtain logistics process pre-processed data; a classification and calling module, which is used to classify the logistics process pre-processed data, obtain transportation data and warehousing data, and call a preset tax calculation model and a tax risk assessment model; a matching calculation module, which is used to match the tax types corresponding to the transportation data and the warehousing data, respectively, and use the tax calculation model to perform tax audit calculation according to the tax types to obtain tax calculation results; an analysis and judgment module, which is used to use the tax risk assessment model to perform risk warning analysis according to the tax calculation results, obtain risk warning analysis results, and judge whether the risk warning analysis results exceed the preset warning threshold; a generation and sending module, which is used to generate risk warning information according to the risk warning analysis results if so, and send the risk warning information to the management terminal.

[0012] Optionally, in a first implementation method of the second aspect of the present invention, the acquisition and processing module includes: an acquisition and parsing unit, which is used to collect logistics process data, parse the logistics process data, and obtain logistics process parsed data; a cleaning unit, which is used to clean the logistics process parsed data, and obtain logistics process cleaned data; a correction unit, which is used to correct erroneous data in the logistics process cleaned data using a regular expression, and obtain logistics process corrected data; a filling unit, which is used to fill missing values ​​in the logistics process corrected data, and obtain logistics process filled data; a conversion unit, which is used to convert the format of the logistics process filled data based on a preset target standard format, and obtain logistics process preprocessed data.

[0013] Optionally, in a second implementation of the second aspect of the present invention, the classification calling module includes: a first identification unit, used to identify all data labels in the logistics process preprocessing data; a classification unit, used to classify the logistics process preprocessing data according to the data labels to obtain transportation data and warehousing data; and a calling unit, used to call a preset tax calculation model and tax risk assessment model.

[0014] Optionally, in a third implementation method of the second aspect of the present invention, the matching calculation module includes: a matching unit, used to match the tax types corresponding to the transportation data and the warehousing data respectively, the tax types including the transportation tax corresponding to the transportation data and the warehousing tax corresponding to the warehousing data; a first calculation unit, used to perform a tax audit calculation on the transportation tax based on a weighted average algorithm using the tax calculation model to obtain a first calculation result; a second calculation unit, used to perform a tax audit calculation on the warehousing tax based on a linear regression algorithm using the tax calculation model to obtain a second calculation result; and an integration unit, used to integrate the first calculation result and the second calculation result to obtain a tax calculation result.

[0015] Optionally, in a fourth implementation method of the second aspect of the present invention, the analysis and judgment module includes: a division and comparison unit, used to divide the tax risk assessment problem into multiple levels, and compare the relative importance of each factor in the same level; a solution unit, used to establish a judgment matrix according to the relative importance, and solve the maximum eigenvalue and corresponding eigenvector of the judgment matrix based on the hierarchical analysis method to obtain the weight of each risk indicator; an analysis unit, used to use the tax risk assessment model to perform risk warning analysis according to the weights and the tax calculation results to obtain a risk warning analysis result; a second identification unit, used to identify the comprehensive risk score of the risk warning analysis result; a judgment unit, used to judge whether the comprehensive risk score exceeds a preset warning threshold.

[0016] Optionally, in a fifth implementation of the second aspect of the present invention, the generation and sending module includes: a generation unit, which is used to generate risk warning information according to the risk warning analysis results; an acquisition unit, which is used to acquire, from a preset risk handling solution library, processing suggestion plan information that has a mapping relationship with the risk warning information; a merging unit, which is used to merge the risk warning information and the processing suggestion plan information to obtain merged information; and a sending unit, which is used to send the merged information to a management terminal.

[0017] Optionally, in a sixth implementation method of the second aspect of the present invention, it also includes: an encryption upload module, used to encrypt the risk warning information, obtain encrypted information, and upload the encrypted information to the blockchain; a monitoring module is created, used to create a listener, and use the listener to monitor real-time tax and fee policy information; an acquisition module is used to obtain the current real-time tax and fee policy information when the listener listens to the real-time tax and fee policy information; an adjustment module is used to dynamically adjust the tax rate range of the corresponding tax in the tax and fee calculation model according to the real-time tax and fee policy information.

[0018] The third aspect of the present invention provides a logistics tax intelligent management device, which includes: a memory and at least one processor, wherein the memory stores instructions; at least one of the processors calls the instructions in the memory to enable the logistics tax intelligent management device to execute each step of the logistics tax intelligent management method described in any one of the above items.

[0019] The fourth aspect of the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the various steps of any of the above-mentioned logistics tax intelligent management methods are implemented.

[0020] In the technical solution of the present invention, by matching the tax types corresponding to the transportation data and the warehousing data respectively, the tax calculation model is used to perform tax audit calculations according to the tax types to obtain the tax calculation results, and the logistics taxes are automatically calculated, thereby avoiding the tediousness and errors of manual calculations and improving the efficiency and accuracy of tax management. The tax risk assessment model is used to perform risk warning analysis according to the tax calculation results to obtain the risk warning analysis results. When the risk warning analysis results exceed the preset warning threshold, risk warning information is generated according to the risk warning analysis results, and the risk warning information is sent to the management terminal to monitor and warn tax risks in real time, and timely discover potential tax risks, so as to help enterprises take measures to correct them in time and reduce tax risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A first flow chart of the logistics tax intelligent management method provided by an embodiment of the present invention;

[0022] Figure 2 A second flow chart of the logistics tax intelligent management method provided by an embodiment of the present invention;

[0023] Figure 3 A third flow chart of the logistics tax intelligent management method provided by an embodiment of the present invention;

[0024] Figure 4 A fourth flow chart of the logistics tax intelligent management method provided by an embodiment of the present invention;

[0025] Figure 5 A schematic diagram of the structure of a logistics tax intelligent management device provided by an embodiment of the present invention;

[0026] Figure 6 Another structural schematic diagram of the logistics tax intelligent management device provided by an embodiment of the present invention;

[0027] Figure 7 A schematic diagram of the structure of the logistics tax intelligent management device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The present invention provides a logistics tax intelligent management method, device, equipment and storage medium, which automatically calculates logistics taxes and fees, avoids the tediousness and errors of manual calculations, improves the efficiency and accuracy of tax management, conducts real-time monitoring and early warning of tax risks, promptly discovers potential tax risks, and helps enterprises take measures to correct them in a timely manner and reduce tax risks.

[0029] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 An embodiment of the logistics tax intelligent management method in the embodiment of the present invention includes:

[0031] 101. Collect logistics process data, pre-process the logistics process data, and obtain logistics process pre-processed data;

[0032] In this embodiment, the source of data collection is determined, such as the logistics management system and sensors, barcode scanners, RFID devices, GPS positioning devices, etc. installed in logistics transportation vehicles and warehouses, the type of data to be collected is identified, including transportation mode, transportation time, transportation route, cargo status, warehouse temperature and humidity, warehouse inventory, warehouse area, storage time, etc., the frequency of data collection is set to ensure real-time or regular data acquisition, the data set is checked, duplicate records are removed, the uniqueness of the data is ensured, missing items in the data are identified, and appropriate filling strategies are selected, such as mean filling, interpolation, etc., regular expressions or other methods are applied to correct data that does not conform to the standard format, such as date format or numerical range, outliers are identified and processed to ensure the validity and accuracy of the data, and a method for filling missing values ​​is selected according to the characteristics of the data to ensure the integrity of the data, and to ensure that all data are in a unified unit, such as unifying all distances into kilometers, and normalizing data of different dimensions for subsequent analysis.

[0033] 102. Classify the pre-processed data of the logistics process, obtain the transportation data and warehousing data, and call the preset tax calculation model and tax risk assessment model;

[0034] In this embodiment, it is determined how to distinguish between transportation data and warehousing data. For example, transportation data involves information such as the time, place, method, and status of cargo transportation, and warehousing data involves information such as inventory, warehousing, outbound delivery, and storage conditions. Preprocessed data is marked as "transportation data" or "warehousing data" using predefined labels or attributes. For example, it can be identified by field name or keyword, and the tax calculation model applicable to transportation and warehousing is determined. Relevant tax regulations and tax rate information are prepared to ensure that the calculation of the model complies with current laws and regulations. The classified transportation data and warehousing data are sorted and formatted according to the requirements of the model.

[0035] 103. Match the tax types corresponding to the transportation data and warehousing data, and use the tax calculation model to perform tax audit calculations according to the tax types to obtain tax calculation results;

[0036] In this embodiment, all types of taxes and fees related to transportation and warehousing are determined, the conditions and standards for the application of each tax and fee are determined based on the business type, cargo characteristics, mode of transportation, etc., the transportation data and warehousing data are matched according to business rules and tax types, and the tax calculation model is used to perform tax audit calculations based on the tax types to obtain tax calculation results.

[0037] 104. Use the tax risk assessment model to conduct risk warning analysis based on the tax calculation results, obtain the risk warning analysis results, and determine whether the risk warning analysis results exceed the preset warning threshold;

[0038] In this embodiment, a suitable tax risk assessment model is selected, historical data, industry benchmarks and specific risk indicators are considered, the input parameters of the model are set according to the tax calculation results, including tax amount, tax type, historical compliance records, etc., the tax calculation results are sorted, and the relevant data are converted into a format acceptable to the model, including numerical and categorical variables, the completeness and accuracy of the input data are verified to improve the reliability of the analysis, the tax risk assessment model is run, the input tax data is analyzed, potential tax risks are identified, and the model results are output, including risk scores, major risk factors and their impact, and reasonable risk warning thresholds are set according to historical data and industry standards to facilitate subsequent judgments, and the risk analysis results are compared with the preset thresholds to determine whether they exceed the warning line. According to the comparison results, the risks are divided into three levels: normal, concern and warning, so that corresponding measures can be taken.

[0039] 105. If yes, generate risk warning information according to the risk warning analysis result, and send the risk warning information to the management terminal;

[0040] In this embodiment, if the risk warning analysis result exceeds the preset warning threshold, the structure of the risk warning information is determined, including the risk level, risk description, scope of impact, recommended measures, etc. The risk analysis results are integrated with other relevant data, such as historical compliance records, industry benchmarks, etc. to enhance the integrity of the information. Risk warning information is generated based on the risk warning analysis results, and appropriate sending channels, such as e-mail, internal management systems, instant messaging applications, etc., are determined. The system is configured to ensure that the risk warning information is automatically sent when the risk assessment results reach the preset threshold, and the risk warning information is sent to the management terminal to reduce human intervention. The sending time, channel and recipient are recorded to facilitate subsequent tracking and auditing.

[0041] In an embodiment of the present invention, by matching the types of taxes and fees corresponding to the transportation data and warehousing data respectively, a tax calculation model is used to perform tax audit calculations according to the types of taxes and fees to obtain tax calculation results, and logistics taxes and fees are automatically calculated, thereby avoiding the tediousness and errors of manual calculations and improving the efficiency and accuracy of tax management. A tax risk assessment model is used to perform risk warning analysis based on the tax calculation results to obtain risk warning analysis results. When the risk warning analysis results exceed a preset warning threshold, risk warning information is generated based on the risk warning analysis results, and the risk warning information is sent to a management terminal to monitor and warn tax risks in real time, and to promptly discover potential tax risks, so as to help enterprises take measures to promptly correct and reduce tax risks.

[0042] See also Figure 2 The second embodiment of the logistics tax intelligent management method in the embodiment of the present invention includes:

[0043] 201. Collect logistics process data, analyze the logistics process data, and obtain logistics process analysis data;

[0044] In this embodiment, the source of data collection is determined, such as the logistics management system and sensors, barcode scanners, RFID devices, GPS positioning devices, etc. installed in logistics transportation vehicles and warehouses, and the type of data to be collected is identified, including transportation method, transportation time, transportation route, cargo status, warehouse temperature and humidity, warehouse inventory, warehouse area, storage time, etc. The frequency of data collection is set to ensure real-time or regular data acquisition, and Python is used to parse the logistics process data to obtain logistics process parsed data.

[0045] 202. Perform data cleaning on the logistics process analysis data to obtain logistics process cleansing data;

[0046] In this embodiment, the identification criteria for duplicate data are set, such as the same cargo ID and transportation time, and duplicate records are identified and removed to ensure the uniqueness of each record. The cleaned data is saved as a new data set to obtain the logistics process cleaned data.

[0047] 203. Use regular expressions to correct erroneous data in the logistics process cleaning data to obtain logistics process correction data;

[0048] In this embodiment, the fields that need to be corrected are identified, such as whether the format is uniform, whether there are spelling errors or multiple expressions, and appropriate regular expressions are written according to the identified data type. Each record in the data set is traversed and the regular expression is applied for matching and correction. For example, if a certain product ID does not conform to the regular expression, the ID is recorded and replaced with a default value or a correct value inferred by other logic.

[0049] 204. Fill missing values ​​in the logistics process correction data to obtain logistics process filled data;

[0050] In this embodiment, it is determined which fields have missing values, and the reasons for the missing values ​​are understood, such as data entry errors, system failures, etc. According to the nature of the missing values, a suitable filling method is selected. For numeric fields (such as transportation time), the mean or median of non-missing values ​​is calculated, and the missing values ​​are replaced with this value, or the missing values ​​are filled with the value of the previous record or the next record. For categorical fields (such as cargo status), the most common status is used to fill the missing values, or the status is inferred based on the cargo ID or transportation time (such as "in transit" if it is within a specific time range). The data set is traversed, and the selected filling method is applied to the missing values ​​in each record. The number of missing values ​​before and after filling is counted to ensure that all missing values ​​have been processed.

[0051] 205. Based on the preset target standard format, the logistics process filling data is format converted to obtain the logistics process preprocessing data;

[0052] In this embodiment, the preset target standard format is determined, the original data format is checked, including the field name, data type, missing value situation and abnormal value, the existing data format is compared with the target standard format, the fields and data that need to be converted are found, the existing field names are converted to the names in the target standard format, for the data that needs to be converted to numerical data (such as transportation time), the correct format is ensured (such as conversion from string to numerical value), for category fields, the data is ensured to meet the preset category standard, and for date and time data, the format is ensured to be unified, for example, all dates are unified into the "YYYY-MM-DD" format.

[0053] 206. Identify all data tags in the pre-processed data of the logistics process;

[0054] In this embodiment, the data label refers to the field name or identifier that describes specific data, such as cargo ID, transportation time, cargo status, etc. View the original data set, list all currently existing field names, record the format and data type of each field, and identify the basic fields directly related to the logistics process.

[0055] 207. Classify the pre-processed data of the logistics process according to the data labels to obtain transportation data and warehousing data;

[0056] In this embodiment, data labels related to transportation are extracted from the preprocessed data set to form a transportation data set, and data labels related to warehousing are extracted to form a warehousing data set. According to the nature of the data labels, the data are clearly divided into transportation or warehousing categories, and classification rules are written using programming or data processing tools (such as Python, Excel, etc.) to automate identification and classification. The classification results are compared with business realities to ensure that each record is correctly classified.

[0057] 208. Call the preset tax calculation model and tax risk assessment model;

[0058] In this embodiment, the purpose of the model is understood, and the preset tax calculation model and tax risk assessment model are called according to the purpose. The tax calculation model is intended to automatically calculate the taxes payable, and the tax risk assessment model is used to identify and assess potential tax risks, helping enterprises take measures in advance to avoid legal and financial risks.

[0059] 209. Match the tax types corresponding to the transportation data and the warehousing data, respectively. The tax types include the transportation tax corresponding to the transportation data and the warehousing tax corresponding to the warehousing data;

[0060] In this embodiment, the types of taxes and fees corresponding to the transportation data and warehousing data are matched respectively. The transportation tax is the tax payable for the transportation service, and the warehousing tax is the tax payable for the warehousing service. The transportation data is collected, including the transportation company, transportation method, transportation amount, invoice information, transportation time, etc., and the warehousing data is collected, including warehouse information, storage time, warehousing fees, invoice information, etc.

[0061] 210. Based on the weighted average algorithm, the tax calculation model is used to perform tax audit calculation on the transportation tax to obtain a first calculation result;

[0062] In this embodiment, the cost information of each transport order is obtained, including basic fees and additional fees, and different modes of transportation (such as land, sea, air, etc.) are identified, because the tax rates of different modes may be different. The quantity and frequency of each type of transportation are recorded for use in weighted calculations, the tax rates applicable to different types of transportation and regions are confirmed, and relevant tax policy change information is obtained to ensure that the tax rates used are the latest. Weights are set according to the importance of the transportation amount, transportation frequency, and transportation type. Based on the weighted average algorithm, the transportation costs, tax rates, weights, etc. are input into the tax calculation model for calculation to obtain the first calculation result.

[0063] 211. Based on the linear regression algorithm, the tax calculation model is used to perform tax audit calculation on the storage tax to obtain the second calculation result;

[0064] In this embodiment, the fees of different warehousing orders, including basic fees and additional fees, are collected, the occupied area and storage time of each warehousing order are recorded, different types of goods are identified, because different tax rates may be applicable to different goods, the tax rates applicable to different types of warehousing are determined, and the latest information on relevant tax policies is obtained to ensure that the tax rate used is the latest. Based on the linear regression algorithm, the storage area, storage time, and type of goods are input into the tax calculation model for calculation to obtain the second calculation result.

[0065] 212. Integrate the first calculation result and the second calculation result to obtain a tax calculation result;

[0066] In this embodiment, the first calculation result and the second calculation result are integrated into a data frame to obtain the tax calculation result.

[0067] In the embodiment of the present invention, it is ensured that the entire process from data collection to final calculation is standardized, thereby improving the overall efficiency. The links such as data cleaning, correction and missing value filling ensure the accuracy and completeness of the input data, thereby improving the reliability of subsequent analysis. The use of regular expressions and algorithms for data correction and calculation embodies automation and intelligence, improves processing efficiency, and identifies and classifies data labels to help clarify the processing methods of different data, ensure the pertinence and accuracy of tax calculations. Through the application of tax risk assessment models, potential tax risks can be identified and responded to in a timely manner, provide support for decision-making, integrate the calculation results of transportation tax and warehousing tax, and provide comprehensive tax calculation results, which is conducive to better financial analysis and decision-making.

[0068] See also Figure 3 The third embodiment of the logistics tax intelligent management method in the embodiment of the present invention includes:

[0069] 301. Divide tax risk assessment issues into multiple levels and compare the relative importance of factors at the same level;

[0070] In this embodiment, the tax risk assessment problem is divided into multiple levels, and the factors of each level are further subdivided to compare the relative importance of the factors in the same level.

[0071] 302. Establish a judgment matrix based on relative importance, solve the maximum eigenvalue and corresponding eigenvector of the judgment matrix based on the hierarchical analysis method, and obtain the weight of each risk indicator;

[0072] In this embodiment, all risk indicators that need to be evaluated are listed, such as "regulatory compliance", "financial transparency", "operational risk", "external environment", etc., and these indicators are compared in pairs according to the relative importance standard, and filled in the judgment matrix. The eigenvalue decomposition method of the matrix is ​​used to calculate the eigenvalue of the judgment matrix, and the eigenvector corresponding to the maximum eigenvalue is obtained by solving the equation. Each element of these eigenvectors corresponds to the relative weight of the indicator, and each element in the eigenvector is normalized so that the sum of the weights is 1.

[0073] 303. Use the tax risk assessment model to conduct risk warning analysis based on the weights and tax calculation results to obtain risk warning analysis results;

[0074] In this embodiment, the weights calculated previously are applied to the tax calculation results to obtain weighted tax calculation results, and the tax risk assessment model is used to perform risk warning analysis on the weighted tax calculation results to obtain risk warning analysis results.

[0075] 304. Identify the comprehensive risk score of the risk warning analysis results;

[0076] In this embodiment, the risk warning analysis result includes the specific content of the risk, the cause of the risk, and the comprehensive risk score. The text recognition technology is used to identify the comprehensive risk score in the risk warning analysis result.

[0077] 305. Determine whether the comprehensive risk score exceeds the preset warning threshold;

[0078] In this embodiment, a warning threshold is set based on historical data and industry standards, and the comprehensive risk score is compared with the warning threshold to determine whether the comprehensive risk score exceeds the preset warning threshold.

[0079] 306. If yes, then generate risk warning information based on the risk warning analysis results;

[0080] In this embodiment, if the comprehensive risk score exceeds the preset warning threshold, the risk level is clearly marked, the specific risk source and characteristics are briefly described, the impact of the risk on the business, project or organization is assessed, the above content is generated as risk warning information, and the risk warning information is organized into a standardized format.

[0081] 307. Obtaining treatment suggestion plan information having a mapping relationship with risk warning information from a preset risk treatment plan library;

[0082] In this embodiment, the mapping relationship between risk warning information and risk treatment solutions is clarified. Relevant treatment solutions can be retrieved according to the specific risk types (such as financial risk, operational risk, compliance risk, etc.) described in the risk warning information, or appropriate treatment solutions can be selected according to the severity of the risk (low, medium, high). The query function of the database management system or risk management platform is used to retrieve relevant solutions from the risk treatment solution library, and searches are performed based on keywords in the risk warning information to find relevant treatment suggestions, or qualified treatment solutions are screened out based on preset risk classifications, and the retrieved treatment solutions are preliminarily evaluated to ensure that they are applicable to the current risk situation.

[0083] 308. Merge the risk warning information and the processing suggestion plan information to obtain merged information;

[0084] In this embodiment, the risk warning information and the corresponding treatment suggestion solutions are effectively combined to form a comprehensive report or document. Specifically, the risk warning information and the treatment suggestions are matched one by one and merged into complete information items. For each risk warning information, its corresponding treatment solution is found and merged to form a "risk description + treatment suggestion" format. The risks and corresponding treatment solutions are displayed in a table so that the information is clear at a glance. The merged information is integrated into a formal document to obtain merged information.

[0085] 309. Send the merge information to the management terminal;

[0086] In this embodiment, it is clear to which management terminals the merged information is to be sent, which may be senior managers, department heads or other relevant personnel, and a suitable sending channel is selected to send the merged information to the management terminal.

[0087] In the embodiment of the present invention, by processing risk assessment problems in a hierarchical manner, the comprehensiveness and systematicness of the analysis are ensured, which helps to clarify the relationship between complex factors. By using the judgment matrix and hierarchical analysis method, the weight of each risk indicator can be objectively quantified, which improves the scientific nature of the decision-making. The weight and tax calculation results are combined to perform risk warning analysis, so that potential risks can be identified in a timely manner, so that corresponding measures can be taken to reduce losses. Through the preset risk handling solution library, corresponding handling suggestions can be quickly obtained, which improves the efficiency and pertinence of risk response. The risk warning information and the handling suggestion solution information are merged to provide a more comprehensive decision-making basis, which helps the management to make a more effective response. The merged information is sent to the management terminal, which realizes the timely transmission of information and enhances the flexibility and adaptability of risk management.

[0088] See also Figure 4 The fourth embodiment of the logistics tax intelligent management method in the embodiment of the present invention includes:

[0089] 401. Encrypt the risk warning information to obtain encrypted information, and upload the encrypted information to the blockchain;

[0090] In this embodiment, a suitable encryption algorithm (such as AES, RSA, etc.) is selected according to security requirements, an encryption key is generated using a secure method, the risk warning information is encrypted using the selected algorithm and key to obtain encrypted information, the integrity of the encrypted information is verified to ensure that the information has not been tampered with during the encryption process, a suitable blockchain platform (such as Ethereum, Hyperledger, etc.) is selected, considering its security, scalability and supported smart contract functions, the encrypted information is encapsulated in the blockchain transaction, ensuring that the necessary metadata (such as timestamp, event type, etc.) is included, the transaction is broadcast in the blockchain network, ensuring that it is confirmed and written to the blockchain, obtaining an unalterable record, defining the personnel who can access the encrypted information and decryption keys, ensuring that only authorized users can access sensitive data, and recording all access and operation records for subsequent auditing and security monitoring.

[0091] 402. Create a listener and use it to monitor real-time tax policy information;

[0092] In this embodiment, the sources of tax and fee policy information that need to be monitored are identified, such as official government websites, tax bureau announcements, relevant industry platforms, etc., and the specific types of information that need to be monitored are clarified, including tax rate changes, policy updates, collection scope, etc., and a suitable listener architecture is selected, such as an event-driven architecture (such as using message queues) or a timed polling architecture, and the programming language and framework to be used (such as Python, Node.js), as well as tools for real-time data processing (such as Apache Kafka, Redis, etc.) are determined. The listener code is written according to the selected technology stack, the monitoring conditions are set, the relevant APIs are integrated for real-time data acquisition, and the trigger conditions are set. Once a new policy is released, it is processed immediately.

[0093] 403. When the listener listens to the real-time tax policy information, it obtains the current real-time tax policy information;

[0094] In this embodiment, once the listener is triggered, a request is immediately initiated to a preset data source (such as an API or a web page) to obtain the latest tax policy information, the obtained tax policy information is parsed, key information (such as policy content, release time, etc.) is extracted, and the parsed data is stored in the database. A reasonable data structure is designed, such as creating a "tax policy" table with fields including policy ID, title, content, release time, etc., and setting filtering rules to retain only relevant policy information and eliminate redundant data.

[0095] 404. Dynamically adjust the tax rate range of the corresponding tax in the tax calculation model according to the real-time tax policy information;

[0096] In this embodiment, the composition of the tax calculation model is clarified, including tax types, applicable tax rates, tax bases, calculation formulas, etc., and the basic structure of the model is set. After obtaining new tax policies, they are compared with the tax rates in the existing tax calculation model to identify which tax types need to be adjusted. If the tax rate range in the new policy is inconsistent with that in the current tax calculation model, the tax rate range in the tax calculation model is updated.

[0097] In the embodiment of the present invention, the risk warning information is encrypted and uploaded to the blockchain to ensure the security and non-tamperability of the information, enhance data protection, use a listener to monitor tax policies in real time, achieve rapid response to policy changes, ensure the timeliness and accuracy of tax calculations, dynamically adjust the tax rate range according to real-time policy information, improve the flexibility and adaptability of the tax calculation model, and help to better deal with the risks brought about by policy changes. The transparency provided by blockchain technology makes the information processing process traceable, thereby enhancing supervision and compliance.

[0098] The above describes the logistics tax intelligent management method in the embodiment of the present invention. The following describes the logistics tax intelligent management device in the embodiment of the present invention. Figure 5 In one embodiment of the present invention, an intelligent logistics tax management device includes:

[0099] The collection and processing module 501 is used to collect logistics process data, pre-process the logistics process data, and obtain logistics process pre-processed data;

[0100] The classification calling module 502 is used to classify the pre-processed data of the logistics process, obtain the transportation data and the warehousing data, and call the preset tax calculation model and the tax risk assessment model;

[0101] Matching calculation module 503, used to match the tax types corresponding to the transportation data and the warehousing data, respectively, and use the tax calculation model to perform tax audit calculation according to the tax types to obtain the tax calculation results;

[0102] The analysis and judgment module 504 is used to use the tax risk assessment model to perform risk warning analysis based on the tax calculation results, obtain risk warning analysis results, and determine whether the risk warning analysis results exceed a preset warning threshold;

[0103] The generating and sending module 505 is used to generate risk warning information according to the risk warning analysis result and send the risk warning information to the management terminal.

[0104] In this embodiment, by matching the tax types corresponding to the transportation data and warehousing data, the tax calculation model is used to perform tax audit calculations according to the tax types to obtain tax calculation results, and logistics taxes are automatically calculated, thereby avoiding the tediousness and errors of manual calculations and improving the efficiency and accuracy of tax management. The tax risk assessment model is used to perform risk warning analysis based on the tax calculation results to obtain risk warning analysis results. When the risk warning analysis results exceed the preset warning threshold, risk warning information is generated based on the risk warning analysis results, and the risk warning information is sent to the management terminal to monitor and warn tax risks in real time, and to promptly discover potential tax risks, so as to help enterprises take measures to promptly correct and reduce tax risks.

[0105] See also Figure 6 Another embodiment of the logistics tax intelligent management device in the embodiment of the present invention includes:

[0106] The collection and processing module 501 is used to collect logistics process data, pre-process the logistics process data, and obtain logistics process pre-processed data;

[0107] The classification calling module 502 is used to classify the pre-processed data of the logistics process, obtain the transportation data and the warehousing data, and call the preset tax calculation model and the tax risk assessment model;

[0108] Matching calculation module 503, used to match the tax types corresponding to the transportation data and the warehousing data, respectively, and use the tax calculation model to perform tax audit calculation according to the tax types to obtain the tax calculation results;

[0109] The analysis and judgment module 504 is used to use the tax risk assessment model to perform risk warning analysis based on the tax calculation results, obtain risk warning analysis results, and determine whether the risk warning analysis results exceed a preset warning threshold;

[0110] A generating and sending module 505 is used to generate risk warning information according to the risk warning analysis result and send the risk warning information to the management terminal;

[0111] In this embodiment, the collection and processing module 501 includes: an acquisition and analysis unit 5011, which is used to collect logistics process data, analyze the logistics process data, and obtain logistics process analysis data; a cleaning unit 5012, which is used to clean the logistics process analysis data to obtain logistics process cleaned data; a correction unit 5013, which is used to use regular expressions to correct erroneous data in the logistics process cleaned data to obtain logistics process corrected data; a filling unit 5014, which is used to fill missing values ​​in the logistics process corrected data to obtain logistics process filled data; a conversion unit 5015, which is used to convert the format of the logistics process filled data based on a preset target standard format to obtain logistics process preprocessed data.

[0112] In this embodiment, the classification calling module 502 includes: a first identification unit 5021, used to identify all data labels in the logistics process preprocessing data; a classification unit 5022, used to classify the logistics process preprocessing data according to the data labels to obtain transportation data and warehousing data; a calling unit 5023, used to call the preset tax calculation model and tax risk assessment model.

[0113] In this embodiment, the matching calculation module 503 includes: a matching unit 5031, which is used to match the tax types corresponding to the transportation data and the warehousing data, respectively, and the tax types include the transportation tax corresponding to the transportation data and the warehousing tax corresponding to the warehousing data; a first calculation unit 5032, which is used to perform tax audit calculation on the transportation tax based on the weighted average algorithm and the tax calculation model to obtain a first calculation result; a second calculation unit 5033, which is used to perform tax audit calculation on the warehousing tax based on the linear regression algorithm and the tax calculation model to obtain a second calculation result; an integration unit 5034, which is used to integrate the first calculation result and the second calculation result to obtain a tax calculation result.

[0114] In this embodiment, the analysis and judgment module 504 includes: a division and comparison unit 5041, which is used to divide the tax risk assessment problem into multiple levels and compare the relative importance of each factor in the same level; a solution unit 5042, which is used to establish a judgment matrix according to the relative importance, and solve the maximum eigenvalue and corresponding eigenvector of the judgment matrix based on the hierarchical analysis method to obtain the weight of each risk indicator; an analysis unit 5043, which is used to use the tax risk assessment model to perform risk warning analysis according to the weights and tax calculation results to obtain risk warning analysis results; a second identification unit 5044, which is used to identify the comprehensive risk score of the risk warning analysis result; a judgment unit 5045, which is used to judge whether the comprehensive risk score exceeds the preset warning threshold.

[0115] In this embodiment, the generation and sending module 505 includes: a generation unit 5051, which is used to generate risk warning information according to the risk warning analysis results; an acquisition unit 5052, which is used to obtain the processing suggestion plan information that has a mapping relationship with the risk warning information from a preset risk processing plan library; a merging unit 5053, which is used to merge the risk warning information and the processing suggestion plan information to obtain merged information; and a sending unit 5054, which is used to send the merged information to the management terminal.

[0116] In this embodiment, it also includes: an encryption upload module 506, which is used to encrypt the risk warning information, obtain the encrypted information, and upload the encrypted information to the blockchain; a creation monitoring module 507, which is used to create a listener and use the listener to monitor the real-time tax and fee policy information; an acquisition module 508, which is used to obtain the current real-time tax and fee policy information when the listener monitors the real-time tax and fee policy information; an adjustment module 509, which is used to dynamically adjust the tax rate range of the corresponding tax in the tax calculation model according to the real-time tax and fee policy information.

[0117] above Figure 5 and Figure 6 The logistics tax intelligent management device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The logistics tax intelligent management device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0118] Figure 76 is a schematic diagram of the structure of a logistics tax intelligent management device provided by an embodiment of the present invention. The logistics tax intelligent management device 600 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (for example, one or more processors) and a memory 620, and one or more storage media 630 (for example, one or more mass storage devices) storing application programs 633 or data 632. Among them, the memory 620 and the storage medium 630 can be short-term storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the logistics tax intelligent management device 600. Furthermore, the processor 610 can be configured to communicate with the storage medium 630, and execute a series of instruction operations in the storage medium 630 on the logistics tax intelligent management device 600 to implement the steps of the logistics tax intelligent management method provided by the above-mentioned method embodiments.

[0119] The logistics tax intelligent management device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input and output interfaces 660, and / or one or more operating systems 631, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that Figure 7 The structure of the logistics tax intelligent management device shown does not constitute a limitation on the logistics tax intelligent management device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0120] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the logistics tax intelligent management method.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0123] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A logistics tax intelligent management method, characterized in that: include: Collecting logistics process data, and preprocessing the logistics process data to obtain logistics process preprocessing data; Classify the logistics process preprocessing data to obtain transportation data and warehousing data, and call the preset tax calculation model and tax risk assessment model; Matching the tax types corresponding to the transportation data and the warehousing data, respectively, and performing tax audit calculation according to the tax types using the tax calculation model to obtain tax calculation results; Using the tax risk assessment model to perform risk warning analysis based on the tax calculation results, obtaining risk warning analysis results, and determining whether the risk warning analysis results exceed a preset warning threshold; If so, risk warning information is generated according to the risk warning analysis result, and the risk warning information is sent to the management terminal.

2. The intelligent logistics tax management method according to claim 1 is characterized in that: The collecting of logistics process data and preprocessing of the logistics process data to obtain logistics process preprocessed data include: Collecting logistics process data, analyzing the logistics process data, and obtaining logistics process analysis data; Performing data cleaning on the logistics process analysis data to obtain logistics process cleaning data; Using regular expressions to correct erroneous data in the logistics process cleaning data to obtain logistics process corrected data; Filling missing values ​​in the logistics process correction data to obtain logistics process filled data; Based on a preset target standard format, the logistics process filling data is format converted to obtain logistics process preprocessing data.

3. The intelligent logistics tax management method according to claim 1 is characterized in that: The logistics process preprocessing data is classified to obtain transportation data and warehousing data, and a preset tax calculation model and tax risk assessment model are called, including: Identify all data tags in the pre-processing data of the logistics process; Classify the logistics process preprocessing data according to the data tags to obtain transportation data and warehousing data; Call the preset tax calculation model and tax risk assessment model.

4. The intelligent logistics tax management method according to claim 1 is characterized in that: The matching of the tax types corresponding to the transportation data and the warehousing data, and performing tax audit calculation according to the tax types using the tax calculation model to obtain tax calculation results include: Matching the tax types corresponding to the transportation data and the storage data, respectively, wherein the tax types include the transportation tax corresponding to the transportation data and the storage tax corresponding to the storage data; Based on a weighted average algorithm, the tax calculation model is used to perform a tax audit calculation on the transportation tax to obtain a first calculation result; Based on a linear regression algorithm, the tax calculation model is used to perform a tax audit calculation on the storage tax to obtain a second calculation result; The first calculation result and the second calculation result are integrated to obtain a tax calculation result.

5. The intelligent logistics tax management method according to claim 1 is characterized in that: The using of the tax risk assessment model to perform risk warning analysis according to the tax calculation result to obtain a risk warning analysis result, and determining whether the risk warning analysis result exceeds a preset warning threshold, includes: Divide tax risk assessment issues into multiple levels and compare the relative importance of various factors in the same level; A judgment matrix is ​​established according to the relative importance, and the maximum eigenvalue and the corresponding eigenvector of the judgment matrix are solved based on the hierarchical analysis method to obtain the weight of each risk indicator; Using the tax risk assessment model to perform risk warning analysis according to the weights and the tax calculation results, to obtain risk warning analysis results; Identify the comprehensive risk score of the risk warning analysis result; Determine whether the comprehensive risk score exceeds a preset warning threshold.

6. The intelligent logistics tax management method according to claim 1 is characterized in that: If so, generating risk warning information according to the risk warning analysis result, and sending the risk warning information to the management terminal, including: If yes, then generating risk warning information according to the risk warning analysis result; Acquire processing suggestion solution information having a mapping relationship with the risk warning information from a preset risk processing solution library; Merging the risk warning information and the treatment suggestion information to obtain merged information; The merge information is sent to the management terminal.

7. The intelligent logistics tax management method according to claim 1 is characterized in that: If so, generating risk warning information according to the risk warning analysis result, and sending the risk warning information to the management terminal, further comprising: Encrypting the risk warning information to obtain encrypted information, and uploading the encrypted information to the blockchain; Create a listener, and use the listener to monitor real-time tax policy information; When the listener listens to the real-time tax policy information, the current real-time tax policy information is obtained; The tax rate range of the corresponding taxes in the tax calculation model is dynamically adjusted according to the real-time tax policy information.

8. A logistics tax intelligent management device, characterized in that: include: The collection and processing module is used to collect logistics process data, pre-process the logistics process data, and obtain logistics process pre-processed data; A classification calling module is used to classify the pre-processed data of the logistics process, obtain transportation data and warehousing data, and call a preset tax calculation model and tax risk assessment model; A matching calculation module, used for matching the tax types corresponding to the transportation data and the warehousing data, and performing tax audit calculation according to the tax types using the tax calculation model to obtain a tax calculation result; An analysis and judgment module, used to use the tax risk assessment model to perform risk warning analysis based on the tax calculation results, obtain risk warning analysis results, and judge whether the risk warning analysis results exceed a preset warning threshold; A generating and sending module is used to generate risk warning information according to the risk warning analysis result and send the risk warning information to the management terminal.

9. A logistics tax intelligent management device, characterized in that: The logistics tax intelligent management device comprises: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors calls the instructions in the memory so that the logistics tax intelligent management device executes each step of the logistics tax intelligent management method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the logistics tax intelligent management method as described in any one of claims 1-7 are implemented.

Images