CN106934705A - A kind of special ticket doubtful point taxpayer's monitoring method of value-added tax based on SVMs - Google Patents
A kind of special ticket doubtful point taxpayer's monitoring method of value-added tax based on SVMs Download PDFInfo
- Publication number
- CN106934705A CN106934705A CN201511001568.6A CN201511001568A CN106934705A CN 106934705 A CN106934705 A CN 106934705A CN 201511001568 A CN201511001568 A CN 201511001568A CN 106934705 A CN106934705 A CN 106934705A
- Authority
- CN
- China
- Prior art keywords
- item
- taxpayer
- information
- subunit
- vector machine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 61
- 238000012544 monitoring process Methods 0.000 title claims abstract description 32
- 238000012216 screening Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 4
- 230000029305 taxis Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/10—Tax strategies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24553—Query execution of query operations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of special ticket doubtful point taxpayer monitoring method of value-added tax based on SVMs and system, methods described is set up learning process table, supporting vector machine model is set up by study according to available data and relevant criterion；The Item Information in tables of data to be measured is processed using the supporting vector machine model set up then, the article is classified, classification effectiveness and quality are improved by the foundation and use of supporting vector machine model.Sorted Item Information is compared again, so as to analyze doubtful point taxpayer, effective monitoring and the illegal enterprise's tax evasion of analysis, guarantee tax income, improves the operating efficiency of the aspects such as tax authority's tax payment evaluation, Tax Check；Meanwhile, the risk for issuing invoice lack of standardization is reduced, promote the legacy specification operation of enterprise, effectively contain that illegal enterprise writes false value added tax invoice, obtains the behaviors such as income of not making out an invoice, reduce the generation of enterprise's tax evasion phenomenon.
Description
Technical Field
The invention belongs to the technical field of tax monitoring, and particularly relates to a method for monitoring suspected taxpayers of value-added tax special tickets based on a support vector machine.
Background
The popularization and the use of the value-added tax anti-counterfeiting tax control system greatly increase the national tax and become one of the powerful means for state tax collection and management, but enterprises still use the defects of the existing means for collecting and managing the tax to engage in illegal operation activities. In the process of value-added tax collection, the staff of the tax bureau reflects the condition that the goods and the money of the value-added tax entry invoice and the value-added tax sale invoice of the business enterprises do not correspond frequently. However, the amount of tax data associated with an invoice is very large, and it is not easy to find out noncompliance with the invoice.
In the prior art, whether the enterprises have illegal operation or not is judged by detecting the number one and multiple names of the value-added tax invoices. The Chinese patent with application number 201310547638.2 and application name 'a method and a system for detecting the first number and the multiple names of value-added tax invoices', discloses a method and a system for detecting the first number and the multiple names of the value-added tax invoices, wherein the system comprises: preparing data, performing data query, and taking out entry invoice data which is not processed by one number and multiple names one by one in the entry invoice data; building a special character dictionary table; taking taxpayer identification numbers and enterprise Chinese names of sellers enterprises; acquiring the enterprise Chinese name registered in the tax authority according to the taxpayer identification number; calculating the similarity between the enterprise Chinese name of the taxpayer and the registered enterprise Chinese name; and performing one-number multi-name judgment. The method of the invention can detect the doubtful points of one number and multiple names of the value-added tax invoice, namely: when the enterprises issue the value-added tax invoices, if the enterprises with one seller tax number corresponding to a plurality of seller names are listed as one number and a plurality of suspicious points, the enterprise is tracked and monitored whether to take invoices for a generation or not and to issue invoices falsely, reference is provided for tax authorities, and illegal operation of the enterprises is avoided.
However, the above monitoring of the enterprise judges whether the enterprise is one number with multiple names only by calculating the similarity between the Chinese name of the taxpayer enterprise and the Chinese name of the registered enterprise, and cannot monitor the concrete sale and sale conditions of the enterprise.
Disclosure of Invention
The embodiment of the invention aims to provide a method for monitoring suspected taxpayers of value-added tax special tickets based on a support vector machine, which screens and monitors suspected taxpayers through the dimensionality of the value-added tax special ticket articles and the amount of money, realizes the classification work of article names by using the algorithm of the support vector machine, improves the recognition rate of words, strengthens the risk management of value-added tax, strengthens the monitoring of tax sources, and inhibits lawbreakers from evading tax by using the technical bottleneck of the current tax management.
According to one aspect of the invention, a method for monitoring a value-added tax special bill suspected taxpayer based on a support vector machine is provided, and the method comprises the following steps:
establishing a support vector machine model;
inquiring first article information and taxpayer identification numbers of the value-added tax special ticket entry and sale items of the data table to be detected;
classifying the articles according to the first article information by using a support vector machine model, and establishing a classification result table;
inquiring first article information corresponding to a certain taxpayer identification number to be detected from the classification result table, and comparing the article information in the entry with the article information in the sales item;
and when the first article information in the entering item is inconsistent with the first article information in the selling item, judging that the taxpayer corresponding to the taxpayer identification number is a doubtful taxpayer.
In the foregoing solution, the establishing a support vector machine model includes:
executing SQL sentences, and extracting second item information from the value-added tax special ticket entry and sale table;
summarizing the extracted second article information, screening and discarding repeated data and invalid data, and keeping valid data;
establishing a learning process table according to the effective data and the national industry classification standard;
and learning the data in the learning process table by using a support vector machine, thereby establishing a support vector machine model.
In the above scheme, the first item information includes one or more of an item name, an item quantity, and an item amount.
In the above scheme, the second item information includes one or more of an item name, an item type, an item quantity, and an item amount.
In the above scheme, the establishing of the classification result table may further include inserting an article type column into a data table to be tested, classifying the article by the support vector machine model according to the first article information to obtain a classification result, and adding the classification result to a corresponding column of the article type to obtain the classification result table.
According to another aspect of the invention, there is also provided a value-added tax special bill doubtful point taxpayer monitoring system based on a support vector machine, the system comprising: the system comprises a model establishing unit, an information query unit to be tested, a classification unit and a comparison and judgment unit; wherein,
the model establishing unit is used for establishing a support vector machine model;
the information query unit to be tested is used for querying the first item information and the taxpayer identification number of the value-added tax special ticket entry and sale items of the data table to be tested;
the classification unit is connected with the model establishing unit and the information query unit to be tested at the same time, and is used for classifying the articles according to the first article information by using a support vector machine model and establishing a classification result table;
the comparing and judging unit is connected with the classifying unit and is used for inquiring first article information corresponding to a certain taxpayer identification number to be detected from the classifying result table and comparing the article information in the entry with the article information in the sales item; and is also used for: and when the first article information in the entering item is inconsistent with the first article information in the selling item, judging that the taxpayer corresponding to the taxpayer identification number is a doubtful taxpayer.
In the foregoing solution, the model establishing unit includes: the system comprises an information extraction subunit, an information summarization subunit, a learning process table establishing subunit and a learning subunit; wherein,
the information extraction subunit is used for executing SQL sentences and extracting second item information from the value-added tax special ticket entry and sale table;
the information gathering subunit is connected with the information extracting subunit and is used for gathering the extracted second article information, screening and discarding repeated data and invalid data, and keeping valid data;
the learning process table establishing subunit is used for establishing a learning process table according to the effective data and the national industry classification standard;
the learning subunit is connected with the learning process table establishing subunit and is used for learning the data in the learning process table by using a support vector machine so as to establish a support vector machine model.
In the foregoing solution, the classification unit includes: a column-adding subunit for executing the classification subunit and adding the result subunit; wherein,
the column adding subunit is used for inserting an article type column into the data table to be tested;
the classification execution subunit is used for supporting a vector machine model to classify the articles according to the first article information to obtain a classification result;
and the addition result subunit is connected with the column adding subunit and the execution classification subunit simultaneously and is used for adding the classification result into the corresponding column of the article type so as to obtain a classification result table.
In the above scheme, the first item information includes one or more of an item name, an item quantity, and an item amount.
In the above scheme, the second item information includes one or more of an item name, an item type, an item quantity, and an item amount.
According to the technical scheme, the method and the system for monitoring the value-added tax special ticket suspicious taxpayer based on the support vector machine, which are disclosed by the embodiment of the invention, establish the learning process table according to the existing data and relevant standards, establish the support vector machine model through the supervised learning algorithm, and fully utilize the remarkable advantages of small sample nonlinearity and high-dimensional pattern recognition. The established support vector machine model is utilized to process the article information in the data table to be detected, the articles are classified, and the classification efficiency and quality are improved through establishment and use of the support vector machine model. The classified article information is compared, so that doubtful taxpayers are analyzed, illegal enterprises can be effectively monitored and analyzed to evade taxes, tax income is guaranteed, and the working efficiency of tax authorities in tax payment evaluation, tax inspection and the like is improved; meanwhile, the risk of issuing invoices in an irregular way is reduced, the legal and regular operation of enterprises is promoted, the behaviors of falsely issuing value-added tax invoices, obtaining invoiced income and the like of illegal enterprises are effectively restrained, and the phenomenon that the enterprises steal taxes is greatly reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1 is a schematic flow chart of a value-added tax special invoice suspicious point taxpayer monitoring method based on a support vector machine model according to a first embodiment of the present invention;
FIG. 2 is a schematic flow chart of the process of establishing a support vector machine model shown in FIG. 1;
fig. 3 is a schematic structural diagram of a support vector machine-based value-added tax special ticket suspicious node taxpayer monitoring system according to a second embodiment of the present invention.
Detailed Description
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The embodiments of the present invention will be described in detail below to facilitate understanding of the embodiments of the present invention, and the embodiments described by referring to the drawings are exemplary only for the purpose of explaining the present invention and are not to be construed as limiting the present invention.
Fig. 1 is a schematic flow chart of a value-added tax special ticket suspicious node taxpayer monitoring method based on a support vector machine model according to a first embodiment of the present invention. As shown in fig. 1, the method for monitoring a value-added tax special ticket suspicious spot taxpayer based on a support vector machine model in the embodiment includes the following steps:
step S101, a support vector machine model is established.
Preferably, the establishing of the support vector machine model may specifically include the following steps, as shown in fig. 2:
in step S1011, the SQL statement is executed to extract the second item information from the value-added tax special bill entry and sale table.
Step S1012, summarizing the extracted second item information, screening and discarding duplicate data and invalid data, and retaining valid data;
and S1013, establishing a learning process table according to the effective data and the national industry classification standard.
In the sub-step, the form data screening process of the learning process is established to keep the number of training samples as small as possible, excessive samples are not added under the condition of covering basic samples, and the screening process removes a large amount of repeated data and invalid data, effectively prevents the occurrence of information repetition, thereby covering relatively few samples and forming an overfitting phenomenon. The learning process table is created by typical data samples given by the national industry classification table and/or the tax administration, and the main fields are item unit, item name, item unit price and item category.
And step S1014, learning the data in the learning process table by using a support vector machine, thereby establishing a support vector machine model.
The method for monitoring the suspicious tax payer of the value-added tax special bill further comprises the following steps:
and S102, inquiring the first item information and the taxpayer identification number of the value-added tax special ticket entry and the sales item of the data table to be detected. Preferably, the first item information includes one or more of an item name, an item quantity, and an item amount.
And S103, classifying the articles according to the first article information by using a support vector machine model, and establishing a classification result table. Preferably, the second item information includes one or more of an item name, an item type, an item quantity, and an item amount.
In the step S101, a support vector machine of a supervised learning algorithm is used, which has significant advantages for the problem of small sample nonlinearity and high-dimensional pattern recognition. In the process of classifying the value-added tax special ticket articles related to the embodiment, the screening accuracy and the screening efficiency are obviously improved through the support vector machine, and the articles are easily classified wrongly by the traditional manual classification method.
In the step of establishing the classification result table, an article type column may be inserted into the data table to be tested, the support vector machine model classifies the articles according to the first article information to obtain a classification result, and the classification result is added to a corresponding column of the article type to obtain the classification result table.
And step S104, inquiring first article information corresponding to a certain taxpayer identification number to be detected from the classification result table, and comparing the article information in the input item with the article information in the sales item.
Step S105, judging whether the first article information in the entry is consistent with the first article information in the sales item, and if not, executing step S106; and when the two are consistent, ending the monitoring.
And step S106, judging the taxpayer corresponding to the taxpayer identification number as the doubtful point taxpayer.
For example, in steps 104 to 106, the commodity and amount information of the entry invoice and the sale invoice collected by the commercial enterprises in the process of processing tax copying and authentication is used to compare the article names of the entry and the sale of the same commercial enterprise, analyze whether the same commodity belongs to the same class of articles, and then compare whether the amount of the commodity is normal, so as to determine whether the commodity is a suspicious taxpayer who wrongly issues an invoice.
According to the method for monitoring the value-added tax special ticket suspicious tax payer based on the support vector machine, the learning process table is established according to the existing data and standards, the support vector machine model is established through the supervised learning algorithm, and the remarkable advantages of small sample nonlinearity and high-dimensional mode recognition are fully utilized. The established support vector machine model is utilized to process the article information in the data table to be detected, the articles are classified, and the classification efficiency and quality are improved through establishment and use of the support vector machine model. The classified article information is compared, so that doubtful taxpayers are analyzed, illegal enterprises can be effectively monitored and analyzed to evade taxes, tax income is guaranteed, and the working efficiency of tax authorities in tax payment evaluation, tax inspection and the like is improved; meanwhile, the risk of issuing invoices in an irregular way is reduced, the legal and regular operation of enterprises is promoted, the behaviors of falsely issuing value-added tax invoices, obtaining invoiced income and the like of illegal enterprises are effectively restrained, and the phenomenon that the enterprises steal taxes is greatly reduced.
Fig. 3 is a schematic structural diagram of a support vector machine-based value-added tax special ticket suspicious node taxpayer monitoring system according to a second embodiment of the present invention.
As shown in fig. 3, the system for monitoring a value-added tax special ticket suspicious tax payer based on a support vector machine in this embodiment includes: the system comprises a model establishing unit 1, an information query unit 2 to be tested, a classification unit 3 and a comparison and judgment unit 4; wherein,
the model establishing unit 1 is used for establishing a support vector machine model;
the information query unit 2 to be tested is used for querying the first item information and the taxpayer identification number of the value-added tax special ticket entry and sale items of the data table to be tested;
the classification unit 3 is connected with the model establishing unit and the to-be-detected information query unit at the same time, and is used for classifying the articles according to the first article information by using a support vector machine model and establishing a classification result table;
the comparing and judging unit 4 is connected with the classifying unit and is used for inquiring first article information corresponding to a certain taxpayer identification number to be detected from the classifying result table and comparing the article information in the entering item with the article information in the selling item; and is also used for: and when the first article information in the entering item is inconsistent with the first article information in the selling item, judging that the taxpayer corresponding to the taxpayer identification number is a doubtful taxpayer.
Preferably, the model building unit 1 includes: an information extraction subunit 11, an information summarizing subunit 12, a learning process table establishing subunit 13, and a learning subunit 14; wherein,
the information extraction subunit 11 is configured to execute an SQL statement and extract second item information from the value-added tax special ticket entry and sale table;
the information summarizing sub-unit 12 is connected to the information extracting sub-unit, and is configured to summarize the extracted second item information, filter and discard duplicate data and invalid data, retain valid data,
the learning process table establishing subunit 13 is connected to the information summarizing subunit and is configured to establish a learning process table according to the valid data and the national industry classification standard;
the learning subunit 14 is connected to the learning process table establishing subunit, and is configured to use a support vector machine to learn data in the learning process table, so as to establish a support vector machine model.
The classification unit 3 includes: a column addition subunit 31 that executes a classification subunit 32 and adds a result subunit 33; wherein,
the column adding subunit 31 is configured to insert an article type column into the data table to be tested;
the classification execution subunit 32 is configured to support a vector machine model to classify the article according to the first article information to obtain a classification result;
the add result subunit 33 is connected to both the add column subunit and the execute classification subunit, and is configured to add the classification result to the corresponding column of the article type, so as to obtain a classification result table.
The value-added tax special ticket suspicious tax payer monitoring system based on the support vector machine of the embodiment establishes a learning process table according to the existing data and standards, establishes a support vector machine model through a supervised learning algorithm, and fully utilizes the remarkable advantages of small sample nonlinearity and high-dimensional mode identification. The established support vector machine model is utilized to process the article information in the data table to be detected, the articles are classified, and the classification efficiency and quality are improved through establishment and use of the support vector machine model. The classified article information is compared, so that doubtful taxpayers are analyzed, illegal enterprises can be effectively monitored and analyzed to evade taxes, tax income is guaranteed, and the working efficiency of tax authorities in tax payment evaluation, tax inspection and the like is improved; meanwhile, the risk of issuing invoices in an irregular way is reduced, the legal and regular operation of enterprises is promoted, the behaviors of falsely issuing value-added tax invoices, obtaining invoiced income and the like of illegal enterprises are effectively restrained, and the phenomenon that the enterprises steal taxes is greatly reduced.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for monitoring a value-added tax special ticket suspicious spot taxpayer based on a support vector machine is characterized by comprising the following steps:
establishing a support vector machine model;
inquiring first article information and taxpayer identification numbers of the value-added tax special ticket entry and sale items of the data table to be detected;
classifying the articles according to the first article information by using a support vector machine model, and establishing a classification result table;
inquiring first article information corresponding to a certain taxpayer identification number to be detected from the classification result table, and comparing the article information in the entry with the article information in the sales item;
and when the first article information in the entering item is inconsistent with the first article information in the selling item, judging that the taxpayer corresponding to the taxpayer identification number is a doubtful taxpayer.
2. The value-added tax special ticket suspects taxpayer monitoring method according to claim 1, wherein said establishing a support vector machine model comprises:
executing SQL sentences, and extracting second item information from the value-added tax special ticket entry and sale table;
summarizing the extracted second article information, screening and discarding repeated data and invalid data, and keeping valid data;
establishing a learning process table according to the effective data and the national industry classification standard;
and learning the data in the learning process table by using a support vector machine, thereby establishing a support vector machine model.
3. The value-added tax special ticket suspect taxpayer monitoring method according to claim 1 or 2, wherein said first item information includes one or more of an item name, an item quantity, and an item amount.
4. The value-added tax special ticket suspect taxpayer monitoring method of claim 2, wherein said second item information includes one or more of item name, item type, item quantity, item amount.
5. The method for monitoring the value-added tax special ticket suspicious tax payer according to claim 1 or 2, wherein the establishing of the classification result table is further characterized in that an item type column is inserted into the data table to be tested, a support vector machine model classifies the items according to the first item information to obtain a classification result, and the classification result is added to a corresponding column of the item type to obtain the classification result table.
6. A value-added tax special ticket suspect taxpayer monitoring system based on a support vector machine, the system comprising: the system comprises a model establishing unit, an information query unit to be tested, a classification unit and a comparison and judgment unit; wherein,
the model establishing unit is used for establishing a support vector machine model;
the information query unit to be tested is used for querying the first item information and the taxpayer identification number of the value-added tax special ticket entry and sale items of the data table to be tested;
the classification unit is connected with the model establishing unit and the information query unit to be tested at the same time, and is used for classifying the articles according to the first article information by using a support vector machine model and establishing a classification result table;
the comparing and judging unit is connected with the classifying unit and is used for inquiring first article information corresponding to a certain taxpayer identification number to be detected from the classifying result table and comparing the article information in the entry with the article information in the sales item; and is also used for: and when the first article information in the entering item is inconsistent with the first article information in the selling item, judging that the taxpayer corresponding to the taxpayer identification number is a doubtful taxpayer.
7. The suspected taxpayer monitoring system of claim 6, wherein the model building unit includes: the system comprises an information extraction subunit, an information summarization subunit, a learning process table establishing subunit and a learning subunit; wherein,
the information extraction subunit is used for executing SQL sentences and extracting second item information from the value-added tax special ticket entry and sale table;
the information gathering subunit is connected with the information extracting subunit and is used for gathering the extracted second article information, screening and discarding repeated data and invalid data, and keeping valid data;
the learning process table establishing subunit is used for establishing a learning process table according to the effective data and the national industry classification standard;
the learning subunit is connected with the learning process table establishing subunit and is used for learning the data in the learning process table by using a support vector machine so as to establish a support vector machine model.
8. The doubtful point taxpayer monitoring system according to claim 6 or 7, wherein the classification unit comprises: a column-adding subunit for executing the classification subunit and adding the result subunit; wherein,
the column adding subunit is used for inserting an article type column into the data table to be tested;
the classification execution subunit is used for supporting a vector machine model to classify the articles according to the first article information to obtain a classification result;
and the addition result subunit is connected with the column adding subunit and the execution classification subunit simultaneously and is used for adding the classification result into the corresponding column of the article type so as to obtain a classification result table.
9. The suspected taxpayer monitoring system of claim 6 or claim 7, wherein the first item information includes one or more of an item name, an item quantity, and an item amount.
10. The suspected taxpayer monitoring system of claim 7, wherein the second item information includes one or more of an item name, an item type, an item quantity, and an item amount.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511001568.6A CN106934705A (en) | 2015-12-28 | 2015-12-28 | A kind of special ticket doubtful point taxpayer's monitoring method of value-added tax based on SVMs |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511001568.6A CN106934705A (en) | 2015-12-28 | 2015-12-28 | A kind of special ticket doubtful point taxpayer's monitoring method of value-added tax based on SVMs |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106934705A true CN106934705A (en) | 2017-07-07 |
Family
ID=59458277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511001568.6A Pending CN106934705A (en) | 2015-12-28 | 2015-12-28 | A kind of special ticket doubtful point taxpayer's monitoring method of value-added tax based on SVMs |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106934705A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595621A (en) * | 2018-04-23 | 2018-09-28 | 泰华智慧产业集团股份有限公司 | A kind of early warning analysis method and system write false value added tax invoice |
| CN109426968A (en) * | 2017-08-22 | 2019-03-05 | 阿里巴巴集团控股有限公司 | Method for detecting abnormality, device and the method for detecting abnormality of enterprise of main body to be measured |
| CN109615153A (en) * | 2017-09-26 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Businessman's methods of risk assessment, device, equipment and storage medium |
| CN109636111A (en) * | 2018-11-09 | 2019-04-16 | 航天信息股份有限公司 | A kind of method and system of determining enterprise's income pin item diversity factor |
| CN109636036A (en) * | 2018-12-12 | 2019-04-16 | 税友软件集团股份有限公司 | A kind of method, system and the equipment of the prediction of enterprise's invoiced amount |
| CN109993644A (en) * | 2017-12-29 | 2019-07-09 | 航天信息股份有限公司 | A kind of portrait determines method, apparatus, electronic equipment and storage medium |
| CN110019324A (en) * | 2017-12-06 | 2019-07-16 | 航天信息股份有限公司 | A kind of method and system generating taxpayer's fund circuit |
| CN111241175A (en) * | 2019-12-30 | 2020-06-05 | 航天信息(山东)科技有限公司 | Method and system for monitoring product oil consumption tax data |
| CN112308638A (en) * | 2020-10-29 | 2021-02-02 | 北京中科闻歌科技股份有限公司 | False invoice behavior detection method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424595A (en) * | 2013-09-04 | 2015-03-18 | 航天信息股份有限公司 | Tax administration monitoring method and tax administration monitoring system thereof |
| CN104463649A (en) * | 2015-01-07 | 2015-03-25 | 税友软件集团股份有限公司 | Invoice recording method and system |
| CN104636970A (en) * | 2013-11-06 | 2015-05-20 | 航天信息股份有限公司 | Method of monitoring enterprise tax evasion through commodity differences and system thereof |
-
2015
- 2015-12-28 CN CN201511001568.6A patent/CN106934705A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424595A (en) * | 2013-09-04 | 2015-03-18 | 航天信息股份有限公司 | Tax administration monitoring method and tax administration monitoring system thereof |
| CN104636970A (en) * | 2013-11-06 | 2015-05-20 | 航天信息股份有限公司 | Method of monitoring enterprise tax evasion through commodity differences and system thereof |
| CN104463649A (en) * | 2015-01-07 | 2015-03-25 | 税友软件集团股份有限公司 | Invoice recording method and system |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109426968A (en) * | 2017-08-22 | 2019-03-05 | 阿里巴巴集团控股有限公司 | Method for detecting abnormality, device and the method for detecting abnormality of enterprise of main body to be measured |
| CN109426968B (en) * | 2017-08-22 | 2022-08-30 | 阿里巴巴集团控股有限公司 | Abnormity detection method and device for main body to be detected and enterprise abnormity detection method |
| CN109615153A (en) * | 2017-09-26 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Businessman's methods of risk assessment, device, equipment and storage medium |
| CN109615153B (en) * | 2017-09-26 | 2023-06-16 | 阿里巴巴集团控股有限公司 | Merchant risk assessment method, device, equipment and storage medium |
| CN110019324B (en) * | 2017-12-06 | 2021-05-14 | 航天信息股份有限公司 | Method and system for generating taxpayer fund loop |
| CN110019324A (en) * | 2017-12-06 | 2019-07-16 | 航天信息股份有限公司 | A kind of method and system generating taxpayer's fund circuit |
| CN109993644A (en) * | 2017-12-29 | 2019-07-09 | 航天信息股份有限公司 | A kind of portrait determines method, apparatus, electronic equipment and storage medium |
| CN108595621A (en) * | 2018-04-23 | 2018-09-28 | 泰华智慧产业集团股份有限公司 | A kind of early warning analysis method and system write false value added tax invoice |
| CN108595621B (en) * | 2018-04-23 | 2020-10-30 | 泰华智慧产业集团股份有限公司 | Early warning analysis method and system for false value-added tax invoice |
| CN109636111A (en) * | 2018-11-09 | 2019-04-16 | 航天信息股份有限公司 | A kind of method and system of determining enterprise's income pin item diversity factor |
| CN109636111B (en) * | 2018-11-09 | 2023-04-18 | 航天信息股份有限公司 | Method and system for determining business entry and sale item difference degree |
| CN109636036B (en) * | 2018-12-12 | 2021-03-26 | 亿企赢网络科技有限公司 | Method, system and equipment for enterprise invoice quantity prediction |
| CN109636036A (en) * | 2018-12-12 | 2019-04-16 | 税友软件集团股份有限公司 | A kind of method, system and the equipment of the prediction of enterprise's invoiced amount |
| CN111241175A (en) * | 2019-12-30 | 2020-06-05 | 航天信息(山东)科技有限公司 | Method and system for monitoring product oil consumption tax data |
| CN112308638A (en) * | 2020-10-29 | 2021-02-02 | 北京中科闻歌科技股份有限公司 | False invoice behavior detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106934705A (en) | A kind of special ticket doubtful point taxpayer's monitoring method of value-added tax based on SVMs | |
| US10482093B2 (en) | Data mining method | |
| CN102592067B (en) | Webpage recognition method, device and system | |
| CN104899508B (en) | A kind of multistage detection method for phishing site and system | |
| CN105701905A (en) | Invoice recognition method and system | |
| US20150169745A1 (en) | Document Sorting System, Document Sorting Method, and Document Sorting Program | |
| CN104123370A (en) | Method and system for detecting sensitive information in database | |
| CN103544436A (en) | System and method for distinguishing phishing websites | |
| CN107016298B (en) | Webpage tampering monitoring method and device | |
| CN112001586A (en) | Enterprise networking big data audit risk control architecture based on block chain consensus mechanism | |
| CN104408635A (en) | Method and device for recognizing class information of commercial tenant | |
| CN111598753A (en) | Suspect recommendation method and device, electronic equipment and storage medium | |
| CN113360566A (en) | Information content monitoring method and system | |
| CN107358519A (en) | Invoice monitoring method and system | |
| CN114692593A (en) | Network information safety monitoring and early warning method | |
| CN104636971A (en) | Method of detecting one number for multiple names of value added tax invoice and system thereof | |
| CN113989859B (en) | Fingerprint similarity identification method and device for anti-flashing equipment | |
| Soni et al. | Reducing risk in KYC (know your customer) for large Indian banks using big data analytics | |
| CN111651768A (en) | Method and device for identifying link library function name of computer binary program | |
| CN105989093A (en) | Automatic discovery method, device and application of sensitive word | |
| KR102512982B1 (en) | Insurance fraud detection system | |
| CN109409091B (en) | Method, device and equipment for detecting Web page and computer storage medium | |
| US20200242121A1 (en) | Method and apparatus for analyzing data | |
| CN110543910A (en) | Credit state monitoring system and monitoring method | |
| CN106156046A (en) | A kind of informatization management method, device, system and analytical equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170707 |
|
| RJ01 | Rejection of invention patent application after publication |