CN115909586A - Method and system for checking the authenticity of value-added tax invoices based on intelligent process robots - Google Patents

Abstract

The invention provides a method and a system for checking the authenticity of a value-added tax invoice based on an intelligent process robot, wherein the method comprises the following steps: step S1: the invoice information to be checked is sent to a robot management server, and the robot management server starts an intelligent process robot to automatically recognize the invoice information to obtain invoice authenticity information and invoice surface information; step S2: and logging in a value-added tax invoice inspection platform of the national tax administration by using the intelligent process robot to perform invoice-adding inspection and perform image filing. The invention utilizes the characteristic that the process robot can replace manual work to carry out mechanized operation and the capability that the optical character recognition technology can recognize key information from the image file, realizes the automation of the business process of the authenticity check of the value-added tax invoice, has the characteristics of uninterrupted work, exception handling, check and recheck and the like, and can greatly improve the working efficiency and the accuracy.

Description

Method and system for checking the authenticity of value-added tax invoices based on intelligent process robots

technical field

The invention relates to the technical field of invoice management, in particular to a method and system for checking the authenticity of value-added tax invoices based on an intelligent process robot.

Background technique

With its high liquidity and stable income, the bill business has become the main channel for enterprises to solve the shortage of funds, and it is also an important driving force for the profit growth of various financial institutions. Due to its important position in the financial industry, the banking industry needs to check the authenticity of value-added tax invoices in its own business processes such as lending. Because the bank bill business volume is huge and most of them are electronic images in the form of photographing and scanning, how to quickly and accurately The authenticity inspection of large quantities of invoices has become a major pain point in the invoice business.

Patent document CN111105548B (application number: 201911284182.9) discloses a batch inspection device and method for special value-added tax invoices, which belongs to the technical field of invoice management, and solves the problems of low inspection efficiency and high error rate of existing equipment. Including: an invoice storage unit, an invoice scanning unit, an invoice information confirmation unit, and an invoice verification unit; the invoice verification unit is used to receive the invoice information output by the invoice scanning unit and/or the invoice information confirmation unit, and call the invoice pool or tax The corresponding information of the system is checked for authenticity by comparison, and the result of the authenticity check is obtained and recorded.

Contents of the invention

In view of the deficiencies in the prior art, the object of the present invention is to provide a method and system for checking the authenticity of value-added tax invoices based on intelligent process robots.

A method for checking the authenticity of value-added tax invoices based on an intelligent process robot according to the present invention includes:

Step S1: Send the invoice information to be checked to the robot management server, and the robot management server starts the intelligent process robot to automatically identify the invoice information, obtain the authenticity information of the invoice and the face information of the invoice;

Step S2: Use the intelligent process robot to log in to the VAT invoice inspection platform of the State Administration of Taxation to check the added invoice and record the image.

Preferably, the intelligent process robot reads computer configuration information, including: computer operating system time, computer operating environment, and computer hard disk file directory; read through the computer operating environment and computer hard disk file directory to ensure that the intelligent process robot can run normally; Read the computer operating system time to ensure the safe operation of intelligent process robots.

Preferably, the step S1 adopts:

Step S1.1: Send the invoice information to be inspected to the robot management server, the robot management server starts the intelligent process robot, and the intelligent process robot obtains a list of task numbers to be inspected from the robot management server;

Step S1.2: The intelligent process robot obtains the corresponding value-added tax invoice information from the robot management server according to the task number, and judges that the current value-added tax invoice information is the value-added tax invoice image or the four-element text of the invoice;

Step S1.3: When the current value-added tax invoice information is a value-added tax invoice image, use optical character recognition technology to obtain the four-element text of the invoice;

Step S1.4: The intelligent process robot queries whether the current value-added tax invoice information is true through the four-element text of the invoice, and obtains the face information of the invoice when the invoice information is true.

Preferably, the invoice face information includes: invoice number on the face, invoice code, invoice date, verification code, tax-exclusive amount, tax amount, tax-included amount, machine code, invoice status, historical inspection times, account opening by the seller Bank information, bank account number of the seller, address of the seller, phone number of the seller, name of the seller, tax number of the seller, information of the bank of the buyer, account number of the buyer’s bank, address of the buyer, phone number of the buyer, name of the buyer, and Tax ID information of the buyer.

Preferably, the step S2 adopts:

Step S2.1: The intelligent process robot automatically logs in and visits the VAT invoice inspection platform of the State Administration of Taxation. Based on the obtained invoice face information, the intelligent process robot simulates the manual and automatically fills in the corresponding content in the corresponding check box on the webpage for inspection, and obtains the inspection of the current invoice information Result and perform a screenshot operation to obtain the image;

Step S2.2: The intelligent process robot sends the obtained invoice details and inspection result images to the data management server for storage.

Preferably, the step S2.1 adopts:

Step S2.1.1: The intelligent process robot visits the homepage of the VAT invoice inspection platform of the State Administration of Taxation, and the process robot automatically fills in the invoice code and invoice number in the corresponding check boxes in sequence. After the invoice code and invoice number are successfully entered, the pop-up calendar will be displayed. Simulate manual selection of the invoice date of the value-added tax invoice. If: the invoice type of the invoice is identified as general invoice, the process robot will fill in the verification of the invoice in the last item popped up on the value-added tax invoice inspection platform of the State Administration of Taxation code, if the invoice type of the invoice is identified as a special invoice, the tax-exclusive amount will be filled in;

Step S2.1.2: After the process robot clicks the check button, it uses AI technology to intelligently identify the invoice information. The invoice status obtained by the query is genuine, voided invoice, non-existent invoice, and inconsistent invoice information. The state of the system is treated differently;

Step S2.1.3: If the status of the invoice recognized by the process robot is genuine, the process robot obtains the information fed back by the VAT invoice inspection platform of the State Administration of Taxation, and automatically converts the information into a PDF image and saves it. If there are too many types, the product type, quantity, tax amount and other information will be automatically listed in a separate sheet for viewing, and the specific information on the ticket will be saved separately in a single page that can be easily viewed;

Step S2.1.4: If the status of the invoice identified by the process robot is voided, the process robot takes the information fed back from the VAT invoice inspection platform of the State Administration of Taxation, and automatically converts the information into a PDF image and prints the word "voided" on the invoice image and save;

Step S2.1.5: If the status of the invoice recognized by the process robot is that the invoice does not exist, the process robot will combine the information of the four elements of the invoice to generate a feedback image and directly print a message that the invoice does not exist on the image;

Step S2.1.6: If the status of the invoice identified by the process robot is that the invoice information is inconsistent, the process robot will combine the information of the four elements of the invoice to generate a feedback image and directly print out a message that the invoice information is inconsistent on the image.

A value-added tax invoice authenticity inspection system based on an intelligent process robot provided according to the present invention includes:

Module M1: Send the invoice information to be checked to the robot management server, and the robot management server starts the intelligent process robot to automatically identify the invoice information, obtain the authenticity information of the invoice and the face information of the invoice;

Module M2: Use the intelligent process robot to log in to the VAT invoice inspection platform of the State Administration of Taxation to perform invoice increment inspection and image retention.

Preferably, the module M1 adopts:

Module M1.1: Send the invoice information to be inspected to the robot management server, the robot management server starts the intelligent process robot, and the intelligent process robot obtains the list of task numbers to be inspected from the robot management server;

Module M1.2: The intelligent process robot obtains the corresponding value-added tax invoice information from the robot management server according to the task number, and judges that the current value-added tax invoice information is the value-added tax invoice image or the four-element text of the invoice;

Module M1.3: When the current value-added tax invoice information is a value-added tax invoice image, use optical character recognition technology to obtain the four-element invoice text of the image;

Module M1.4: The intelligent process robot queries whether the current value-added tax invoice information is true through the four-element text of the invoice, and obtains the face information of the invoice when the invoice information is true.

Preferably, the invoice face information includes: invoice number on the face, invoice code, invoice date, verification code, tax-exclusive amount, tax amount, tax-included amount, machine code, invoice status, historical inspection times, account opening by the seller Bank information, bank account number of the seller, address of the seller, phone number of the seller, name of the seller, tax number of the seller, information of the bank of the buyer, account number of the buyer’s bank, address of the buyer, phone number of the buyer, name of the buyer, and Tax ID information of the buyer.

Preferably, the module M2 adopts:

Module M2.1: The intelligent process robot automatically logs in to access the VAT invoice inspection platform of the State Administration of Taxation. The intelligent process robot simulates the manual and automatically fills in the corresponding content in the corresponding check box on the web page based on the obtained invoice face information to obtain the current invoice information inspection. Result and perform a screenshot operation to obtain the image;

Module M2.2: The intelligent process robot sends the obtained invoice details and inspection result images to the data management server for storage.

Preferably, the module M2.1 adopts:

Module M2.1.1: The intelligent process robot visits the homepage of the VAT invoice inspection platform of the State Administration of Taxation, and the process robot automatically fills in the invoice code and invoice number in the corresponding check boxes in turn. After the invoice code and invoice number are successfully entered, they will be displayed in the pop-up calendar Simulate manual selection of the invoice date of the value-added tax invoice. If: the invoice type of the invoice is identified as general invoice, the process robot will fill in the verification of the invoice in the last item popped up on the value-added tax invoice inspection platform of the State Administration of Taxation code, if the invoice type of the invoice is identified as a special invoice, the tax-exclusive amount will be filled in;

Module M2.1.2: After the process robot clicks the inspection button, it uses AI technology to intelligently identify the invoice information. The invoice status obtained by querying is genuine, voided invoice, non-existent invoice, and inconsistent invoice information. The state of the system is treated differently;

Module M2.1.3: If the status of the invoice recognized by the process robot is genuine, the process robot obtains the information fed back by the VAT invoice inspection platform of the State Administration of Taxation, and automatically converts the information into a PDF image and saves it. If there are too many types, the product type, quantity, tax amount and other information will be automatically listed in a separate sheet for viewing, and the specific information on the ticket will be saved separately in a single page that can be easily viewed;

Module M2.1.4: If the status of the invoice identified by the process robot is voided, the process robot takes the information fed back from the VAT invoice inspection platform of the State Administration of Taxation, and automatically converts the information into a PDF image and prints the word "voided" on the invoice image and save;

Module M2.1.5: If the status of the invoice recognized by the process robot is that the invoice does not exist, the process robot will combine the information of the four elements of the invoice to generate a feedback image and directly print a message that the invoice does not exist on the image;

Module M2.1.6: If the status of the invoice recognized by the process robot is that the invoice information is inconsistent, the process robot will combine the information of the four elements of the invoice to generate a feedback image and directly print out a message that the invoice information is inconsistent on the image.

Compared with the prior art, the present invention has the following beneficial effects: the present invention utilizes the feature that process robots can replace manual mechanized operations and the ability of optical character recognition technology to identify key information from image files, and realizes the authenticity of value-added tax invoices. The business process automation of false inspection has the characteristics of uninterrupted work, exception handling, verification review, etc., which can greatly improve work efficiency and accuracy.

Description of drawings

Other characteristics, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

Fig. 1 is a flow chart of a method for checking the authenticity of value-added tax invoices based on an intelligent process robot.

Detailed ways

The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

Example 1

The present invention provides a method and system for checking the authenticity of value-added tax invoices based on an intelligent process robot, which utilizes the characteristics that process robots can replace manual mechanized operations and the ability of optical character recognition technology to identify key information from image files to achieve The business process automation of the authenticity inspection of value-added tax invoices has the characteristics of uninterrupted work, exception handling, verification and review, etc., which can greatly improve work efficiency and accuracy: business personnel can interact with the desktop software and send the invoice information to be inspected to the robot management Server, the server will automatically start the intelligent process robot program, which will automatically perform optical character recognition on the obtained invoice information, obtain the authenticity information of the invoice, obtain the face information of the invoice, and log in to the value-added tax invoice inspection platform of the State Administration of Taxation for additional invoice inspection And carry out image retention.

A method for checking the authenticity of a value-added tax invoice based on an intelligent process robot provided according to the present invention, as shown in Figure 1, includes:

Step 1: Start the main program of the process robot and initialize the parameters;

Step 2: The process robot reads relevant configurations, such as system time, operating environment, file directory, etc., and obtains a list of task numbers to be checked from the robot management server queue;

Step 3: The process robot judges whether the list of task numbers to be checked has been processed. If not, execute step 4. If all processing is completed, execute step 10;

Step 4: the process robot uses the task number to obtain the relevant data of the value-added tax invoice from the database of the data management server;

Step 5: The process robot judges that the value-added tax invoice information obtained is a value-added tax invoice image or an invoice four-element text, if it is a value-added tax invoice image, then perform step 6, and if it is an invoice four-element text, then perform step 7;

Step 6: The process robot uses optical character recognition technology to obtain the four-element text of the invoice in the image of the value-added tax invoice;

Step 7: The process robot queries whether the value-added tax invoice information is true through the four-element text of the invoice. If the invoice is true, it will obtain the invoice number, invoice code, invoice date, check code, tax-exclusive amount, tax amount, and Tax amount, machine code, invoice status, historical inspection times, seller’s bank information, seller’s account number, seller’s address, seller’s phone number, seller’s name, seller’s tax ID, buyer’s bank information, buyer’s Bank account number, buyer's address, buyer's phone number, buyer's name, buyer's tax ID, etc.;

Step 8: The process robot automatically logs in and visits the VAT invoice inspection platform of the State Administration of Taxation. The robot simulates manually filling in the four elements of the invoice in the webpage selection box and inspecting it, obtaining the inspection result of the invoice information and taking a screenshot to obtain the image;

Step 9: The process robot sends the invoice details obtained in step 7 and the VAT invoice inspection platform certificate of the State Administration of Taxation obtained in step 8 to the data management server for storage;

Step 10: The data management server sends back the verification result to the demand initiator and informs the business department that the verification of the VAT invoice has been completed;

Described step 8 comprises the following steps:

Step 8.1: The process robot visits the homepage of the VAT invoice inspection platform of the State Administration of Taxation, and the process robot automatically fills in the invoice code and invoice number in the corresponding check boxes in sequence. After the invoice code and invoice number are successfully entered, the manual point is simulated in the pop-up calendar Select the invoice date of the value-added tax invoice. If the invoice type of the invoice is recognized as a general invoice in step 5, the process robot will fill in the verification code of the invoice in the last item popped up on the value-added tax invoice inspection platform of the State Administration of Taxation , if the invoice type of the invoice identified in step 5 is a special invoice, the amount excluding tax will be filled in;

Step 8.2: After the process robot clicks the check button, it uses AI technology to intelligently identify the invoice status of the invoice. The status of the invoice obtained from the query is genuine, voided invoice, non-existent invoice, and inconsistent invoice information, and according to these four different statuses be treated differently;

Step 8.3: If the status of the invoice recognized by the process robot is genuine, the process robot obtains the information fed back by the VAT invoice inspection platform of the State Administration of Taxation, and automatically converts the information into a PDF image and saves it. If there are many, the information such as commodity type, quantity, tax amount, etc. will be automatically listed separately and saved for viewing, and the specific information on the ticket will be saved separately in a single page that can be easily viewed;

Step 8.4: If the status of the invoice recognized by the process robot is voided, the process robot will take the information fed back from the VAT invoice inspection platform of the State Administration of Taxation, and will automatically convert the information into a PDF image and print the word "voided" on the invoice image and save;

Step 8.5: If the status of the invoice identified by the process robot is that the invoice does not exist, the process robot will combine the information of the four elements of the invoice to generate a feedback image (which one of the four elements of the invoice does not exist) and print directly on the image that the invoice does not exist news;

Step 8.6: If the status of the invoice recognized by the process robot is that the invoice information is inconsistent, the process robot will combine the information of the four elements of the invoice to generate a feedback image (which one of the four elements of the invoice information is inconsistent) and directly print out the invoice information on the image. information.

A value-added tax invoice authenticity inspection system based on an intelligent process robot provided according to the present invention includes:

Module 1: Start the main program of the process robot and initialize the parameters;

Module 2: The process robot reads related configurations, such as system time, operating environment, file directory, etc., and obtains a list of task numbers to be checked from the robot management server queue;

Module 3: The process robot judges whether the list of task numbers to be inspected has been processed. If not, execute module 4. If all processing is completed, execute module 10;

Module 4: The process robot uses the task number to obtain the relevant data of the value-added tax invoice from the database of the data management server;

Module 5: The process robot judges that the value-added tax invoice information obtained is a value-added tax invoice image or an invoice four-element text, if it is a value-added tax invoice image, execute module 6, and if it is an invoice four-element text, then execute module 7;

Module 6: The process robot uses optical character recognition technology to obtain the four-element text of the invoice in the image of the value-added tax invoice;

Module 7: The process robot queries whether the value-added tax invoice information is true through the text of the four elements of the invoice. If the invoice is true, it will obtain the invoice number, invoice code, invoice date, check code, tax-exclusive amount, tax amount, and Tax amount, machine code, invoice status, historical inspection times, seller’s bank information, seller’s account number, seller’s address, seller’s phone number, seller’s name, seller’s tax ID, buyer’s bank information, buyer’s Bank account number, buyer's address, buyer's phone number, buyer's name, buyer's tax ID, etc.;

Module 8: The process robot automatically logs in and visits the VAT invoice inspection platform of the State Administration of Taxation. The robot simulates manually filling in the four elements of the invoice in the web page selection box and inspecting it, obtaining the inspection result of the invoice information and taking a screenshot to obtain the image;

Module 9: The process robot sends the detailed invoice information obtained in Module 7 and the VAT invoice inspection platform certificate of the State Administration of Taxation obtained in Module 8 to the data management server for storage;

Module 10: The data management server sends back the verification result to the demand initiator and informs the business department that the verification of the VAT invoice has been completed;

Described module 8 comprises following modules:

Module 8.1: The process robot visits the homepage of the VAT invoice inspection platform of the State Administration of Taxation, and the process robot automatically fills in the invoice code and invoice number in the corresponding check boxes in sequence. After the invoice code and invoice number are successfully entered, the manual point is simulated in the pop-up calendar Select the invoice date of the value-added tax invoice. If the invoice type of the invoice is recognized as a general invoice in module 5, the process robot will fill in the verification code of the invoice in the last item popped up on the value-added tax invoice inspection platform of the State Administration of Taxation , if the invoice type of the invoice identified in module 5 is a special invoice, the tax-free amount will be filled in;

Module 8.2: After the process robot clicks the check button, it uses AI technology to intelligently identify the invoice information. The invoice status obtained from the query is genuine, voided invoice, non-existent invoice, and inconsistent invoice information, and according to these four different statuses be treated differently;

Module 8.3: If the status of the invoice identified by the process robot is genuine, the process robot obtains the information fed back by the VAT invoice inspection platform of the State Administration of Taxation, and automatically converts the information into a PDF image and saves it. If there are many, the information such as commodity type, quantity, tax amount, etc. will be automatically listed separately and saved for viewing, and the specific information on the ticket will be saved separately in a single page that can be easily viewed;

Module 8.4: If the status of the invoice recognized by the process robot is voided, the process robot will take the information fed back from the VAT invoice inspection platform of the State Administration of Taxation, and will automatically convert the information into a PDF image and print the word "voided" on the invoice image and save;

Module 8.5: If the status of the invoice recognized by the process robot is that the invoice does not exist, the process robot will combine the information of the four elements of the invoice to generate a feedback image (which one of the four elements of the invoice does not exist) and print directly on the image that the invoice does not exist news;

Module 8.6: If the status of the invoice recognized by the process robot is that the invoice information is inconsistent, the process robot will combine the information of the four elements of the invoice to generate a feedback image (which one of the four elements of the invoice information is inconsistent) and directly print out the inconsistent invoice information on the image information.

Those skilled in the art know that, in addition to realizing the system, device and each module thereof provided by the present invention in a purely computer-readable program code mode, the system, device and each module thereof provided by the present invention can be completely programmed by logically programming the method steps. The same program is implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers, among others. Therefore, the system, device and each module provided by the present invention can be regarded as a hardware component, and the modules included in it for realizing various programs can also be regarded as the structure in the hardware component; A module for realizing various functions can be regarded as either a software program realizing a method or a structure within a hardware component.

Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art may make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. In the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims (10)

1. A value-added tax invoice authenticity checking method based on an intelligent process robot is characterized by comprising the following steps:

step S1: the invoice information to be checked is sent to a robot management server, and the robot management server starts an intelligent process robot to automatically recognize the invoice information to obtain invoice authenticity information and invoice surface information;

step S2: and logging in a value-added tax invoice inspection platform of the national tax administration by using the intelligent process robot to perform invoice-added inspection and image file-keeping.

2. The method for verifying the authenticity of the value-added tax invoice based on the intelligent process robot as claimed in claim 1, wherein the reading of the computer configuration information by the intelligent process robot comprises: the method comprises the following steps of (1) operating system time of a computer, a computer running environment and a computer hard disk file directory; the intelligent process robot can be ensured to normally operate through the computer operating environment and the reading of the hard disk file directory of the computer; the operation safety of the intelligent process robot is ensured by reading the time of the computer operating system.

3. The value-added tax invoice authenticity checking method based on the intelligent process robot as claimed in claim 1, wherein the step S1 adopts:

step S1.1: sending invoice information to be checked to a robot management server, starting an intelligent flow robot by the robot management server, and acquiring a task number list to be checked from the robot management server by the intelligent flow robot;

step S1.2: the intelligent process robot acquires corresponding value-added tax invoice information from the robot management server according to the task number, and judges that the current value-added tax invoice information is a value-added tax invoice image or an invoice four-element text;

step S1.3: when the current value-added tax invoice information is a value-added tax invoice image, acquiring an invoice four-element text of the image by using an optical character recognition technology;

step S1.4: the intelligent process robot inquires whether the current value-added tax invoice information is true through the invoice four-element text, and when the invoice information is true, the invoice face information of the invoice is obtained.

4. The value-added tax invoice authenticity checking method based on the intelligent process robot as claimed in claim 3, wherein the invoice face information comprises: invoice number, invoice code, invoicing date, check code, tax free amount, tax containing amount, machine code, invoice status, historical check times, seller issuer information, seller issuer account number, seller address, seller telephone number, seller name, seller tax number, buyer issuer information, buyer issuer account number, buyer address, buyer telephone number, and buyer tax number information on the invoice surface.

5. The value-added tax invoice authenticity checking method based on the intelligent process robot as claimed in claim 1, wherein the step S2 adopts:

step S2.1: the intelligent process robot automatically logs in and visits a value-added tax invoice checking platform of the national tax administration, and simulates manual work to automatically fill corresponding contents in a corresponding selection frame of a webpage for checking based on the acquired invoice face information, so as to acquire a checking result of current invoice information and execute screenshot operation to acquire an image;

step S2.2: and the intelligent process robot sends the obtained invoice detail surface information and the inspection result image to the data management server for storage.

6. The value-added tax invoice authenticity checking method based on the intelligent process robot as claimed in claim 5, wherein the step S2.1 adopts:

step S2.1.1: the intelligent process robot accesses the homepage of the national tax administration value-added tax invoice checking platform, automatically and sequentially fills invoice codes and invoice numbers in corresponding selection frames, simulates and manually clicks the invoicing date of the value-added tax invoice in a popped calendar after the invoice codes and the invoice numbers are successfully recorded, if the invoice type of the invoice is identified to be a common invoice, the process robot fills the check code of the invoice in the last item popped by the national tax administration value-added tax invoice checking platform, and if the invoice type of the invoice is identified to be a special invoice, the process robot fills the check code without tax amount;

step S2.1.2: after clicking the checking button, the flow robot intelligently identifies the states of the invoice inquired by the invoice information, namely the real invoice, the invalidated invoice, the nonexistence of the invoice and the inconsistent invoice information by using an AI technology, and carries out different treatment according to the four different states;

step S2.1.3: if the invoice state identified by the process robot is a true invoice, the process robot acquires information fed back by a value-added tax invoice inspection platform of the State tax administration, automatically converts the information into a PDF image and stores the PDF image, if the types of goods contained in the invoice surface are excessive, automatically lists the information such as the types, the quantity, the tax amount and the like of the goods individually for storage, and stores the specific information of the invoice surface individually into a single page which can be conveniently checked;

step S2.1.4: if the invoice identified by the process robot is a voided invoice, the process robot takes the information fed back by the value-added tax invoice checking platform of the State tax administration, automatically converts the information into a PDF image, prints 'voided' characters on the invoice image and stores the characters;

step S2.1.5: if the invoice identified by the process robot is in the state that the invoice does not exist, the process robot generates a feedback image by combining the four-element information of the invoice and directly prints a message that the invoice does not exist on the image;

step S2.1.6: if the invoice status identified by the process robot is inconsistent with the invoice information, the process robot generates a feedback image by combining the four element information of the invoice and directly prints out the information of the inconsistent invoice information on the image.

7. The utility model provides a value-added tax invoice true and false inspection system based on intelligent process robot which characterized in that includes:

a module M1: sending invoice information to be checked to a robot management server, starting an intelligent process robot by the robot management server to automatically recognize the invoice information, and acquiring invoice authenticity information and invoice surface information;

a module M2: and logging in a value-added tax invoice inspection platform of the national tax administration by using the intelligent process robot to perform invoice-adding inspection and perform image filing.

8. The value-added tax invoice authenticity checking system based on the intelligent process robot as claimed in claim 7, wherein the module M1 adopts:

module M1.1: sending invoice information to be checked to a robot management server, starting an intelligent flow robot by the robot management server, and acquiring a task number list to be checked from the robot management server by the intelligent flow robot;

module M1.2: the intelligent process robot acquires corresponding value-added tax invoice information from the robot management server according to the task number, and judges that the current value-added tax invoice information is a value-added tax invoice image or an invoice four-element text;

module M1.3: when the current value-added tax invoice information is a value-added tax invoice image, acquiring an invoice four-element text of the image by using an optical character recognition technology;

module M1.4: the intelligent process robot inquires whether the current value-added tax invoice information is true through the invoice four-element text, and when the invoice information is true, the invoice face information of the invoice is obtained.

9. The value-added tax invoice authenticity checking system based on the intelligent process robot as claimed in claim 7, wherein the module M2 adopts:

module M2.1: the intelligent process robot automatically logs in and visits a value-added tax invoice checking platform of the national tax administration, and simulates manual work to automatically fill corresponding contents in a corresponding selection frame of a webpage for checking based on the acquired invoice face information, so as to acquire a checking result of current invoice information and execute screenshot operation to acquire an image;

module M2.2: and the intelligent flow robot sends the obtained detailed invoice surface information and the inspection result image of the invoice to the data management server for storage.

10. The value-added tax invoice authenticity checking system based on the intelligent process robot as claimed in claim 9, wherein the module M2.1 adopts:

module m2.1.1: the intelligent process robot accesses the homepage of the national tax administration value-added tax invoice checking platform, automatically and sequentially fills invoice codes and invoice numbers in corresponding selection frames, simulates and manually clicks the invoicing date of the value-added tax invoice in a popped calendar after the invoice codes and the invoice numbers are successfully recorded, if the invoice type of the invoice is identified to be a common invoice, the process robot fills the check code of the invoice in the last item popped by the national tax administration value-added tax invoice checking platform, and if the invoice type of the invoice is identified to be a special invoice, the process robot fills the check code without tax amount;

module m2.1.2: after clicking the checking button, the flow robot intelligently identifies the states of the invoice inquired by the invoice information, namely the real invoice, the invalidated invoice, the nonexistence of the invoice and the inconsistent invoice information by using an AI technology, and carries out different treatment according to the four different states;

module m2.1.3: if the invoice state identified by the process robot is a true invoice, the process robot acquires information fed back by a value-added tax invoice checking platform of the State tax administration, automatically converts the information into a PDF image and stores the PDF image, if the types of commodities contained in the invoice face are excessive, automatically and independently lists information such as the types, the quantities, the tax amounts and the like of the commodities for checking, and independently stores specific information of the invoice face into a single page convenient to check;

module m2.1.4: if the invoice state identified by the process robot is a waste invoice, the process robot takes information fed back by a value-added tax invoice inspection platform of the State tax administration, automatically converts the information into a PDF image, prints a waste character on the invoice image and stores the waste character;

module m2.1.5: if the invoice identified by the process robot is in the state of nonexistence, the process robot generates a feedback image by combining the four-element information of the invoice and directly prints a nonexistence invoice message on the image;

module m2.1.6: if the invoice status identified by the process robot is inconsistent with the invoice information, the process robot generates a feedback image by combining the four element information of the invoice and directly prints out the information of the inconsistent invoice information on the image.

Images