CN114693269A

CN114693269A - Invoice verification service handling method and device combining RPA and AI and electronic equipment

Info

Publication number: CN114693269A
Application number: CN202210362548.5A
Authority: CN
Inventors: 马炜利
Original assignee: Shanghai Laiyibert Network Technology Co ltd; Laiye Technology Beijing Co Ltd
Current assignee: Shanghai Laiyibert Network Technology Co ltd; Laiye Technology Beijing Co Ltd
Priority date: 2022-04-07
Filing date: 2022-04-07
Publication date: 2022-07-01

Abstract

The application relates to an invoice approval business handling method, an invoice approval business handling device and electronic equipment which are combined with RPA and AI, and relates to the technical field of RPA and AI, wherein the invoice approval business handling method comprises the following steps: logging in a business system of a tax department; acquiring taxpayer identification corresponding to target business items from a business system; inquiring in the service auxiliary system according to the taxpayer identification to obtain a service judgment result corresponding to the target service item; and transacting the target business items in the business system based on the business judgment result. Therefore, the handling of the invoice approval business is automatically performed by combining the RPA robot with the AI instead of manual work, the labor cost and the time cost required by handling the invoice approval business are reduced, and the accuracy of handling the invoice approval business is improved.

Description

Invoice verification service handling method and device combining RPA and AI and electronic equipment

Technical Field

The application relates to the technical field of robot process automation and artificial intelligence, in particular to an invoice approval business handling method and device combining RPA and AI and electronic equipment.

Background

Robot Process Automation (RPA for short) simulates the operation of a human on a computer through specific robot software, and automatically executes a Process task according to rules.

Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence.

Currently, many businesses can be transacted in an online manner. For example, when the taxpayer needs to check the invoice, the taxpayer can apply for the invoice through the relevant website on the line, and then the tax department can approve the application of the taxpayer. However, in this way of handling the invoice approval business online, the tax department still adopts a manual method to approve the business, which wastes a lot of labor cost and time cost, and cannot ensure the accuracy of business handling. How to improve the handling accuracy of the invoice approval business and reduce the labor and time cost becomes a problem to be solved urgently.

Disclosure of Invention

The application provides an invoice approval business handling method, an invoice approval business handling device and electronic equipment which are combined with RPA and AI, and aims to solve the technical problems of high labor cost and time cost and poor accuracy of the invoice approval business handling method in the related technology.

An embodiment of the first aspect of the present application provides an invoice approval service handling method combining an RPA and an AI, which is executed by an RPA robot, and includes: logging in a business system of a tax department; acquiring taxpayer identification corresponding to target business items from a business system; inquiring in the service auxiliary system according to the taxpayer identification to obtain a service judgment result corresponding to the target service item; and transacting the target business items in the business system based on the business judgment result.

In some embodiments, the service determination result includes a target type to which the target service item belongs and approval information corresponding to the target service item; the handling the target service item in the service system based on the service determination result includes: and transacting the target business items in the business system according to the transacting mode corresponding to the target type based on the approval information corresponding to the target business items.

In some embodiments, the target type is a first type, the first type indicating that the target business item meets business handling requirements; the processing the target business item in the business system based on the approval information corresponding to the target business item and according to the processing mode corresponding to the target type comprises the following steps: on the basis of the approval information, the target business item is transacted at a business transaction node, and after the transaction is completed, the transaction result of the target business item is pushed to an auditing node; auditing the transaction result of the target business item at the auditing node, and pushing the auditing result of the target business item to a distribution node after the auditing is passed; and processing the auditing result of the target business item at the issuing node to complete the handling process of the target business item.

In some embodiments, the target type is a second type, the second type indicating that the target business item does not meet business handling requirements; the processing the target business item in the business system based on the approval information corresponding to the target business item and according to the processing mode corresponding to the target type comprises the following steps: and the business handling node carries out invalidation processing on the target business item, and fills the invalidation reason of the target business item in a business handling page of the business handling node based on the verification information.

In some embodiments, the target type is a third type, and the third type indicates that the confidence of the service determination result is lower than a preset threshold; the processing the target business item in the business system based on the approval information corresponding to the target business item and according to the processing mode corresponding to the target type comprises the following steps: and on the basis of the approval information, the business acceptance node transacts the target business item, and after the transaction is completed, the transaction result of the target business item is pushed to other tax department nodes, so that the other tax departments further confirm the target business item on the basis of the transaction result.

In some embodiments, the business assistance system includes a business query page; the querying in the service auxiliary system according to the taxpayer identification to obtain the service judgment result corresponding to the target service item includes: logging in the service auxiliary system; accessing the service inquiry page according to the access path of the service inquiry page; and inputting the taxpayer identification corresponding to the target business item on the business query page so as to query by using the taxpayer identification and obtain a business judgment result corresponding to the target business item.

In some embodiments, the business system includes a login page; the business system for logging in the tax department comprises: accessing the service system according to the website information of the service system; accessing the login page according to the access path of the login page; calling a password manager, and inputting account information and corresponding password information on the login page in a virtual keyboard mode to log in the business system; the account information and the encrypted password information are stored in the password manager.

In some embodiments, after the accessing the login page according to the access path of the login page, the method further includes: judging whether a verification code picture exists on the login page or not; identifying the verification code on the verification code picture by adopting an Optical Character Recognition (OCR) technology under the condition that the verification code picture exists on the login page; and inputting the verification code on the login page.

The embodiment of the second aspect of the present application provides an invoice approval business handling device combining an RPA and an AI, which is applied to an RPA robot, and the device includes: the login module is used for logging in a business system of the tax department; the obtaining module is used for obtaining taxpayer identification corresponding to the target business item from the business system; the query module is used for querying in the service auxiliary system according to the taxpayer identification so as to obtain a service judgment result corresponding to the target service item; and the transaction module is used for transacting the target business items in the business system based on the business judgment result.

In some embodiments, the service determination result includes a target type to which the target service item belongs and approval information corresponding to the target service item; the transaction module comprises: and the transaction unit is used for transacting the target business items in the business system according to the transaction mode corresponding to the target type based on the approval information corresponding to the target business items.

In some embodiments, the target type is a first type, the first type indicating that the target business item meets business handling requirements; the transaction unit is used for: on the basis of the approval information, the target business item is transacted at a business transaction node, and after the transaction is completed, the transaction result of the target business item is pushed to an auditing node; auditing the transaction result of the target business item at the auditing node, and pushing the auditing result of the target business item to a distribution node after the auditing is passed; and processing the auditing result of the target business item at the issuing node to complete the handling process of the target business item.

In some embodiments, the target type is a second type, the second type indicating that the target business transaction does not comply with business handling requirements; the transaction unit is used for: and the business handling node carries out invalidation processing on the target business item, and fills the invalidation reason of the target business item in a business handling page of the business handling node based on the verification information.

In some embodiments, the target type is a third type, and the third type indicates that the confidence of the service determination result is lower than a preset threshold; the transaction unit is used for: and on the basis of the approval information, the business acceptance node transacts the target business item, and after the transaction is completed, the transaction result of the target business item is pushed to other tax department nodes, so that the other tax departments further confirm the target business item on the basis of the transaction result.

In some embodiments, the business assistance system includes a business query page; a query module comprising: the login unit is used for logging in the service auxiliary system; the first access unit is used for accessing the service inquiry page according to the access path of the service inquiry page; and the query unit is used for inputting the taxpayer identification corresponding to the target business item on the business query page so as to query by using the taxpayer identification and obtain a business judgment result corresponding to the target business item.

In some embodiments, the business system includes a login page; a login module comprising: the second access unit is used for accessing the service system according to the website information of the service system; the second access unit is used for accessing the login page according to the access path of the login page; the first processing unit is used for calling the password manager, and inputting account information and corresponding password information on a login page in a virtual keyboard mode so as to log in the service system; the password manager stores account information and encrypted password information.

In some embodiments, the login module further comprises: the judging unit is used for judging whether the verification code picture exists on the login page or not; the identification unit is used for identifying the verification code on the verification code picture by adopting an Optical Character Recognition (OCR) technology under the condition that the verification code picture exists on the login page; and the second processing unit is used for inputting the verification code on the login page.

An embodiment of the third aspect of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method according to the embodiment of the first aspect of the present application is implemented.

An embodiment of a fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method according to the embodiment of the first aspect of the present application.

An embodiment of the fifth aspect of the present application provides a computer program product, which includes a computer program, and the computer program, when executed by a processor, implements the method according to the embodiment of the first aspect of the present application.

The technical scheme provided by the embodiment of the application can have the following beneficial effects:

the method comprises the steps of logging in a business system of a tax department through an RPA robot, obtaining taxpayer identification corresponding to target business items from the business system, inquiring in a business auxiliary system according to the taxpayer identification to obtain business judgment results corresponding to the target business items, and handling the target business items in the business system based on the business judgment results, so that the RPA robot can automatically handle invoice approval business by combining with AI instead of manual work, the labor cost and the time cost required by handling the invoice approval business are reduced, and the accuracy of handling the invoice approval business is improved.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.

FIG. 1 is a schematic flow chart diagram of an invoice reconciliation business method combining RPA and AI according to a first embodiment of the present application;

FIG. 2 is an exemplary diagram of a business transaction page according to a first embodiment of the present application;

FIG. 3 is an exemplary diagram of a business transaction page according to a first embodiment of the present application;

FIG. 4 is a flow chart of an invoice reconciliation business method incorporating RPA and AI according to a second embodiment of the present application;

FIG. 5 is an exemplary diagram of a business query page in accordance with a second embodiment of the present application;

FIG. 6 is another exemplary diagram of a business query page in accordance with a second embodiment of the present application;

FIG. 7 is a flow chart of a method of invoice reconciliation business transaction in conjunction with RPA and AI according to a third embodiment of the present application;

FIG. 8 is an exemplary diagram of a top page of a business system in accordance with a third embodiment of the present application;

FIG. 9 is another exemplary diagram of a business transaction page according to a third embodiment of the present application;

FIG. 10 is an exemplary illustration of a pop-up window according to a third embodiment of the present application;

FIG. 11 is another exemplary diagram of a top page of a business system in accordance with a third embodiment of the present application;

FIG. 12 is an exemplary diagram of an audit result of a target business transaction according to a third embodiment of the present application;

fig. 13 is a schematic structural diagram of an invoice reconciliation service device combining RPA and AI according to a fourth embodiment of the present application;

fig. 14 is a block diagram of an electronic device for implementing an invoice reconciliation service method in conjunction with RPA and AI according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the embodiments of the present application/disclosure, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application/disclosure, and should not be construed as limiting the present application/disclosure.

These and other aspects of the embodiments of the present application/disclosure will be apparent with reference to the following description and attached drawings. In the description and drawings, particular embodiments of the present application/disclosed embodiments are disclosed in detail as being indicative of some of the ways in which the principles of the present application/disclosed embodiments may be practiced, but it is understood that the scope of the present application/disclosed embodiments is not limited thereby. Rather, the embodiments of the application/disclosure include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.

It should be noted that, in the technical solution of the present disclosure, the acquisition, storage, application, and the like of the personal information of the related user all conform to the regulations of the related laws and regulations, and do not violate the customs of the public order.

In the description of the present application/disclosure, the term "plurality" means two or more.

The utility model provides a mode through RPA robot and AI combination replaces the manual work to handle the thinking of invoice approval business automatically. The RPA robot can log in a business system of a tax department, obtain taxpayer identification corresponding to target business items from the business system, inquire in a business auxiliary system according to the taxpayer identification to obtain business judgment results corresponding to the target business items, and handle the target business items in the business system based on the business judgment results, so that the RPA robot can automatically handle invoice approval business by combining AI (artificial intelligence) instead of manual work, the labor cost and the time cost required by handling the invoice approval business are reduced, and the accuracy of handling the invoice approval business is improved.

For the purpose of clearly explaining the embodiments of the present invention, terms related to the embodiments of the present invention will be explained first.

In the description of the present application, the "RPA robot" refers to a software robot that can automatically perform invoice approval transaction in combination with AI technology and RPA technology. The RPA robot has two characteristics of 'connector' and 'non-invasion', and extracts, integrates and communicates data of different systems in a non-invasive mode on the premise of not changing an information system by simulating an operation method of a human.

In the description of the present application, "invoice reconciliation service" may include invoice reconciliation as well as invoice reconciliation adjustment service. The invoice verification refers to the confirmation of the type, quantity, purchase mode and the like of the invoice to be received by the tax department according to the operation range and scale of the unit and the individual who need to receive the invoice. The invoice approval adjustment refers to a business that the tax department changes the number of invoices issued and the maximum invoicing limit according to the application of the taxpayers who have handled the invoices and the production and operation change conditions of the taxpayers. The invoice in the embodiment of the present application may be a common invoice, or may also be a value-added tax invoice or other types of invoices, which is not limited in the present application.

In the description of the present application, a "business item" refers to a specific invoice approval business item in the pending invoice approval business, such as a value added tax invoice approval business applied by a taxpayer at a certain time.

In the description of the present application, a "business system" refers to an online system for the tax department to handle invoice approval business. The business system includes, but is not limited to, a "login page", a "business item page", a "business transaction page", and a "home page". The login page refers to a webpage for enabling a user to log in a user account, and the user account can be logged in by inputting information such as an account and a password in the webpage; "business item page" refers to a web page including business items for each invoice approval to be transacted and corresponding item information (such as taxpayer identification, business serial number, taxpayer name, application date, etc.); the service transaction page refers to a webpage for handling a specific invoice verification service item in the invoice verification service, and the information such as the number of invoices, the highest invoicing limit and the like can be filled or modified or the invoice verification service item can be invalidated through the service transaction page; the "home page" includes the business items to be handled, and through the page, the business handling page corresponding to the invoice approval business items can be accessed.

In the description of the present application, the "taxpayer identification" is used to uniquely identify the taxpayer, and may be, for example, a taxpayer identification number, or other identification, which is not limited in this application.

In the description of the present application, the "business assistance system" refers to a system for assisting the handling process of the invoice approval business, a rule to be followed by the invoice approval business is configured in the business assistance system, and by using the taxpayer identifier to perform query in the business assistance system, it can be determined whether the invoice approval business item corresponding to the taxpayer identifier meets the requirement specified by the rule. In the embodiment of the present application, the requirement specified by the rule is referred to as a service handling requirement. Business assistance systems include, but are not limited to, "landing pages," business query pages. The login page refers to a webpage for enabling a user to log in a user account, and the user account can be logged in by inputting information such as an account and a password into the webpage; the 'business inquiry page' refers to a webpage providing inquiry service, and can inquire whether the invoice approval business items corresponding to the taxpayer identification meet the business handling requirements or not by inputting the taxpayer identification in the webpage.

In the description of the present application, the "service determination result" refers to a result queried from the service assistance system using the taxpayer identification. The service determination result may include a target type to which the invoice approval service item belongs and approval information corresponding to the invoice approval service item.

Wherein, the target type may be any one of a first type, a second type and a third type. Wherein the first type represents that the invoice approval business items meet the business handling requirements. The second type indicates that the invoice reconciliation business item does not meet the business handling requirements. The third type indicates that the service auxiliary system cannot accurately determine whether the invoice approval service items meet the service handling requirements, namely, the confidence of the service judgment result is lower than a preset threshold. The preset threshold may be a value set as needed, which is not limited in the present application. When the target type is the first type or the third type, the approval information may include information such as a highest invoicing limit for a single invoice, a highest ticket buying amount per month, a highest ticket buying amount per time, a highest ticket holding amount, an offline invoicing time limit, and an offline invoicing accumulated limit. When the target type is the second type, the approval information may include a reason why the invoice approval business transaction does not meet the business handling requirements.

In the description of the present application, "service acceptance node", "audit node", "issuing node", and "other tax department node" refer to each transaction node included in the transaction process when transaction of invoice approval service items is performed in the service system.

The service acceptance node is an initial node of the transaction process, and can accept the invoice approval service items at the node, and the invoice approval service items are handled according to the service judgment result of the service auxiliary system on the invoice approval service items to obtain the transaction result of the invoice approval service items.

And the auditing node is an intermediate node of the transaction process under the condition that the invoice verification business items belong to the first type, and can audit the transaction result of the invoice verification business items pushed by the previous node at the node to obtain the auditing result of the invoice verification business items.

And the issuing node is an ending node of the transaction process when the invoice approval business item belongs to the first type, and at the node, an audit result of the invoice approval business item pushed by the previous node can be processed, for example, the audit result of the invoice approval business item is displayed, for example, whether the invoice approval business item is approved or not is passed, the number of invoices allowed to be issued by taxpayers after the tax department approves, the highest invoicing limit and the like.

And the other tax department nodes handle the intermediate node of the flow under the condition that the invoice verification business item belongs to the third type, and the handling result of the invoice verification business item pushed by the previous node can be further confirmed at the intermediate node.

In the description of the present application, a "password manager" is a hardware product for solving the problem of password storage and input, and may be connected to an electronic device through, for example, a USB (Universal Serial Bus) interface, so that the electronic device may be recognized as a USB keyboard by an operating system of the electronic device, and may also store multiple sets of encrypted passwords, and when input is required, the passwords may be directly input into the operating system by means of a virtual keyboard.

In the description of the present application, "OCR (Optical Character Recognition)", specifically refers to a process in which an electronic device checks a Character printed on paper, determines its shape by detecting dark and light patterns, and then translates the shape into a computer text by a Character Recognition method; the method is characterized in that characters in a paper document are converted into an image file with a black-white dot matrix in an optical mode aiming at print characters, and the characters in the image are converted into a text format through recognition software for further editing and processing by word processing software.

An invoice reconciliation business method, an apparatus, an electronic device, and a storage medium according to the embodiments of the present application/disclosure are described below with reference to the accompanying drawings.

First, an invoice approval business transaction method combining RPA and AI applied to an RPA robot in the embodiment of the present application will be described with reference to the drawings.

Fig. 1 is a flowchart of an invoice reconciliation service method combining RPA and AI according to a first embodiment of the present application. As shown in fig. 1, the method may include the steps of:

step 101, logging in a business system of a tax department.

Note that, the invoice approval transaction method combining the RPA and the AI according to the embodiment of the present application may be executed by an invoice approval transaction apparatus combining the RPA and the AI, and the invoice approval transaction apparatus combining the RPA and the AI will be simply referred to as an invoice approval transaction apparatus hereinafter. The invoice approval business handling device may be implemented by an RPA robot, for example, the invoice approval business handling device may be an RPA robot, or the invoice approval business handling device may be configured in the RPA robot, which is not limited in this application.

The RPA robot may be configured in an electronic device, and the electronic device may include, but is not limited to, a terminal device, a server, and the like. The embodiment of the present application is described by taking an invoice approval service transaction apparatus as an example of an RPA robot installed in a terminal device.

The RPA robot in this embodiment may execute the method in real time in a specific time period or all day, which is not limited in this application. Wherein the specific time period can be set as desired.

Alternatively, the RPA robot may be started at regular time or based on the reception of a start instruction. For example, the staff of the tax department may trigger the above starting instruction for the RPA robot by means of a dialog. The triggering of the starting instruction for the RPA robot may be implemented in various ways, for example, the starting instruction for the RPA robot may be triggered in a manner of voice and/or text, and for example, the starting instruction for the RPA robot may also be triggered in a manner of triggering a designated control on a human-computer interaction interface, which is not specifically limited in this embodiment of the present application.

And 102, acquiring taxpayer identification corresponding to the target business item from the business system.

The target business items are invoice approval business items which need to be handled currently.

The taxpayer identification is used to uniquely identify the taxpayer, for example, the taxpayer identification may be a taxpayer identification number, or other identification, which is not limited in this application.

In the embodiment of the present application, taking the taxpayer identification as the taxpayer identification number as an example, referring to fig. 2, the business system may include a business item page, where the business item page includes each invoice approval business item to be transacted and corresponding item information, where the item information includes, for example, the taxpayer identification number, the business serial number, the taxpayer name, the application date, and the like. The RPA robot may obtain the taxpayer identification number corresponding to the target business item from the business item page.

Or, the RPA robot may open a service transaction page corresponding to the target service item based on the service item page, where the service transaction page may include a tax payer invoice seed approval table. For example, the RPA robot may simulate a mouse click operation, and click a service serial number corresponding to the target service item in fig. 2 to open a service transaction page shown in fig. 3, where the service transaction page includes a taxpayer invoice receipt approval table. The tax payer receipt type approval table comprises specific information of the target business item, wherein the specific information comprises information such as a tax payer identification number, a tax payer name, a contact telephone and the like, so that the RPA robot can obtain the tax payer identification number corresponding to the target business item from the tax payer receipt type approval table corresponding to the target business item.

And 103, inquiring in the service auxiliary system according to the taxpayer identification to obtain a service judgment result corresponding to the target service item.

And 104, transacting the target business items in the business system based on the business judgment result.

In the embodiment of the application, after acquiring the taxpayer identifier corresponding to the target service item from the service system, the RPA robot may switch from the service system to the service auxiliary system, where the service auxiliary system includes a service inquiry page, so that the RPA robot may input the taxpayer identifier corresponding to the target service item on the service inquiry page, so as to perform inquiry by using the taxpayer identifier, and acquire the service determination result corresponding to the target service item. Further, the RPA robot may switch from the service assistance system to the service system, and transact the target service item in the service system based on the service determination result.

To sum up, according to the invoice approval business transaction method combining the RPA and the AI provided by the embodiment of the application, the RPA robot logs in the business system of the tax department, obtains the taxpayer identification corresponding to the target business item from the business system, queries in the business auxiliary system according to the taxpayer identification to obtain the business judgment result corresponding to the target business item, and transacts the target business item in the business system based on the business judgment result, so that the RPA robot automatically transacts the invoice approval business by combining the AI instead of manual work, the labor cost and the time cost required for transacting the invoice approval business are reduced, and the accuracy of the invoice approval business transaction is improved.

The following further describes the invoice approval transaction method combining the RPA and the AI provided in the embodiment of the present application with reference to fig. 4. Fig. 4 is a flowchart of an invoice reconciliation business method combining RPA and AI according to a second embodiment of the present application, as shown in fig. 4, the method comprising:

step 401, accessing the service system according to the website information of the service system.

In the embodiment of the application, the RPA robot can acquire the website information of the service system and access the service system according to the website information of the service system.

Step 402, accessing the login page according to the access path of the login page.

It will be appreciated that the access path to the landing page of a business system may be different for different business systems. In the embodiment of the application, the RPA robot may access the login page of the service system according to the access path corresponding to the login page of the logged-in service system.

Step 403, invoking a password manager, and inputting account information and corresponding password information on a login page in a virtual keyboard manner to log in the service system.

The password manager stores account information and encrypted password information.

In an embodiment of the present application, when logging in a business system, account information and corresponding password information may need to be input on a login page. In the embodiment of the application, the account information and the corresponding password information can be input on the login page by using the password manager so as to log in the business system. Specifically, the password manager stores account information and encrypted password information, and can be connected with the terminal device, so that the RPA robot can call the password manager after accessing a login page of the service system, and input the account information and the corresponding password information on the login page in a virtual keyboard manner to log in the service system. Therefore, the method and the device realize that the RPA robot is combined with the password manager to automatically input the account information and the corresponding password information so as to log in the business system.

In one possible implementation form, when logging in the business system, in addition to the account information and the corresponding password information, the verification of the picture verification code may be required.

In the embodiment of the application, the RPA robot can judge whether the verification code picture exists on the login page or not so as to judge whether the picture verification code verification is required or not. When the verification code picture exists on the login page, namely the picture verification code needs to be verified, the RPA robot can identify the verification code on the verification code picture by adopting an OCR technology, and then input the verification code on the login page to perform safety verification.

That is, after step 402, the method may further include: judging whether a verification code picture exists on the login page or not; identifying the verification code on the verification code picture by adopting an Optical Character Recognition (OCR) technology under the condition that the verification code picture exists on the login page; enter the verification code on the login page.

Therefore, the picture identifying code is identified by combining the RPA robot with the AI automatic identification picture identifying code so as to log in a service system.

Step 404, obtaining taxpayer identification corresponding to the target business item from the business system.

The specific implementation process and principle of step 404 may refer to the description of the above embodiments, and are not described herein again.

Step 405, logging in the service assistance system.

In the embodiment of the application, the RPA robot may acquire the website information of the service assistance system, and access the service assistance system according to the website information of the service assistance system. Furthermore, the RPA robot can access the login page according to the access path of the login page in the service auxiliary system, then call the password manager, and input account information and corresponding password information on the login page in a virtual keyboard manner to log in the service auxiliary system.

And step 406, accessing the service inquiry page according to the access path of the service inquiry page.

Step 407, inputting the taxpayer identification corresponding to the target business item on the business query page, so as to perform query by using the taxpayer identification, and obtaining the business judgment result corresponding to the target business item.

In the embodiment of the application, the service query page may provide an input frame for inputting the taxpayer identification and a query button for starting a query process, so that the RPA robot may input the taxpayer identification corresponding to the target service item in the input frame, and click the query button through simulating mouse operation to perform query by using the taxpayer identification to obtain the service determination result corresponding to the target service item.

For example, referring to an exemplary diagram of a service query page included in the service assistance system shown in fig. 5, the service query page may provide an input box 501 for inputting taxpayer identifiers and a query button 502 for starting a query process, and the RPA robot may input taxpayer identifiers corresponding to target service items in the input box 501, click the query button 502 by simulating mouse operation, so as to perform query by using the taxpayer identifiers, and wait for a preset duration. The preset duration can be set arbitrarily according to needs, and the application is not limited to this.

After waiting for the preset duration, referring to fig. 6, the service inquiry page may display information such as a service type, a service serial number, a taxpayer identification number, a taxpayer name, a tax authority, an application date, a progress status, and the like corresponding to the target service item inquired by the service assisting system. The RPA robot may simulate a mouse click operation to click the service serial number 601, so that a service query page may display a service determination result corresponding to the target service item as shown in part 602 in fig. 6.

Therefore, the RPA robot can automatically acquire the service judgment result corresponding to the target service item by using the service auxiliary system.

Step 408, transacting the target business item in the business system based on the business judgment result.

To sum up, the invoice verification service transaction method combining the RPA and the AI provided in the embodiment of the present application, an RPA robot accesses a service system according to website information of the service system, accesses a login page according to an access path of the login page, invokes a password manager, inputs account information and corresponding password information on the login page in a virtual keyboard manner to log in the service system, obtains a taxpayer identifier corresponding to a target service item from the service system, logs in a service auxiliary system, accesses a service inquiry page according to the access path of the service inquiry page, inputs a taxpayer identifier corresponding to the target service item on the service inquiry page, performs inquiry by using the taxpayer identifier, obtains a service determination result corresponding to the target service item, and transacts the target service item in the service system based on the service determination result, thereby, the handling of the invoice approval business is automatically performed by combining the RPA robot with the AI instead of manual work, the labor cost and the time cost required by handling the invoice approval business are reduced, and the accuracy of handling the invoice approval business is improved.

With reference to fig. 7, a process of transacting a target service item in a service system based on a service determination result in the invoice approval service transaction method combining the RPA and the AI according to the embodiment of the present application is further described. Fig. 7 is a flowchart of an invoice reconciliation business method combining RPA and AI according to a third embodiment of the present application, as shown in fig. 7, the method including:

and step 701, logging in a business system of the tax department.

Step 702, obtaining taxpayer identification corresponding to the target business item from the business system.

Step 703, inquiring in the service auxiliary system according to the taxpayer identification to obtain a service judgment result corresponding to the target service item; the service judgment result comprises a target type to which the target service item belongs and approval information corresponding to the target service item.

The specific implementation process and principle of steps 701-703 may refer to the description of the foregoing embodiments, and are not described herein again.

And 704, transacting the target business item in the business system according to the transaction mode corresponding to the target type based on the approval information corresponding to the target business item.

Wherein, the target type may be any one of a first type, a second type and a third type. Wherein the first type represents that the invoice approval business items meet the business handling requirements. The second type indicates that the invoice reconciliation business item does not meet the business handling requirements. The third type indicates that the service auxiliary system cannot accurately determine whether the invoice approval service items meet the service handling requirements, namely, the confidence of the service judgment result is lower than a preset threshold. The preset threshold may be a value set as needed, which is not limited in the present application.

In practical applications, the service assistance system may display the target type to which the target service item belongs by displaying the text of the determination result portion in fig. 6 in different colors. For example, when the target type to which the target service item belongs is the first type, the text of the judgment result part is displayed as green; when the target type of the target business item is a second type, displaying characters of the judgment result part as red; and when the target type of the target business item is a third type, displaying the characters of the judgment result part in yellow.

It can be understood that different target types correspond to different transaction manners, in this embodiment of the application, the target business item may be transacted in the business system according to the transaction manner corresponding to the target type based on the approval information corresponding to the target business item.

The following describes a specific implementation procedure of step 704 when the target types to which the target service items belong are the first type, the second type, and the third type, respectively.

The first condition is as follows: the target type is the first type

In an embodiment of the present application, in the case that the target type is the first type, step 704 may be implemented by: processing the target business items at the business processing node based on the approval information, and pushing the processing result of the target business items to the auditing node after the processing is finished; auditing the transaction result of the target business item at the auditing node, and pushing the auditing result of the target business item to the issuing node after the auditing is passed; and processing the auditing result of the target business item at the issuing node to complete the handling process of the target business item.

When the target type is the first type, the approval information may include information such as a highest invoicing limit of a single invoice, a highest monthly ticket purchasing quantity, a highest ticket purchasing quantity each time, a highest ticket holding quantity, an offline invoicing time limit, an offline invoicing accumulated limit, and the like.

In the embodiment of the application, when the target type to which the target business item belongs is the first type and the invoice approval business item is transacted in the business system, the transaction flow at least comprises the business transaction node, the audit node and the issuing node.

Wherein, at the service acceptance node, the RPA robot can handle the target service item based on the approval information. Specifically, the RPA robot may perform information filling in a service transaction page corresponding to the target service item, and store the service transaction page after the completion of the filling, where the transaction result of the target service item in the embodiment of the present application may be understood as information included in the service transaction page that is completed by the filling. And then the RPA robot can push the transaction result of the target business item to the auditing node based on the stored business transaction page.

One or more auditing nodes may be provided. When the number of the auditing nodes is one, the RPA robot can audit the transaction result of the target business item pushed by the previous node at the auditing nodes, store the auditing result of the target business item after the auditing is passed, and then push the auditing result of the target business item to the issuing node. When a plurality of audit nodes are provided, at each audit node, the RPA robot can audit the transaction result of the target service item pushed by the previous node, and after the audit is passed, the audit result of the target service item is stored, and then the audit result of the target service item is pushed to the next audit node until the audit result is pushed to the issuing node.

In the issuing node, the service system may process an audit result of the target service item pushed by the previous node, for example, show the audit result of the target service item, for example, whether the invoice approval service item is approved or not is passed, the number of invoices allowed to be issued by the taxpayer after approval by the tax department, the highest invoice quota, and the like, and the RPA robot may store the audit result of the target service item. In addition, the RPA robot may continue to execute the node pushing operation after the audit result is saved, and determine that the transaction process of the target business item is ended after the business system outputs the prompt information that the node is the last node of the transaction process.

Referring to fig. 8-12, taking the actual scenario as an example, the process of the RPA robot handling the target business transaction when the target type is the first type will be described. In the scene, two auditing nodes of 'tax source management department confirmation' and 'tax source management department responsible person confirmation' are included.

Referring to fig. 8, the business system of the tax department may include a home page including business items to be handled, i.e., tasks to be handled included in the "personal task list" in fig. 8. The theme of the business transaction may include a "accept" word, which indicates that the business transaction is a business transaction that needs to be processed by the accept node. After obtaining the service determination result corresponding to the target service item from the service assistance system, the RPA robot may access the home page shown in fig. 8 when determining that the target type to which the target service item belongs is the first type, and click the theme of the target service item in the home page by simulating a mouse click operation to enter the service acceptance node.

It should be noted that, when the RPA robot acquires the taxpayer identifier corresponding to the target service item from the service system, the service handling page shown in fig. 3 may be opened, and before the RPA robot enters the service handling node through the home page shown in fig. 8, the service handling page shown in fig. 3 may also be saved.

After the RPA robot clicks the subject of the target business item in fig. 8 by simulating the mouse click operation, the business transaction page of the target business item shown in fig. 9 may be accessed, and then, on the business transaction page, various pieces of information in the section "details of ticket approval application" 901 are filled in based on the approval information. After completion of filling, the RPA robot may simulate a mouse click operation, click a "save" button 902 shown in fig. 9, save the service transaction page, and further click a "push" button 903 shown in fig. 9 after successful saving, so as to push the transaction result of the target service item to a "tax authority confirmation" node in the audit node.

When node pushing is performed, after the RPA robot clicks the "push" button 903 shown in fig. 9, a popup window shown in fig. 10 may be displayed in the service transaction page shown in fig. 9 for selecting a next audit node. The RPA robot can acquire the information of the transactants of the next auditing node according to a pre-stored form containing the information of the transactants of each tax department, and then select the corresponding transactants to push according to the information of the transactants. Specifically, the RPA robot may simulate a mouse click operation, click in the selection box 1001 before the clerk code in fig. 10 to select the corresponding clerk, and then click the save button 1002 to push to the corresponding clerk.

Further, referring to fig. 11, after the RPA robot pushes the transaction result of the service accepting node for the target service item to the "tax administration department confirmation" node, in the service system of the tax department, the to-be-handled service items included in the home page may include the service items that the "tax administration department confirms" node needs to process, that is, the to-be-handled task in the "personal to-be-handled task list" includes the word "tax administration department confirms". The RPA robot may click on the subject of the target business transaction by simulating a mouse click operation in the home page shown in fig. 11 to enter the "tax authority confirmation" node.

After the RPA robot clicks the theme of the target business item in fig. 11 by simulating the mouse click operation, the service transaction page of the target business item similar to fig. 9 can be accessed, the transaction result of the target business item pushed by the service transaction node is checked on the service transaction page, and after the check is completed, the "save" button in the service transaction page is clicked by simulating the mouse click operation, so that the service transaction page is saved. Further, after the storage is successful, the RPA robot may click a "push" button in the service transaction page, and push the audit result of the target service item to the "tax authority responsible person confirmation" node through a popup similar to that shown in fig. 10.

Further, the RPA robot may enter a manner similar to the manner of "confirming the node by the tax fund management department", and a person in charge of the tax fund management department confirms that the node verifies the verification result of the target service item pushed by the node by the tax fund management department, and pushes the verification result to the issuing node after the verification is passed.

Further, the RPA robot may enter the issuing node in a manner similar to the "tax authority confirms" node. At the issuing node, the business system may display the audit results of the target business transaction as shown in fig. 12. The RPA robot may simulate a mouse click operation, and click the "save" button 1201 in fig. 12 to save the audit result of the target business transaction. Further, after the saving is successful, the RPA robot may click the "push" button 1202 in fig. 12, and after the service system displays the prompt message that the node is the last node of the transaction process, the RPA robot may determine that the transaction process of the target service item is ended.

Through the process, the RPA robot automatically transacts the target business item in the business system according to the transaction mode corresponding to the target type based on the approval information corresponding to the target business item when the target type of the target business item is the first type. Because the items required to be processed by each node in the transaction flow do not need to be processed manually, the labor cost and the time cost for transacting the target business items are reduced, and the accuracy for transacting the target business items is improved.

Case two: the target type is a second type

In an embodiment of the present application, in the case that the target type is the second type, step 704 may be implemented by: and the business handling node carries out invalidation processing on the target business item, and based on the approval information, fills the invalidation reason of the target business item in the business handling page of the business handling node.

When the target type is the second type, the approval information may include a reason why the invoice approval business item does not meet the business handling requirement.

In the embodiment of the application, when the target type to which the target business item belongs is the second type and the invoice is approved in the business system for business transaction, the transaction flow at least comprises the business transaction node.

The RPA robot can invalidate the target service item at the service acceptance node, and based on the approval information, fill the invalidation reason of the target service item in the service acceptance page of the service acceptance node.

Referring to fig. 3, after acquiring the service determination result corresponding to the target service item from the service assistance system, the RPA robot may access the service transaction page corresponding to the target service item shown in fig. 3 when determining that the target type to which the target service item belongs is the second type. Further, the RPA robot may fill a cancellation reason of the target service item in the "feedback opinion" in the service transaction page based on the approval information, and click the "cancellation" button 301 in the service transaction page by simulating a mouse click operation to cancel the target service item.

Case three: the target type is a third type

In an embodiment of the present application, in the case that the target type is the third type, step 704 may be implemented by: and on the basis of the approval information, the business handling node handles the target business item, and after the handling is finished, the handling result of the target business item is pushed to other tax department nodes, so that other tax departments further confirm the target business item on the basis of the handling result.

When the target type is the third type, the approval information may include information such as a highest invoicing limit of a single invoice, a highest monthly ticket purchasing quantity, a highest ticket purchasing quantity each time, a highest ticket holding quantity, an offline invoicing time limit, an offline invoicing accumulated limit, and the like.

In the embodiment of the application, when the target type to which the target business item belongs is the third type and the invoice approval business item is transacted in the business system, the transaction flow at least includes the business acceptance node and other tax department nodes.

Wherein, at the service acceptance node, the RPA robot can handle the target service item based on the approval information. Specifically, the RPA robot may perform information filling in a service transaction page corresponding to the target service item, and store the service transaction page after the completion of the filling, where the transaction result of the target service item in the embodiment of the present application may be understood as information included in the service transaction page that is completed by the filling. And then the RPA robot can push the transaction result of the target business item to other tax department nodes based on the stored business transaction page, so that other tax departments can further confirm the target business item based on the transaction result.

The RPA robot handles the target business item based on the approval information, and pushes the handling result of the target business item to other tax department nodes after the handling is completed, and the process when the target type is the first type can be referred to, which is not described herein again.

To sum up, the invoice verification service handling method combining the RPA and the AI provided by the embodiment of the application, the RPA robot logs in the service system of the tax department, obtains the taxpayer identification corresponding to the target service item from the service system, and according to the taxpayer identification, inquiring in the service auxiliary system to obtain the service judgment result corresponding to the target service item, wherein, the service judgment result comprises the target type of the target service item and the approval information corresponding to the target service item, based on the approval information corresponding to the target service item and according to the handling mode corresponding to the target type, the target business items are handled in the business system, so that the RPA robot is combined with the AI to replace manual work to automatically handle the invoice approval business, the labor cost and the time cost required by handling the invoice approval business are reduced, and the accuracy of handling the invoice approval business is improved.

In order to implement the above embodiment, the present application further provides an invoice approval transaction apparatus combining an RPA and an AI. Fig. 13 is a schematic structural diagram of an invoice reconciliation service device combining RPA and AI according to a fourth embodiment of the present application.

As shown in fig. 13, the invoice reconciliation transaction apparatus 1300 combining RPA and AI is applied to an RPA robot, and includes: a login module 1301, an acquisition module 1302, a query module 1303, and an transacting module 1304.

The login module 1301 is used for logging in a business system of the tax department;

an obtaining module 1302, configured to obtain, from a service system, a taxpayer identifier corresponding to a target service item;

the query module 1303 is configured to query in the service auxiliary system according to the taxpayer identifier to obtain a service determination result corresponding to the target service item;

a transaction module 1304, configured to transact the target business item in the business system based on the business determination result.

It should be noted that the invoice approval transaction apparatus 1300 according to the embodiment of the present application may execute the invoice approval transaction method according to the RPA and the AI provided in the above embodiment. The invoice approval transaction apparatus 1300 combining RPA and AI may be implemented by an RPA robot, for example, the invoice approval transaction apparatus 1300 combining RPA and AI may be an RPA robot, or the invoice approval transaction apparatus may be configured in an RPA robot, which is not limited in this application.

The RPA robot may be configured in an electronic device, and the electronic device may include, but is not limited to, a terminal device, a server, and the like.

In an embodiment of the present application, the service determination result includes a target type to which the target service item belongs and approval information corresponding to the target service item; an administration module 1304, comprising:

and the transaction unit is used for transacting the target business items in the business system according to the transaction mode corresponding to the target type based on the approval information corresponding to the target business items.

In one embodiment of the present application, the target type is a first type, and the first type indicates that the target business item meets the business handling requirement; a transaction unit to:

processing the target business items at the business processing node based on the approval information, and pushing the processing result of the target business items to the auditing node after the processing is finished;

auditing the transaction result of the target business item at the auditing node, and pushing the auditing result of the target business item to the issuing node after the auditing is passed;

and processing the auditing result of the target business item at the issuing node to complete the handling process of the target business item.

In one embodiment of the present application, the target type is a second type, the second type indicating that the target service item does not meet the service handling requirement; a transaction unit to:

and the business handling node carries out invalidation processing on the target business item, and based on the approval information, fills the invalidation reason of the target business item in the business handling page of the business handling node.

In one embodiment of the application, the target type is a third type, and the third type indicates that the confidence of the service judgment result is lower than a preset threshold; a transaction unit to:

and on the basis of the approval information, the business handling node handles the target business item, and after the handling is finished, the handling result of the target business item is pushed to other tax department nodes, so that other tax departments further confirm the target business item on the basis of the handling result.

In one embodiment of the present application, a business assistance system includes a business query page; query module 1303, including:

the login unit is used for logging in the service auxiliary system;

the first access unit is used for accessing the service inquiry page according to the access path of the service inquiry page;

and the query unit is used for inputting the taxpayer identification corresponding to the target business item on the business query page so as to query by using the taxpayer identification and obtain a business judgment result corresponding to the target business item.

In one embodiment of the present application, a business system includes a landing page; the login module 1301 includes:

the second access unit is used for accessing the service system according to the website information of the service system;

the second access unit is used for accessing the login page according to the access path of the login page;

the first processing unit is used for calling the password manager, and inputting account information and corresponding password information on a login page in a virtual keyboard mode so as to log in the service system;

In an embodiment of the present application, the login module 1301 further includes:

the judging unit is used for judging whether the verification code picture exists on the login page or not;

the recognition unit is used for recognizing the verification code on the verification code picture by adopting an Optical Character Recognition (OCR) technology under the condition that the verification code picture exists on the login page;

and the second processing unit is used for inputting the verification code on the login page.

It should be noted that the explanation of the embodiment of the method for handling invoice approval service in combination with RPA and AI also applies to the apparatus for handling invoice approval service in combination with RPA and AI in this embodiment, and details that are not published in the embodiment of the apparatus for handling invoice approval service in combination with RPA and AI are not described here again.

To sum up, the invoice approval business transaction device combining the RPA and the AI of the embodiment of the application logs in a business system of a tax department, obtains a taxpayer identifier corresponding to a target business item from the business system, queries in a business auxiliary system according to the taxpayer identifier to obtain a business judgment result corresponding to the target business item, and transacts the target business item in the business system based on the business judgment result, thereby realizing that an RPA robot combines the AI to replace manual work to automatically transact the invoice approval business, reducing the labor cost and time cost required for transacting the invoice approval business, and improving the accuracy of transacting the invoice approval business.

In order to implement the foregoing embodiments, an electronic device is further provided in an embodiment of the present application, and includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method for handling invoice approval service in combination with RPA and AI according to any one of the foregoing method embodiments.

In order to implement the foregoing embodiment, the present application further proposes a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for handling invoice approval business in combination with RPA and AI according to any one of the foregoing method embodiments.

In order to implement the foregoing embodiments, the present application further provides a computer program product, wherein when being executed by an instruction processor of the computer program product, the method for handling invoice approval business in combination with RPA and AI according to any of the foregoing method embodiments is implemented.

FIG. 14 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present application. The electronic device 12 shown in fig. 14 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in FIG. 14, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. These architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, to name a few.

Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 14, and commonly referred to as a "hard drive"). Although not shown in FIG. 14, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.

Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with electronic device 12, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via the Network adapter 20. As shown in FIG. 14, the network adapter 20 communicates with the other modules of the electronic device 12 via the bus 18. It should be appreciated that although not shown in FIG. 14, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing by executing programs stored in the memory 28, for example, implementing the methods mentioned in the foregoing embodiments.

In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried out in the method of implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and the program, when executed, includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims

1. A method of invoice reconciliation business in combination with RPA and AI, performed by an RPA robot, the method comprising:

logging in a business system of a tax department;

obtaining taxpayer identification corresponding to the target business item from the business system;

inquiring in a service auxiliary system according to the taxpayer identification to obtain a service judgment result corresponding to the target service item;

and transacting the target business items in the business system based on the business judgment result.

2. The method according to claim 1, wherein the service decision result includes an object type to which the object service item belongs and approval information corresponding to the object service item;

the transacting the target business item in the business system based on the business determination result comprises:

and transacting the target business items in the business system according to the transacting mode corresponding to the target type based on the approval information corresponding to the target business items.

3. The method of claim 2, wherein the target type is a first type, the first type indicating that the target business item meets business handling requirements;

the processing the target business item in the business system according to the processing mode corresponding to the target type based on the approval information corresponding to the target business item comprises the following steps:

on the basis of the approval information, the target business item is transacted at a business transaction node, and after the transaction is completed, the transaction result of the target business item is pushed to an auditing node;

auditing the transaction result of the target business item at the auditing node, and pushing the auditing result of the target business item to a distribution node after the auditing is passed;

and processing the auditing result of the target business item at the issuing node to complete the transaction flow of the target business item.

4. The method of claim 2, wherein the target type is a second type, the second type indicating that the target business transaction does not comply with business handling requirements;

the processing the target business item in the business system based on the approval information corresponding to the target business item and according to the processing mode corresponding to the target type comprises the following steps:

and the business handling node carries out invalidation processing on the target business item, and fills the invalidation reason of the target business item in a business handling page of the business handling node based on the verification information.

5. The method of claim 2, wherein the target type is a third type, and the third type indicates that the confidence of the service decision result is lower than a preset threshold;

and on the basis of the approval information, the business acceptance node transacts the target business item, and after the transaction is completed, the transaction result of the target business item is pushed to other tax department nodes, so that the other tax departments further confirm the target business item on the basis of the transaction result.

6. The method of any of claims 1-5, wherein the business assistance system comprises a business query page;

the querying in the service auxiliary system according to the taxpayer identification to obtain the service judgment result corresponding to the target service item includes:

logging in the service auxiliary system;

accessing the service inquiry page according to the access path of the service inquiry page;

and inputting the taxpayer identification corresponding to the target business item on the business query page so as to query by using the taxpayer identification and obtain a business judgment result corresponding to the target business item.

7. The method of any of claims 1-5, wherein the business system comprises a login page;

the business system for logging in the tax department comprises:

accessing the service system according to the website information of the service system;

accessing the login page according to the access path of the login page;

calling a password manager, and inputting account information and corresponding password information on the login page in a virtual keyboard mode to log in the business system;

the account information and the encrypted password information are stored in the password manager.

8. The method according to claim 7, wherein after accessing the landing page according to the access path of the landing page, further comprising:

judging whether a verification code picture exists on the login page or not;

identifying the verification code on the verification code picture by adopting an Optical Character Recognition (OCR) technology under the condition that the verification code picture exists on the login page;

and inputting the verification code on the login page.

9. An invoice approval business handling device combining RPA and AI, which is applied to an RPA robot, and comprises:

the login module is used for logging in a business system of the tax department;

the obtaining module is used for obtaining taxpayer identification corresponding to the target business item from the business system;

the query module is used for querying in a service auxiliary system according to the taxpayer identification so as to obtain a service judgment result corresponding to the target service item;

and the transaction module is used for transacting the target business items in the business system based on the business judgment result.

10. The apparatus according to claim 9, wherein the service decision result includes a target type to which the target service item belongs and approval information corresponding to the target service item;

the transaction module comprises:

11. The apparatus of claim 10, wherein the target type is a first type, the first type indicating that the target business item meets business handling requirements;

the transaction unit is used for:

processing the target business item at a business processing node based on the approval information, and pushing a processing result of the target business item to an auditing node after the processing is finished;

12. The apparatus of claim 10, wherein the target type is a second type, the second type indicating that the target business transaction does not comply with business handling requirements;

the transaction unit is used for:

13. The apparatus according to claim 10, wherein the target type is a third type, and the third type indicates that a confidence of the service decision result is lower than a preset threshold;

the transaction unit is used for:

14. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1-8 when executing the computer program.

15. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-8.