CN112766892A

CN112766892A - Method and device for combining fund ratio of RPA and AI and electronic equipment

Info

Publication number: CN112766892A
Application number: CN202110031678.6A
Authority: CN
Inventors: 汪冠春; 胡一川; 褚瑞; 李玮; 潘庚生
Original assignee: Beijing Benying Network Technology Co Ltd; Beijing Laiye Network Technology Co Ltd
Current assignee: Beijing Benying Network Technology Co Ltd; Beijing Laiye Network Technology Co Ltd
Priority date: 2021-01-11
Filing date: 2021-01-11
Publication date: 2021-05-07

Abstract

The application provides a method and a device for combining fund ratio of RPA and AI and electronic equipment, and relates to the technical field of RPA and AI. Wherein, the method comprises the following steps: carrying out optical character recognition on the data sheet to be processed to generate an electronic data sheet and corresponding business personnel; acquiring a to-be-checked data set corresponding to the to-be-processed data sheet in the financial management system; according to the electronic data sheet, verifying data corresponding to the specified type in the data set to be verified; generating a capital allocation work order according to the data of the specified type under the condition that the data corresponding to the specified type passes the verification; and sending the fund ratio work order to the business personnel. Therefore, automatic processing of fund matching is realized through the RPA technology, labor cost is reduced, and efficiency and reliability of generating fund matching work orders are improved.

Description

Method and device for combining fund ratio of RPA and AI and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to the fields of Artificial Intelligence (AI) and Robot Process Automation (RPA), and more particularly, to a method and an apparatus for matching funds between RPA and AI, and an electronic device.

Background

Robot Process Automation (RPA) is a Process task automatically executed according to rules by simulating human operations on a computer through specific robot software.

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

In the existing business, a worker needs to log in a financial management system every day, and items in the system are sequentially checked and processed according to the content in a paper document, when the data volume to be processed is large, a large amount of manual time is occupied, the efficiency of manually processing fund proportion is not high, in addition, the situation of misjudgment is easily caused by manual data operation, and the accuracy is low.

Disclosure of Invention

The fund ratio method, the fund ratio device and the electronic equipment combining the RPA and the AI are used for solving the problems that in the related technology, the fund ratio is processed in a manual mode, the efficiency is low, mistakes are easy to occur, and the reliability is poor.

The fund proportioning method combining the RPA and the AI, which is provided by the embodiment of the application on the one hand, comprises the following steps:

carrying out optical character recognition on the data sheet to be processed to generate an electronic data sheet and corresponding business personnel;

acquiring a to-be-checked data set corresponding to the to-be-processed data sheet in the financial management system;

according to the electronic data sheet, verifying data corresponding to the specified type in the data set to be verified;

generating a capital allocation work order according to the data of the specified type under the condition that the data corresponding to the specified type passes the verification;

and sending the fund ratio work order to the business personnel.

Another embodiment of the present application provides an apparatus for combining fund allocation of RPA and AI, including:

the first generation module is used for carrying out optical character recognition on the data sheet to be processed so as to generate an electronic data sheet and corresponding business personnel;

the acquisition module is used for acquiring a to-be-verified data set corresponding to the to-be-processed data sheet in the financial management system;

the verification module is used for verifying the data corresponding to the specified type in the data set to be verified according to the electronic data sheet;

the second generation module is used for generating a fund matching worksheet according to the data of the specified type under the condition that the data corresponding to the specified type passes the verification;

and the first sending module is used for sending the fund matching work order to the business personnel.

An embodiment of another aspect of the present application provides an electronic device, which includes: memory, processor and computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements a method of combining a fund ratio of an RPA and an AI as previously described.

In another aspect, the present application provides a computer readable storage medium, on which a computer program is stored, wherein the program is executed by a processor to implement the method for combining the fund proportioning of RPA and AI as described above.

In another aspect, the present application provides a computer program, which when executed by a processor, implements the method for fund matching in combination with RPA and AI according to the embodiments of the present application.

The method, the device and the electronic equipment for combining the fund ratio of the RPA and the AI have the following beneficial effects:

the method comprises the steps of firstly carrying out optical character recognition on a data sheet to be processed to generate an electronic data sheet and corresponding business personnel, then obtaining a data set to be verified corresponding to the data sheet to be processed in a financial management system, namely, verifying data corresponding to a specified type in the data set to be verified according to the electronic data sheet, generating a capital allocation work order according to the data of the specified type under the condition that the data corresponding to the specified type passes verification, and sending the capital allocation work order to the business personnel. Therefore, the RPA system can automatically perform OCR processing on the data sheet, verify the data corresponding to the designated type in the data set to be verified in the financial management system according to the generated electronic data sheet, and automatically generate the capital allocation work order and send the capital allocation work order to business personnel when the verification is passed, so that the automatic processing of capital allocation is realized through the RPA technology, the labor cost is reduced, and the efficiency and the reliability of generating the capital allocation work order are 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

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

FIG. 1 is a schematic flow chart illustrating a method for combining RPA and AI fund allocation according to an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart illustrating a method for combining RPA and AI fund allocation according to another embodiment of the present disclosure;

FIG. 3 is a schematic structural diagram of an apparatus for combining fund allocation of RPA and AI according to an embodiment of the present disclosure;

FIG. 4 is a schematic structural diagram of an apparatus for combining fund allocation of RPA and AI according to another embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

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

The embodiment of the application provides a fund proportioning method combining RPA and AI aiming at the problems of low efficiency, easy error and poor reliability caused by processing the fund proportioning in a manual mode in the related technology.

The method, apparatus and electronic device for matching funds with RPA and AI provided in the present application are described in detail below with reference to the accompanying drawings.

The method for combining the fund proportioning of the RPA and the AI according to the embodiment of the present application may be performed by the apparatus for combining the fund proportioning of the RPA and the AI according to the embodiment of the present application, and the apparatus may be configured in an electronic device.

Fig. 1 is a schematic flowchart of a method for matching funds with an RPA and an AI according to an embodiment of the present disclosure.

As shown in fig. 1, the method for combining the fund proportion of the RPA and the AI comprises the following steps:

step 101, performing optical character recognition on a data sheet to be processed to generate an electronic data sheet and a corresponding service person.

The data sheet may be any type of paper data sheet, for example, a printed document such as an invoice, or a document manually written, which is not limited in this application.

It should be understood that the characters in the data sheet may be any type of characters, such as chinese characters, numbers, letters, etc., and the present application is not limited thereto.

In addition, Optical Character Recognition (OCR) is a computer input technology that converts characters of various bills, newspapers, books, manuscripts and other printed matters into image information by Optical input methods such as scanning and the like, and converts the image information into usable image information by using a Character Recognition technology, and is applicable to the fields of entry and processing of bank bills, a large amount of Character data, archive files and documents, and is suitable for automatic scanning Recognition and long-term storage of a large amount of bill forms in the industries such as banking, tax and the like.

It is understood that the RPA system may process the paper data sheet using the OCR technology of the AI to generate the electronic data sheet and the corresponding business personnel, and may also read and record the related data information in the data sheet.

In addition, the business personnel may be a worker responsible for data auditing, or may also be a related worker handling fund matching work, and the like, which is not limited in the present application.

For example, if the type of the to-be-processed data sheet is an electric charge refund class, the corresponding service person may be a worker a, or if the type of the to-be-processed data sheet is a worker sales class, the corresponding service person may be a worker B. Or, the business personnel corresponding to any data sheet are all the workers C.

It should be noted that the types of the data sheets, the staff A, B, C, and the like are only illustrative, and should not be taken as limitations on the data sheets to be processed in the embodiment of the present application, the types thereof, corresponding business staff, and the like.

It should be noted that the RPA technology can intelligently understand the existing application of the electronic device through the user interface, automate repeated regular operations based on rules and in large batch, such as automatically and repeatedly reading mails, reading Office components, operating databases, web pages, client software, and the like, collect data and perform complex calculations, so as to generate files and reports in large batch, thereby greatly reducing the input of labor cost and effectively improving the Office efficiency through the RPA technology. Therefore, in a fund proportioning processing scene, an RPA program can be configured in the electronic equipment for fund proportioning, so that the electronic equipment can automatically perform optical character recognition on a data sheet to be processed according to rules set in the RPA program to generate an electronic data sheet and corresponding business personnel.

And 102, acquiring a to-be-verified data set corresponding to the to-be-processed data sheet in the financial management system.

The financial management system may be a system for filling in the content of a to-be-processed data sheet for a user, or may be any system for submitting a data sheet declaration for a user, and the like, which is not limited in the present application.

In addition, the data set to be verified may be the content of a data sheet filled in by the user in the financial management system, or may also be information generated by the financial management system in combination with the content filled in by the user, and the like, which is not limited in the present application.

It can be understood that, when the RPA system searches for a to-be-checked data set corresponding to a to-be-processed data sheet in the financial management system, the to-be-checked data set can be searched in a plurality of query manners. For example, the search may be performed in the financial management system according to the data included in the data sheet, or the search may be performed in the financial management system according to the information such as the payment receiving unit included in the data sheet, which is not limited in the present application.

In the embodiment of the application, after the optical character recognition is carried out on the data sheet to be processed by the RPA system, the data set to be checked corresponding to the data sheet to be processed can be obtained in the financial management system, so that the manual operation is reduced, the time is saved, and the efficiency is greatly improved.

And 103, verifying the data corresponding to the specified type in the data set to be verified according to the electronic data sheet.

The designated type may be a payment type, or may also be a payment type and a budget type, which is not limited in this application.

For example, if the data corresponding to the payment type in the electronic data sheet is 100 and the specified type is the payment type, the RPA system may search for the data corresponding to the payment type in the acquired data set to be verified, and compare the data with 100.

Or, the payment type in the electronic data sheet is 500, the budget type is 600, the specified types are the payment type and the budget type, and the RPA system may search data corresponding to the payment type and the budget type respectively in the acquired data set to be verified, and compare the data corresponding to the payment type and the budget type with 500 and 600 respectively.

It should be noted that the above values 100, 500, 600, etc. are only schematic illustrations, and should not be taken as limitations on the types specified in the embodiments of the present application and their corresponding data, data sets to be verified, etc.

And 104, generating a fund proportioning worksheet according to the data of the specified type under the condition that the data corresponding to the specified type passes the verification.

The fund allocation work order may be a work order automatically generated by the RPA system according to the verified data of the specified type.

For example, if the data corresponding to the payment type in the electronic data sheet is 200, the RPA system finds that the data corresponding to the payment type is also 200 in the acquired data set to be verified, which indicates that the data corresponding to the payment type passes verification, and at this time, the RPA system may automatically generate the fund allocation work sheet according to the 200 corresponding to the payment type.

Or the data corresponding to the payment type in the electronic data sheet is 300, the data corresponding to the budget type is 700, the specified type is the payment type and the budget type, and the RPA system finds that the data corresponding to the payment type and the data corresponding to the budget type are 300 and 700 respectively in the acquired data set to be verified, which indicates that the data corresponding to the specified type passes verification, and at this time, the RPA system can automatically generate the fund proportioning worksheet according to the data corresponding to the payment type 300 and the data corresponding to the budget type 700.

It should be noted that the

above values

200, 300, 700, etc. are only schematic illustrations, and should not be taken as limitations on the data corresponding to the specified types, the data sets to be verified, etc. in the embodiments of the present application.

And 105, sending the fund ratio worksheet to business personnel.

The RPA system may use various modes when sending the fund allocation work order to the business personnel.

For example, the RPA system may send the money allocation worksheet to the business personnel in the form of mail. Alternatively, the RPA system may send the fund allocation worksheet to the business personnel using the corresponding working system. Or, the RPA system may also call corresponding application software, such as nailing, wechat, etc., to send the fund matching worksheet to the business personnel.

It should be noted that the sending manner is only an example, and cannot be taken as a limitation for sending the fund proportion worksheet to the business personnel in the embodiment of the present application.

According to the embodiment of the application, optical character recognition is firstly carried out on a data sheet to be processed to generate an electronic data sheet and corresponding business personnel, then a data set to be verified corresponding to the data sheet to be processed in a financial management system is obtained, namely, data corresponding to the specified type in the data set to be verified can be verified according to the electronic data sheet, so that a capital allocation work order is generated according to the data of the specified type under the condition that the data corresponding to the specified type passes verification, and the capital allocation work order is sent to the business personnel. Therefore, the RPA system can automatically perform OCR processing on the data sheet, verify the data corresponding to the designated type in the data set to be verified in the financial management system according to the generated electronic data sheet, and automatically generate the capital allocation work order and send the capital allocation work order to business personnel when the verification is passed, so that the automatic processing of capital allocation is realized through the RPA technology, the labor cost is reduced, and the efficiency and the reliability of generating the capital allocation work order are improved.

In the embodiment, the RPA system can automatically process the data sheet, verify the data corresponding to the specified type in the data set to be verified in the financial management system according to the generated electronic data sheet, and automatically generate the fund proportioning worksheet and send the fund proportioning worksheet to the service staff when the verification is passed. As can be seen from the above analysis, the data sheet to be processed may include numbers and letters, and when the RPA system identifies the data sheet, the RPA system may identify a character to be identified based on at least two distance values between a central point and at least two boundary points of the character, which will be described in detail with reference to fig. 2.

Step 201, determining a first probability that each character in the data sheet to be processed is a number and a second probability that each character is a letter.

The first probability of the corresponding number and the second probability of the corresponding letter of different characters may be the same or different, and this is not limited in the present application.

For example, a first probability of one character in the data sheet to be processed, which is a number, may be 0.8, and a second probability of one character being a letter may be 0.1.

Alternatively, a first probability of a character in the data sheet to be processed being a number may be 0.6 and a second probability of being a letter may be 0.6.

Note that the characters, the first probabilities 0.8, 0.6, the second probabilities 0.1, 0.6, and the like are merely illustrative, and are not intended to limit the first probability that each character is a numeral and the second probability that each character is a letter in the embodiments of the present application.

Step 202, under the condition that the difference value between the first probability and the second probability corresponding to any character is smaller than a threshold value, at least two distance values between the central point and at least two boundary points of any character are determined.

The threshold may be any preset value, which is not limited in this application.

For example, the threshold is 0.2, the first probability that any character corresponds to a number is 0.6, the second probability that any character corresponds to a letter is 0.5, and the difference between the two probabilities is 0.1 and less than the threshold 0.2, and at this time, at least two distance values between the center point of any character and at least two boundary points may be further determined.

The characters 0, 0.2, 0.6, 0.5, 0.1, etc. are only illustrative, and should not be construed as limitations of the characters, the first probability, the second probability, the threshold, etc. in the embodiments of the present application.

Step 203, determining the type of any character according to at least two distance values.

The candidate number and/or the candidate letter corresponding to any character may be determined, then at least two target distance values corresponding to any character may be determined according to the candidate number and/or the candidate letter, and then the type of any character may be determined according to the at least two target distance values and the at least two distance values.

For example, the probability of any character being identified as the candidate number "0" is 0.7, the probability of being identified as the candidate letter "o" is 0.68, and the two distance values between its center point and the two boundary points are 0.7, 0.4, respectively, while the two target distance values for the candidate number "0" are 0.6, 0.4, respectively, and the two target distance values for the candidate letter "o" are 0.5, respectively. Therefore, according to the magnitude relation between the target distance value and the distance value, the any character can be determined to be the number 0.

Alternatively, the probability of identifying any character as the candidate number "2" is 0.87, the probability of identifying any character as the candidate letter "z" is 0.86, and the two distances between the center point and the two boundary points are 0.3 and 0.3, respectively, while the two target distance values of the candidate number "2" are 0.5 and 0.6, respectively, and the two target distance values corresponding to the candidate letter "z" are 0.35 and 0.35, respectively. Therefore, according to the magnitude relation between the target distance value and the distance value, any character can be determined to be the letter z.

It should be noted that the above examples are only illustrative, and cannot be taken as a limitation for determining the type of any character in the embodiments of the present application.

In the embodiment of the application, when the RPA system identifies the data sheet to be processed, the character can be accurately identified based on at least two distance values between the central point and at least two boundary points of the character to be identified, so that the accuracy of the identification result is further improved.

And 204, acquiring a to-be-verified data set corresponding to the to-be-processed data sheet in the financial management system.

And step 205, respectively verifying the business side name, the financial institution name and the business-related account of the data corresponding to the specified type in the data set to be verified according to the electronic data sheet.

The name of the business party may be a collection unit, or may also be a unit or an individual who opens a document, the financial institution may be a bank, an insurance company, or the like, and the business-related account may be a collection account, or may also be a unit or an individual corresponding account which opens a document, or the like, which is not limited in the present application.

For example, in the data set to be verified acquired by the RPA system, the business party name of the data corresponding to the specified type may be AAA, the financial institution may be the beijing XX bank, and the business-related account may be ABC, and then the business party name, the financial institution, and the business-related account are respectively compared with the business party name, the financial institution, and the business-related account corresponding to the electronic data sheet one by one to verify whether the business party name, the financial institution, and the business-related account are consistent.

It should be noted that the above-mentioned business side name AAA, financial institution Beijing XX bank, business-related account ABC, etc. are only schematic illustrations, and cannot be used as limitations on the business side name, the financial institution name, and the business-related account in the embodiment of the present application.

And step 206, detecting a plurality of business-related accounts corresponding to any data in the electronic data sheet under the condition that the business-related account of any data corresponding to the specified type in the electronic data sheet is not matched with the business-related account of the corresponding data in the data set to be verified.

Step 207, determining that any data passes verification under the condition that the business-related accounts containing any data in the data set to be verified in the plurality of business-related accounts.

For example, the RPA system may match three electronic data sheets A, B, C according to any data in the data set to be verified, where the business-related account in any data is XX, and the business-related account in the electronic data sheet a is YY, and when the two are not matched, further comparing whether XX matches the business-related account in the electronic data sheet B, C. If all of the business-related accounts in the electronic data sheet B, C are XX, and all match a business-related account in any of the data, a comparison can continue as to whether the financial institution name in the electronic data sheet B, C matches the financial institution name in any of the data. If the name of the financial institution of the electronic data sheet C is consistent with that of any data, whether the name of the business party is consistent with that of any data can be continuously judged, and if so, the fact that any data passes the verification can be determined.

It should be noted that the data records, the electronic data sheet A, B, C, the business-related accounts XX, YY, and the like are only schematic illustrations, and cannot be used as limitations when any data in the data set to be verified is verified in the embodiment of the present application.

And step 208, generating a fund ratio worksheet according to the data of the specified type under the condition that the data corresponding to the specified type passes the verification.

And step 209, sending the fund ratio worksheet to business personnel.

Step 210, adding any data into a preset abnormal data list under the condition that any data corresponding to the specified type is not verified.

The abnormal data list may store the abnormal data and information corresponding to the abnormal data, such as a name of a business party, a name of a financial institution, a business-related account, and the like, which is not limited in the present application.

For example, the data 200 corresponding to the payment type is not verified, and the data 200 and the corresponding information such as the name of the business party, the name of the financial institution, the business-related account, and the like may be added to a preset abnormal data list.

It should be noted that the payment type, the data 200, and the like are only schematic illustrations, and cannot be taken as a limitation to add any data to a preset abnormal data list in the embodiment of the present application.

And step 211, sending the abnormal data list to a service staff.

When the RPA system sends the abnormal data list to the service staff, there may be a variety of ways, such as mail, nail, WeChat, etc., which is not limited in this application.

It can be understood that when the service personnel receives the abnormal data list sent by the RPA system, the service personnel can also check and inspect the data therein, so as to ensure the accuracy and integrity of the data.

In XX XXX system, the fund proportioning process performed by RPA system is taken as an example and described in detail below.

The RPA system can automatically perform optical character recognition on the to-be-processed data sheet to generate an electronic data sheet and corresponding business personnel, and it can be understood that the to-be-processed data sheet may include a plurality of information such as a document number, a document name, a payment amount, a collection account, and the like.

The RPA system may then automatically enter a funding proportion payment interface.

It is understood that the fund proportioning payment interface may also be different in different systems and different scenarios, for example, in some scenarios, the type of service processed may be selected, for example, all may be selected [ type of service ]; budget period — current (i.e., the month of the system's current date); (iii) processing state ═ all; each page shows records ═ 2000 bars.

The RPA system can click the [ application payment amount ] in the fund proportioning payment interface to obtain a data set to be verified corresponding to the data sheet to be processed, then verify the data corresponding to the specified type in the data set to be verified according to the electronic data sheet, and display the data and the associated information which pass the verification on a page.

The specified type may be [ pay ], or may also be [ pay ] and [ budget ], and different systems may have different settings. For example, in current systems, the specified type is [ pay ].

In addition, there may be a variety of situations in the dataset to be verified. For example, the following steps: if there is no sum value, it can be recorded in the abnormal record table; or, the money amount values are the same, but the name of the collection account is inconsistent, and the money amount values can be recorded into the abnormal record table at this time; the same amount value, the same name of the collection account and the [ type ] of the collection account may also occur, and at this time, the [ document number ], the [ document name ], the [ payment amount ], the [ abnormal reason ] and the like in the collection account may be recorded in the abnormal recording table; alternatively, multiple pieces of data may be recorded for data of the same amount value, the same name of the collection account, and the type [ pay ]. In some scenes, whether the [ payment plan number ] of a plurality of matched data records meets the condition or not can be continuously checked, if the [ payment plan number ] meets the condition, the data meeting the condition and the associated information thereof are displayed on a page, and if the [ payment plan number ] does not meet the condition, the data is added into an abnormal record table; or if the amount is the same, the name of the collection account is consistent, and only one piece of data with the type of payment is available, the data and the associated information thereof are directly displayed on the page.

It will be appreciated that in some scenarios, the determination may also be continued with respect to the data displayed in the page as described above. For example, whether the [ transfer mark ] meets the condition can be continuously judged, and if the [ transfer mark ] meets the condition, a payment information payment checking link is started; if the [ transfer mark ] does not satisfy the condition, the document is not processed, and at this time, the corresponding [ document number ], [ document name ], [ payment amount ], [ abnormal reason ], and the like may be added to the abnormal record table.

Then, the RPA system can compare the [ collection units ], [ collection accounts ] and [ opening bank names ] in the data records of the fund proportioning interface with the [ collection units ], [ collection accounts ] and [ opening bank names ] in the electronic data sheet one by one, and if the comparison result is consistent, the next step is carried out; if the data is inconsistent with the data in the electronic data sheet, judging whether the data is a plurality of collection account numbers, wherein the collection bank account numbers identified from the electronic data sheet may exist in a plurality, if the data is one of the collection bank account numbers, defaulting legal data, if the data does not belong to the data, defaulting illegal data, and recording abnormal data into an abnormal record table. In addition, in some scenarios, the service types may be multiple or may be one. For example, the RPA system may determine that the current service type is the electric charge refund according to the word "electric charge refund" included in the recognition result. Or, the RPA system may determine that the current service type is employee reimbursement according to the word patterns of "travel", "taxi taking", and the like included in the recognition result, or the RPA system may determine that the current service type is SSS according to other keyword patterns included in the recognition result.

Different requirements may be required for different users, for example, the operator may be modified according to the type of service. For example, for the XYY system, where [ service type ] is [ electric charge refund ], the default fixed operator is [ DD ]; or [ business type ] is [ employee reimbursement ], the operator may be the name of the person in the funding proportion payment.

After a series of checks, the RPA can click the [ ratio payment ] in the page to complete the operation, generate a corresponding fund ratio work order, and send the fund ratio work order to corresponding business personnel. Or, the RPA system may also send the abnormal record table to the corresponding service personnel.

In some scenarios, the RPA system may further record the ratio payment, for example, obtain the [ payment plan number ] of this time, write it back to the WW table, and mark it as "payment plan number [ system ]).

It is understood that the occurrence of clicks [ ratio payments ] may be different according to the data sheet. For example, it may prompt to repeat payment, if there are the same [ cash receiving account ], [ amount ], [ cash receiving party unit ], [ pop-up window, including payment in the previous month, at which point a click [ confirm ] is required; or, possibly prompting that the budget is not released, recording the data into an abnormal record table; or, the over-budget can be prompted, the matching payment failure can be displayed, and the data can be recorded into an abnormal record table; alternatively, other situations may arise, etc.

It should be noted that the above fund proportioning payment interface, page format, page information, windows, and the like are only examples, and may be modified according to actual situations when in specific use, and cannot be used as limitations on the fund proportioning process interface, contents, and the like in the present application.

In the embodiment of the application, when the RPA system identifies the data sheet, the RPA system may identify the character based on at least two distance values between a center point and at least two boundary points of the character to be identified, then check the business party name, the financial institution name and the business-related account of the data corresponding to the specified type in the data set to be checked according to the electronic data sheet, and automatically send the generated capital allocation worksheet to business personnel when the data corresponding to the specified type passes the check, or automatically send the abnormal data list to the business personnel when the data does not pass the check. Therefore, the RPA system can accurately identify the numbers and letters which are difficult to distinguish in the data sheet, accurately check different matching conditions in the electronic data sheet, and send corresponding information to business personnel according to different checking results, thereby further improving the accuracy and reliability of fund proportioning processing.

In order to implement the above embodiments, the present application further provides a device for combining the fund proportioning of the RPA and the AI.

Fig. 3 is a schematic structural diagram of an apparatus for combining fund allocation of RPA and AI according to an embodiment of the present disclosure.

As shown in fig. 3, the apparatus 300 for combining fund proportioning of RPA and AI includes: a first generation module 310, an acquisition module 320, a verification module 330, a second generation module 340, and a first sending module 350.

The first generating module 310 is configured to perform optical character recognition on the data sheet to be processed to generate an electronic data sheet and a corresponding service staff.

An obtaining module 320, configured to obtain a to-be-verified data set corresponding to the to-be-processed data sheet in the financial management system.

And the checking module 330 is configured to check, according to the electronic data sheet, data corresponding to the specified type in the data set to be checked.

The second generating module 340 is configured to generate a fund allocation worksheet according to the data of the specified type when the data corresponding to the specified type passes the verification.

A first sending module 350, configured to send the fund matching work order to the business personnel.

It should be noted that, for the functions and the specific implementation principles of the modules in the embodiment of the present application, reference may be made to the method embodiments described above, and details are not described here again.

The device for capital matching by combining the RPA and the AI, provided by the embodiment of the application, firstly performs optical character recognition on a data sheet to be processed to generate an electronic data sheet and corresponding business personnel, then acquires a data set to be checked corresponding to the data sheet to be processed in a financial management system, namely, the data set to be checked corresponding to an appointed type is checked according to the electronic data sheet, so that a capital matching work sheet is generated according to the data of the appointed type under the condition that the data corresponding to the appointed type passes the check, and the capital matching work sheet is sent to the business personnel. Therefore, the RPA system can automatically perform OCR processing on the data sheet, verify the data corresponding to the designated type in the data set to be verified in the financial management system according to the generated electronic data sheet, and automatically generate the capital allocation work order and send the capital allocation work order to business personnel when the verification is passed, so that the automatic processing of capital allocation is realized through the RPA technology, the labor cost is reduced, and the efficiency and the reliability of generating the capital allocation work order are improved.

As a possible implementation manner of the embodiment of the present application, as shown in fig. 4, on the basis of fig. 3, the apparatus for combining fund proportioning of RPA and AI further includes: an adding module 360 and a second sending module 370.

In one possible implementation, the first generating module 310 includes:

a first determining unit 3110, configured to determine a first probability that each character in the to-be-processed data sheet is a number and a second probability that each character is a letter;

a second determining unit 3120, configured to determine at least two distance values between a center point of any character and at least two boundary points when a difference between a first probability and a second probability corresponding to the character is smaller than a threshold;

a third determining unit 3130 for determining a type of the any character according to the at least two distance values.

In a possible implementation manner, the third determining unit 3130 is specifically configured to: determining candidate numbers and/or candidate letters corresponding to any character; determining at least two target distance values corresponding to any character according to the candidate numbers and/or the candidate letters; and determining the type of any character according to the at least two target distance values and the at least two distance values.

In a possible implementation manner, the checking module 330 is specifically configured to: and respectively verifying the business side name, the financial institution name and the business-related account of the data corresponding to the specified type in the data set to be verified according to the electronic data sheet.

In a possible implementation manner, the checking module 330 is further specifically configured to: under the condition that a business-related account of any data corresponding to the specified type in the electronic data sheet is not matched with a business-related account of corresponding data in the data set to be verified, detecting a plurality of business-related accounts corresponding to the any data in the electronic data sheet; and determining that any data passes verification under the condition that the plurality of business-related accounts contain the business-related account of any data in the data set to be verified.

An adding module 360, configured to add any data corresponding to the specified type into a preset abnormal data list when the data does not pass the verification.

A second sending module 370, configured to send the abnormal data list to the service staff.

According to the device for combining the fund proportioning of the RPA and the AI, when a data sheet is identified, the RPA system can identify the character based on at least two distance values between a center point and at least two boundary points of the character to be identified, then respectively check the name of a business party, the name of a financial institution and a business associated account of data corresponding to an appointed type in a data set to be checked according to an electronic data sheet, and automatically send the generated fund proportioning work sheet to business personnel when the data corresponding to the appointed type passes the check, or automatically send an abnormal data list to the business personnel when the data corresponding to the appointed type does not pass the check. Therefore, the RPA system can accurately identify the numbers and letters which are difficult to distinguish in the data sheet, accurately check different matching conditions in the electronic data sheet, and send corresponding information to business personnel according to different checking results, thereby further improving the accuracy and reliability of fund proportioning processing.

In order to implement the above embodiments, the present application further provides an electronic device.

Fig. 5 is a schematic structural diagram of an electronic device incorporating a method for fund matching of RPA and AI according to an embodiment of the present application.

As shown in fig. 5, the electronic device 200 includes:

a memory 210 and a processor 220, a bus 230 connecting different components (including the memory 210 and the processor 220), wherein the memory 210 stores a computer program, and when the processor 220 executes the computer program, the method for matching funds with RPA and AI according to the embodiment of the present application is implemented.

Bus 230 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. By way of example, such 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.

Electronic device 200 typically includes a variety of electronic device readable media. Such media may be any available media that is accessible by electronic device 200 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 210 may also include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)240 and/or cache memory 250. The electronic device 200 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 260 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic 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 CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 230 by one or more data media interfaces. Memory 210 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 280 having a set (at least one) of program modules 270, including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may comprise an implementation of a network environment, may be stored in, for example, the memory 210. The program modules 270 generally perform the functions and/or methodologies of the embodiments described herein.

Electronic device 200 may also communicate with one or more external devices 290 (e.g., keyboard, pointing device, display 291, etc.), with one or more devices that enable a user to interact with electronic device 200, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 200 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 292. Also, the electronic device 200 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 293. As shown, the network adapter 293 communicates with the other modules of the electronic device 200 via the bus 230. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 200, 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 processor 220 executes various functional applications and data processing by executing programs stored in the memory 210.

It should be noted that, for the implementation process and the technical principle of the electronic device of this embodiment, reference is made to the foregoing explanation of the method for matching funds with an RPA and an AI in this embodiment of the application, and details are not described here again.

According to the electronic equipment provided by the embodiment of the application, optical character recognition is firstly carried out on a data sheet to be processed to generate an electronic data sheet and corresponding business personnel, then a data set to be verified corresponding to the data sheet to be processed in a financial management system is obtained, namely, data corresponding to an appointed type in the data set to be verified can be verified according to the electronic data sheet, so that a capital allocation work order is generated according to the data of the appointed type under the condition that the data corresponding to the appointed type passes verification, and the capital allocation work order is sent to the business personnel. Therefore, the RPA system can automatically perform OCR processing on the data sheet, verify the data corresponding to the designated type in the data set to be verified in the financial management system according to the generated electronic data sheet, and automatically generate the capital allocation work order and send the capital allocation work order to business personnel when the verification is passed, so that the automatic processing of capital allocation is realized through the RPA technology, the labor cost is reduced, and the efficiency and the reliability of generating the capital allocation work order are improved.

In order to implement the above embodiments, the present application also proposes a computer-readable storage medium.

The computer readable storage medium has a computer program stored thereon, and the computer program is executed by a processor to implement the method for combining the fund proportioning of the RPA and the AI according to the embodiment of the present application.

To implement the foregoing embodiments, a further embodiment of the present application provides a computer program, which when executed by a processor, implements the method for matching funds with RPA and AI according to the embodiments of the present application.

In an alternative implementation, the embodiments may be implemented in any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the consumer electronic device, partly on the consumer electronic device, as a stand-alone software package, partly on the consumer electronic device and partly on a remote electronic device, or entirely on the remote electronic device or server. In the case of remote electronic devices, the remote electronic devices may be connected to the consumer electronic device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external electronic device (e.g., through the internet using an internet service provider).

According to the technical scheme, firstly, optical character recognition is carried out on a data sheet to be processed to generate an electronic data sheet and corresponding business personnel, then a data set to be verified corresponding to the data sheet to be processed in a financial management system is obtained, namely, data corresponding to the specified type in the data set to be verified can be verified according to the electronic data sheet, so that a capital allocation work order is generated according to the data of the specified type under the condition that the data corresponding to the specified type passes verification, and the capital allocation work order is sent to the business personnel. Therefore, the RPA system can automatically perform OCR processing on the data sheet, verify the data corresponding to the designated type in the data set to be verified in the financial management system according to the generated electronic data sheet, and automatically generate the capital allocation work order and send the capital allocation work order to business personnel when the verification is passed, so that the automatic processing of capital allocation is realized through the RPA technology, the labor cost is reduced, and the efficiency and the reliability of generating the capital allocation work order are improved.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A method of combining RPA and AI funding, comprising:

s1, carrying out optical character recognition on the data sheet to be processed to generate an electronic data sheet and a corresponding service staff;

s2, acquiring a to-be-verified data set corresponding to the to-be-processed data sheet in the financial management system;

s3, verifying the data corresponding to the specified type in the data set to be verified according to the electronic data sheet;

s4, generating a fund matching work order according to the data of the specified type under the condition that the data corresponding to the specified type passes the verification;

and S5, sending the fund matching work order to the business personnel.

2. The method as claimed in claim 1, wherein the data sheet to be processed includes numbers and letters, and the step S1 includes:

s11, determining a first probability that each character in the data sheet to be processed is a number and a second probability that each character is a letter;

s12, determining at least two distance values between the center point of any character and at least two boundary points under the condition that the difference value between the first probability and the second probability corresponding to the character is smaller than a threshold value;

and S13, determining the type of any character according to the at least two distance values.

3. The method of claim 2, wherein the S13, comprises:

s131, determining candidate numbers and/or candidate letters corresponding to any character;

s132, determining at least two target distance values corresponding to any character according to the candidate numbers and/or the candidate letters;

s133, determining the type of any character according to the at least two target distance values and the at least two distance values.

4. The method of claim 1, wherein the S3, comprises:

and S31, verifying the business side name, the financial institution name and the business-related account of the data corresponding to the specified type in the data set to be verified respectively according to the electronic data sheet.

5. The method of claim 4, after the S31, further comprising:

s32, detecting a plurality of business-related accounts corresponding to any data in the electronic data sheet when the business-related account of any data corresponding to the specified type in the electronic data sheet is not matched with the business-related account of the corresponding data in the data set to be verified;

s33, determining that any data passes verification when the business-related accounts include the business-related account of any data in the data set to be verified.

6. The method according to any of claims 1-5, further comprising, after the S3:

s6, under the condition that any data corresponding to the specified type does not pass the verification, adding any data into a preset abnormal data list;

and S7, sending the abnormal data list to the service personnel.

7. An apparatus for combining RPA and AI funding, comprising:

8. The apparatus of claim 7, wherein the data sheet to be processed comprises numbers and letters, and the first generating module comprises:

the first determining unit is used for determining a first probability that each character in the data sheet to be processed is a number and a second probability that each character is a letter;

the second determining unit is used for determining at least two distance values between the center point of any character and at least two boundary points under the condition that the difference value between the first probability and the second probability corresponding to the character is smaller than a threshold value;

and the third determining unit is used for determining the type of any character according to the at least two distance values.

9. The apparatus of claim 8, wherein the third determining unit is specifically configured to:

determining candidate numbers and/or candidate letters corresponding to any character;

determining at least two target distance values corresponding to any character according to the candidate numbers and/or the candidate letters;

and determining the type of any character according to the at least two target distance values and the at least two distance values.

10. The apparatus of claim 7, wherein the verification module is specifically configured to:

and respectively verifying the business side name, the financial institution name and the business-related account of the data corresponding to the specified type in the data set to be verified according to the electronic data sheet.

11. The apparatus of claim 10, wherein the verification module is further specifically configured to:

under the condition that a business-related account of any data corresponding to the specified type in the electronic data sheet is not matched with a business-related account of corresponding data in the data set to be verified, detecting a plurality of business-related accounts corresponding to the any data in the electronic data sheet;

and determining that any data passes verification under the condition that the plurality of business-related accounts contain the business-related account of any data in the data set to be verified.

12. The apparatus of any of claims 7-11, further comprising:

the adding module is used for adding any data corresponding to the specified type into a preset abnormal data list under the condition that the data do not pass the verification;

and the second sending module is used for sending the abnormal data list to the service personnel.

13. An electronic device, comprising: a memory, a processor, and a program stored on the memory and executable on the processor, the processor when executing the program implementing the method of combining fund proportioning of RPA and AI according to any one of claims 1-6.

14. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out a method of combining fund proportioning for RPA and AI according to any one of claims 1-6.