Method, device and electronic device for capital allocation combining RPA and AI
By combining RPA and AI, the fund allocation process is automated, and the problems of low manual processing efficiency and poor reliability are solved, and the automation and efficient processing of fund allocation are achieved.
Patent Information
- Application Number
- CN202110031678.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-01-11
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2041-01-11
AI Technical Summary
In the prior art, manual processing of funds allocation is inefficient and prone to errors, resulting in poor reliability.
Combined with robot process automation (RPA) and artificial intelligence (AI), electronic data sheets are generated through optical character recognition, and the data is automatically verified in the financial management system, and the fund allocation work orders are automatically generated and sent to business personnel.
It realizes automatic processing of fund allocation, reduces labor costs, and improves the efficiency and reliability of generating fund allocation work orders.
Smart Images

Figure CN112766892B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, specifically to the fields of artificial intelligence (AI) and robotic process automation (RPA), and in particular to a method, device and electronic device for capital allocation combining RPA and AI. Background Art
[0002] Robotic Process Automation (RPA) uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules.
[0003] Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.
[0004] In the existing business, staff need to log in to the financial management system every day and review and process the items in the system in turn according to the contents of the paper documents. When the amount of data to be processed is large, it will take up a lot of manual time, and the efficiency of manual processing of fund allocation is not high. In addition, manual data operations are prone to misjudgment and the accuracy is also low. Summary of the invention
[0005] The method, device and electronic device for fund allocation combining RPA and AI proposed in this application are used to solve the problem in related technologies that manual processing of fund allocation is not only inefficient, but also prone to errors and has poor reliability.
[0006] The method for allocating funds by combining RPA and AI proposed in an embodiment of the present application includes:
[0007] Perform optical character recognition on the data sheets to be processed to generate electronic data sheets and corresponding business personnel;
[0008] Obtaining a data set to be verified corresponding to the data sheet to be processed in the financial management system;
[0009] According to the electronic data sheet, verifying the data corresponding to the specified type in the data set to be verified;
[0010] If the data corresponding to the specified type passes the verification, a fund matching work order is generated according to the data of the specified type;
[0011] The fund matching work order is sent to the business personnel.
[0012] Another aspect of the present application provides a device for combining RPA and AI for capital allocation, including:
[0013] The first generating module is used to perform optical character recognition on the data sheet to be processed to generate an electronic data sheet and corresponding business personnel;
[0014] An acquisition module, used for acquiring a data set to be verified corresponding to the data sheet to be processed in the financial management system;
[0015] A verification module, used for verifying data corresponding to a specified type in the data set to be verified according to the electronic data sheet;
[0016] A second generating module is used to generate a fund matching work order according to the data of the specified type when the data corresponding to the specified type passes the verification;
[0017] The first sending module is used to send the fund matching work order to the business personnel.
[0018] In another aspect of the present application, an electronic device is proposed in an embodiment, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method of capital allocation combining RPA and AI as described above is implemented.
[0019] In another aspect of the present application, a computer-readable storage medium is proposed in an embodiment, on which a computer program is stored, and it is characterized in that when the program is executed by a processor, the method of capital allocation combining RPA and AI as described above is implemented.
[0020] A computer program is proposed in another embodiment of the present application. When the program is executed by a processor, it can implement the method of capital allocation combining RPA and AI as described in the embodiment of the present application.
[0021] The method, device, and electronic device for capital allocation combined with RPA and AI provided in the embodiments of the present application have the following beneficial effects:
[0022] First, perform optical character recognition on the data sheet to be processed to generate an electronic data sheet and the corresponding business personnel. Then, obtain the data set to be verified corresponding to the data sheet to be processed in the financial management system, and verify the data corresponding to the specified type in the data set to be verified based on the electronic data sheet. When the data corresponding to the specified type passes the verification, generate a fund matching work order based on the data of the specified type, and send the fund matching work order to the business personnel. As a result, the RPA system can automatically perform OCR processing on the data sheet, and verify the data corresponding to the specified type in the data set to be verified in the financial management system based on the generated electronic data sheet. When the verification passes, the fund matching work order can be automatically generated and sent to the business personnel, thereby realizing the automatic processing of fund matching through RPA technology, which not only reduces labor costs, but also improves the efficiency and reliability of generating fund matching work orders.
[0023] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0025] Figure 1 A flowchart of a method for capital allocation combining RPA and AI provided in one embodiment of the present application;
[0026] Figure 2 A flowchart of a method for capital allocation combining RPA and AI provided in another embodiment of the present application;
[0027] Figure 3 A schematic diagram of the structure of a device for capital allocation combining RPA and AI provided in one embodiment of the present application;
[0028] Figure 4 A schematic diagram of the structure of a device for capital allocation combining RPA and AI provided in another embodiment of the present application;
[0029] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0030] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
[0031] In view of the problem in the related art that manual processing of fund allocation is not only inefficient but also prone to errors and has poor reliability, the embodiments of the present application propose a method for fund allocation that combines RPA and AI.
[0032] The method, device and electronic device for capital allocation combining RPA and AI provided in the present application are described in detail below with reference to the accompanying drawings.
[0033] The method for funds allocation combining RPA and AI in the embodiment of the present application can be executed by the device for funds allocation combining RPA and AI provided in the embodiment of the present application, and the device can be configured in an electronic device.
[0034] Figure 1 A flowchart of a method for capital allocation combining RPA and AI provided in an embodiment of the present application.
[0035] like Figure 1 As shown, the method of capital allocation combining RPA and AI includes the following steps:
[0036] Step 101, optical character recognition is performed on the data sheet to be processed to generate an electronic data sheet and corresponding business personnel.
[0037] The data sheet may be any type of paper data sheet, such as a printed document such as an invoice, or a handwritten document, and this application does not limit this.
[0038] It is understandable that the characters in the data sheet can be any type, such as Chinese characters, numbers, letters, etc., and this application does not limit this.
[0039] In addition, Optical Character Recognition (OCR) converts the text of various bills, newspapers, books, manuscripts and other printed materials into image information through optical input methods such as scanning, and then uses text recognition technology to convert the image information into usable computer input technology. It can be applied to the entry and processing of bank bills, large amounts of text materials, archive files, and documents. It is suitable for automatic scanning, recognition and long-term storage of large amounts of bills and forms in industries such as banking and taxation.
[0040] It is understandable that the RPA system can use AI's OCR technology to process paper data sheets to generate electronic data sheets and corresponding business personnel, and can also read and record relevant data information in the data sheets.
[0041] In addition, the business personnel may be the staff responsible for data review, or the relevant staff who handles fund allocation work, etc. This application does not limit this.
[0042] For example, if the type of the data sheet to be processed is electricity bill refund, the corresponding business person may be staff member A, or, if the type of the data sheet to be processed is employee reimbursement, the corresponding business person may be staff member B. Alternatively, the business person corresponding to any data sheet is staff member C.
[0043] It should be noted that the types of data sheets, staff members A, B, C, etc. mentioned above are merely illustrative and cannot be used as limitations on the data sheets to be processed and their types, corresponding business personnel, etc. in the embodiments of the present application.
[0044] It should be noted that RPA technology can intelligently understand the existing applications of the electronic device through the user interface, and automate repetitive, rule-based, and large-scale routine operations, such as automatically and repeatedly reading emails, reading Office components, operating databases and web pages, client software, etc., collecting data and performing tedious calculations to generate files and reports in large quantities, thereby greatly reducing the investment in labor costs and effectively improving office efficiency through RPA technology. Therefore, in the capital matching processing scenario, the RPA program can be configured in the electronic device used for capital matching, so that the electronic device can automatically perform optical character recognition on the data sheets to be processed according to the rules set in the RPA program to generate electronic data sheets and corresponding business personnel.
[0045] Step 102: Obtain the data set to be verified corresponding to the data sheet to be processed in the financial management system.
[0046] Among them, the financial management system can be a system for users to fill in the content of the data sheet to be processed, or it can also be any system for users to submit data sheet declarations, etc. This application does not limit this.
[0047] In addition, the data set to be verified may be the content of a data sheet filled in by a user in a financial management system, or may be information generated by the financial management system in combination with the content filled in by the user, etc. This application does not limit this.
[0048] It is understandable that when the RPA system searches for the data set to be verified corresponding to the data sheet to be processed in the financial management system, it can search through a variety of query methods. For example, it can search in the financial management system based on the data contained in the data sheet, or it can search in the financial management system based on the information such as the receiving unit contained in the data sheet, and this application does not limit this.
[0049] In the embodiment of the present application, after performing optical character recognition on the data sheet to be processed, the RPA system can obtain the data set to be verified corresponding to the data sheet to be processed in the financial management system, thereby reducing manual operations, saving time, and greatly improving efficiency.
[0050] Step 103: Verify the data corresponding to the specified type in the data set to be verified according to the electronic data sheet.
[0051] The specified type may be a payment type, or a payment type and a budget type, which is not limited in this application.
[0052] 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 can search for the data corresponding to the payment type in the acquired data set to be verified and compare it with 100.
[0053] Alternatively, the payment type in the electronic data sheet is 500, the budget type is 600, and the specified types are payment type and budget type. The RPA system can find the data corresponding to the payment type and budget type in the acquired data set to be verified, and compare the corresponding data with 500 and 600 respectively.
[0054] It should be noted that the above numerical values 100, 500, 600, etc. are only for illustrative purposes and cannot be used as limitations on the specified types and their corresponding data, data sets to be verified, etc. in the embodiments of the present application.
[0055] Step 104: When the data corresponding to the specified type passes verification, a fund allocation work order is generated according to the data of the specified type.
[0056] Among them, the fund allocation work order can be a work order automatically generated by the RPA system based on the specified type of data that has passed the verification.
[0057] For example, if the data corresponding to the payment type in the electronic data sheet is 200, the data corresponding to the payment type found by the RPA system in the data set to be verified is also 200, indicating that the data corresponding to the payment type has passed the verification. At this time, the RPA system can automatically generate a fund matching work order based on the 200 corresponding to the payment type.
[0058] Alternatively, the data corresponding to the payment type in the electronic data sheet is 300, and the data corresponding to the budget type is 700, and the specified types are payment type and budget type. The RPA system finds that the data corresponding to the payment type and budget type are 300 and 700 respectively in the acquired data set to be verified, indicating that the data corresponding to the specified type has passed the verification. At this time, the RPA system can automatically generate a fund allocation work order based on the data 300 corresponding to the payment type and the data 700 corresponding to the budget type.
[0059] It should be noted that the above numerical values 200, 300, 700, etc. are only for illustrative purposes and cannot be used as limitations on the data corresponding to the specified type, the data set to be verified, etc. in the embodiments of the present application.
[0060] Step 105: Send the fund allocation work order to the business personnel.
[0061] Among them, the RPA system can use multiple methods when sending fund allocation work orders to business personnel.
[0062] For example, the RPA system can send the fund allocation work order to the business personnel in the form of an email. Alternatively, the RPA system can also use the corresponding work system to send the fund allocation work order to the business personnel. Alternatively, the RPA system can also call the corresponding application software, such as DingTalk, WeChat, etc., to send the fund allocation work order to the business personnel.
[0063] It should be noted that the above-mentioned sending method is only an example and cannot be used as a limitation on sending the fund matching work order to the business personnel in the embodiment of the present application.
[0064] In the embodiment of the present application, optical character recognition is first performed on the data sheet to be processed to generate an electronic data sheet and the corresponding business personnel, and then the data set to be verified corresponding to the data sheet to be processed in the financial management system is obtained, and the data corresponding to the specified type in the data set to be verified can be verified according to the electronic data sheet, so that when the data corresponding to the specified type passes the verification, a fund matching work order is generated according to the data of the specified type, and the fund matching work order is sent to the business personnel. Thus, the RPA system can automatically perform OCR processing on the data sheet, and 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. When the verification passes, the fund matching work order can be automatically generated and sent to the business personnel, thereby realizing the automatic processing of fund matching through RPA technology, which not only reduces labor costs, but also improves the efficiency and reliability of generating fund matching work orders.
[0065] In the above embodiment, the RPA system can automatically process the data sheet, and verify the data corresponding to the specified type in the data set to be verified in the financial management system based on the generated electronic data sheet. When the verification passes, the capital matching work order can be automatically generated and sent to the business personnel. From the above analysis, it can be seen that the data sheet to be processed may contain numbers and letters. When the RPA system recognizes the data sheet, it can recognize the character based on at least two distance values between the center point of the character to be recognized and at least two boundary points. Figure 2 The above process is described in detail.
[0066] 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.
[0067] Among them, different characters may have the same or different first probabilities of numbers and second probabilities of letters, and this application does not limit this.
[0068] For example, a character in the data sheet to be processed may have a first probability of being a number of 0.8, and a second probability of being a letter of 0.1.
[0069] Alternatively, a character in the data sheet to be processed may have a first probability of being a number of 0.6, and a second probability of being a letter of 0.6.
[0070] It should be noted that the above characters, first probabilities of 0.8, 0.6, second probabilities of 0.1, 0.6, etc. are merely illustrative and cannot be used as limitations on the first probability of each character being a number and the second probability of being a letter in the embodiments of the present application.
[0071] Step 202: when the difference between the first probability and the second probability corresponding to any character is less than a threshold, determine at least two distance values between the center point of any character and at least two boundary points.
[0072] The threshold value may be any pre-set value, which is not limited in this application.
[0073] For example, the threshold is 0.2, the first probability of any character being a number is 0.6, and the second probability of being a letter is 0.5. The difference between the two is 0.1, which is less than the threshold 0.2. At this time, at least two distance values between the center point of any character and at least two boundary points can be further determined.
[0074] It should be noted that the above characters 0, 0.2, 0.6, 0.5, 0.1, etc. are only schematic illustrations and cannot be used as limitations on the characters, first probability, second probability, threshold, etc. in the embodiments of the present application.
[0075] Step 203: Determine the type of any character according to at least two distance values.
[0076] Among them, the candidate numbers and / or candidate letters corresponding to any character can be determined first, and then at least two target distance values corresponding to any character can be determined based on the candidate numbers and / or candidate letters, and then the type of any character can be determined based on at least two target distance values and at least two distance values.
[0077] For example, the probability of any character being recognized as a candidate number "0" is 0.7, and the probability of being recognized as a candidate letter "o" is 0.68, and the two distance values between its center point and two boundary points are 0.7 and 0.4 respectively, while the two target distance values of the candidate number "0" are 0.6 and 0.4 respectively, and the two target distance values of the candidate letter "o" are 0.5 and 0.5 respectively. Therefore, according to the relationship between the target distance value and the distance value, it can be determined that any character is the number 0.
[0078] Alternatively, the probability of any character being recognized as the candidate number "2" is 0.87, the probability of being recognized as the candidate letter "z" is 0.86, and the two distances between its 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. Thus, according to the relationship between the target distance value and the distance value, it can be determined that any character is the letter z.
[0079] It should be noted that the above examples are merely illustrative and cannot be used as a limitation on the type of any character determined in the embodiments of the present application.
[0080] In an embodiment of the present application, when the RPA system identifies the data sheet to be processed, it can accurately identify the character based on at least two distance values between the center point of the character to be identified and at least two boundary points, thereby further improving the accuracy of the recognition result.
[0081] Step 204: Obtain the data set to be verified corresponding to the data sheet to be processed in the financial management system.
[0082] Step 205 , based on the electronic data sheet, verify the business party name, financial institution name, and business-related account of the data corresponding to the specified type in the data set to be verified.
[0083] Among them, the name of the business party can be the receiving unit, or it can also be the unit or individual that issues the document, etc. The financial institution can be a bank, insurance company, etc. The business-related account can be the receiving account, or it can also be the account corresponding to the unit or individual that issues the document, etc. This application does not limit this.
[0084] For example, in the data set to be verified obtained by the RPA system, the business party name corresponding to the specified type of data may be AAA, the financial institution may be Beijing XX Bank, and the business-related account may be ABC. Then they are compared one by one with the corresponding business party name, financial institution, and business-related account in the electronic data sheet to verify whether they are consistent.
[0085] It should be noted that the above-mentioned business party name AAA, financial institution Beijing XX Bank, business-related account ABC, etc. are only exemplary illustrations and cannot be used as a limitation on the business party name, financial institution name, and business-related account in the embodiment of the present application.
[0086] Step 206 , when the business-associated account of any data corresponding to the specified type in the electronic data sheet does not match the business-associated account of the corresponding data in the data set to be verified, detect multiple business-associated accounts corresponding to any data in the electronic data sheet.
[0087] Step 207 : if the multiple business-related accounts include a business-related account for any data in the data set to be verified, determine that any data has passed the verification.
[0088] For example, the RPA system may match three electronic data sheets A, B, and C based on any data in the data set to be verified. The business-related account in any data is XX, and the business-related account in electronic data sheet A is YY. At this time, the two do not match. You can further compare whether XX matches the business-related accounts in electronic data sheets B and C. If the business-related accounts in electronic data sheets B and C are both XX, and they match the business-related accounts in any data, you can continue to compare whether the financial institution names in electronic data sheets B and C are consistent with the financial institution names in any data. If the financial institution name of electronic data sheet C is also consistent with that of any data, you can continue to determine whether its business party name is consistent with that of any data. If they are consistent, you can determine that any data has passed the verification.
[0089] It should be noted that the above-mentioned data records, electronic data sheets A, B, C, business-related accounts XX, YY, etc. are only schematic illustrations and cannot be used as limitations for verifying any data in the data set to be verified in the embodiments of the present application.
[0090] Step 208: When the data corresponding to the specified type passes verification, a fund allocation work order is generated according to the data of the specified type.
[0091] Step 209: Send the fund allocation work order to the business personnel.
[0092] Step 210: If any data corresponding to the specified type fails to pass the verification, any data is added to a preset abnormal data list.
[0093] Among them, the abnormal data list can store abnormal data and its corresponding information, such as the name of the business party, the name of the financial institution, the business-related account, etc., which is not limited in this application.
[0094] For example, if the data 200 corresponding to the payment type fails verification, 200 and its corresponding business party name, financial institution name, business-related account and other information may be added to a preset abnormal data list.
[0095] It should be noted that the above-mentioned payment type, data 200, etc. are only schematic illustrations and cannot be used as a limitation on adding any data to the preset abnormal data list in the embodiments of the present application.
[0096] Step 211, sending the abnormal data list to the business personnel.
[0097] Among them, when the RPA system sends the list of abnormal data to business personnel, there are many ways, such as email, DingTalk, WeChat, etc., and this application does not limit this.
[0098] It is understandable that when business personnel receive the list of abnormal data sent by the RPA system, they can also verify the data therein to ensure the accuracy and completeness of the data.
[0099] The following is a detailed explanation of the capital allocation process of the RPA system in the XXX system of XX company as an example.
[0100] The RPA system can automatically perform optical character recognition on the data sheets to be processed to generate electronic data sheets and corresponding business personnel. It can be understood that the data sheets to be processed may include a variety of information such as document number, document name, payment amount, and receiving account.
[0101] After that, the RPA system can automatically enter the funds allocation payment interface.
[0102] It is understandable that the funds allocation payment interface may be different in different systems and scenarios. For example, in some scenarios, you can select the type of business to be processed, such as [Business Type] = All; [Budget Period] = Current (i.e. the month of the current system date); [Processing Status] = All; [Records Displayed Per Page] = 2000.
[0103] The RPA system can click [Apply for Payment Amount] in the fund matching payment interface to obtain the data set to be verified corresponding to the data sheet to be processed. After that, the data corresponding to the specified type in the data set to be verified can be verified based on the electronic data sheet, and the verified data and related information can be displayed on the page.
[0104] The specified type can be [Payment], or [Payment] and [Budget]. Different systems may have different settings. For example, in the current system, the specified type is [Payment].
[0105] In addition, there may be multiple situations in the data set to be verified. For example, if there is no amount value, it can be recorded in the exception record table; or, if the amount value is the same, but the name of the receiving account is inconsistent, it can be recorded in the exception record table; there may also be a situation where the amount value is the same, the receiving account name is the same, and the [Type] is [Budget], in which case the [Document Number], [Document Name], [Payment Amount], [Exception Reason], etc. can be recorded in the exception record table; or, there may be multiple data records with the same amount value, the same receiving account name, and the type of [Payment]. In some scenarios, for multiple matching data records, you can continue to check whether the [Payment Plan Number] meets the conditions. If the [Payment Plan Number] meets the conditions, the data that meets the conditions and its related information will be displayed on the page. If it does not meet the conditions, the data will be added to the exception record table; or if there is only one data with the same amount, the same receiving account name, and the type of [Payment], the data and its related information will be directly displayed on the page.
[0106] It is understandable that in some scenarios, the data displayed on the page can be further judged. For example, it can be further judged whether the [Allocation Identifier] meets the conditions. If the [Allocation Identifier] meets the conditions, the payment information payment verification phase will begin; if the [Allocation Identifier] does not meet the conditions, the document will not be processed, and the corresponding [Document Number], [Document Name], [Payment Amount], [Exception Reason], etc. can be added to the exception record table.
[0107] After that, the RPA system can compare the [payee unit], [payee account number], and [name of bank account] in the data record of the fund matching interface with the [payee unit], [payee account number], and [name of bank account] in the electronic data sheet. If they are consistent, the system proceeds to the next step. If they are inconsistent, the system determines whether there are multiple payee accounts. There may be multiple payee bank accounts identified from the electronic data sheet. If it is one of them, the legal data is assumed. If it is not one of them, the illegal data is assumed. The document is not approved and the abnormal data is recorded in the abnormal record table. In addition, in some scenarios, there may be multiple business types, or there may be only one. For example, the RPA system can determine that the current business type is electricity bill refund based on the words "electricity bill refund" contained in the recognition result. Alternatively, the RPA system can determine that the current business type is employee reimbursement based on the words "business trip" and "taxi" contained in the recognition result. Alternatively, the RPA system can determine that the current business type is SSS based on other key words contained in the recognition result.
[0108] Different users may have different requirements. For example, the operator may be modified according to different business types. For example, for the XYY system, if the [Business Type] is [Electricity Bill Refund], the default fixed operator is [DD]; or if the [Business Type] is [Employee Reimbursement], the operator can be the name of the person in the fund matching payment.
[0109] After a series of checks, RPA can click [Match Payment] on the page to complete the operation and generate a corresponding fund matching work order, which can also be sent to the corresponding business personnel. Alternatively, the RPA system can also send the exception record table to the corresponding business personnel.
[0110] In some scenarios, the RPA system can also record the current matching payment. For example, it can obtain the [payment plan number] and write it back to the WW table, marking it as "payment plan number [system]".
[0111] It is understandable that the situation that occurs when you click [Matching Payment] may be different depending on the data sheet. For example, it may prompt duplicate payment, and if there is a pop-up window with the same [Receiving Account], [Amount], and [Receiving Unit], including payments made in previous months, you need to click [Confirm] at this time; or, it may prompt that the budget has not been released, and the data will be recorded in the exception record table; or, it may also prompt that the budget is exceeded, and the matching payment will fail, and the data can be recorded in the exception record table; or, other situations may occur, etc.
[0112] It should be noted that the above-mentioned fund matching payment interface, page format, page information, various windows, etc. are only examples. When used in specific situations, they can be modified according to actual conditions and cannot be used as a limitation on the fund matching process interface, content, etc. in this application.
[0113] In the embodiment of the present application, when the RPA system identifies the data sheet, it can identify the character based on at least two distance values between the center point of the character to be identified and at least two boundary points, and then verify the business party name, financial institution name, and business-related account of the data corresponding to the specified type in the data set to be verified according to the electronic data sheet, and automatically send the generated fund matching work order to the business personnel when the data corresponding to the specified type passes the verification, or automatically send the abnormal data list to the business personnel when it fails the verification. As a result, the RPA system can accurately identify the numbers and letters in the data sheet that are difficult to distinguish, and can also accurately verify different matching situations in the electronic data sheet, and send corresponding information to the business personnel according to different verification results, thereby further improving the accuracy and reliability of the fund matching processing.
[0114] In order to implement the above embodiments, the present application also proposes a device for capital allocation combining RPA and AI.
[0115] Figure 3 A schematic diagram of the structure of a device for capital allocation combining RPA and AI provided in an embodiment of the present application.
[0116] like Figure 3 As shown, the device 300 for capital allocation combining RPA and AI includes: a first generating module 310, an acquiring module 320, a verifying module 330, a second generating module 340, and a first sending module 350.
[0117] The first generating module 310 is used to perform optical character recognition on the data sheet to be processed to generate an electronic data sheet and corresponding business personnel.
[0118] The acquisition module 320 is used to acquire the data set to be verified corresponding to the data sheet to be processed in the financial management system.
[0119] The verification module 330 is used to verify the data corresponding to the specified type in the data set to be verified according to the electronic data sheet.
[0120] The second generating module 340 is used to generate a fund matching work order according to the data of the specified type when the data corresponding to the specified type passes the verification.
[0121] The first sending module 350 is used to send the fund matching work order to the business personnel.
[0122] It should be noted that the functions and specific implementation principles of the above-mentioned modules in the embodiments of the present application can be referred to the above-mentioned method embodiments and will not be repeated here.
[0123] The device for capital matching that combines RPA and AI provided in the embodiment of the present application first performs optical character recognition on the data sheet to be processed to generate an electronic data sheet and the corresponding business personnel, and then obtains the data set to be verified corresponding to the data sheet to be processed in the financial management system, and can verify the data corresponding to the specified type in the data set to be verified according to the electronic data sheet, so that when the data corresponding to the specified type passes the verification, a capital matching work order is generated according to the data of the specified type, and the capital matching work order is sent to the business personnel. Thus, the RPA system can automatically perform OCR processing on the data sheet, and 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. When the verification passes, a capital matching work order can be automatically generated and sent to the business personnel, thereby realizing the automatic processing of capital matching through RPA technology, which not only reduces labor costs, but also improves the efficiency and reliability of generating capital matching work orders.
[0124] As a possible implementation method of the embodiment of the present application, Figure 4 As shown, in Figure 3 On the basis shown, the device for capital allocation combining RPA and AI also includes: an adding module 360 and a second sending module 370.
[0125] In a possible implementation, the first generating module 310 includes:
[0126] A first determining unit 3110, configured to determine 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;
[0127] 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 the first probability and the second probability corresponding to any character is less than a threshold;
[0128] The third determining unit 3130 is configured to determine the type of any one character according to the at least two distance values.
[0129] In one possible implementation, the third determination unit 3130 is specifically used to: determine candidate numbers and / or candidate letters corresponding to any character; determine at least two target distance values corresponding to any character based on the candidate numbers and / or candidate letters; and determine the type of any character based on the at least two target distance values and the at least two distance values.
[0130] In a possible implementation, the verification module 330 is specifically used to verify the business party name, financial institution name, and business-related account of the data corresponding to the specified type in the data set to be verified, according to the electronic data sheet.
[0131] In a possible implementation, the verification module 330 is further specifically used to: if the business-associated account of any data corresponding to the specified type in the electronic data sheet does not match the business-associated account of the corresponding data in the data set to be verified, detect multiple business-associated accounts corresponding to the any data in the electronic data sheet; if the multiple business-associated accounts include a business-associated account for the any data in the data set to be verified, determine that the any data has passed the verification.
[0132] The adding module 360 is used to add any data corresponding to the specified type to a preset abnormal data list when the data fails to pass the verification.
[0133] The second sending module 370 is used to send the abnormal data list to the business personnel.
[0134] It should be noted that the functions and specific implementation principles of the above-mentioned modules in the embodiments of the present application can be referred to the above-mentioned method embodiments and will not be repeated here.
[0135] The device for capital matching that combines RPA and AI provided in the embodiment of the present application can identify the character based on at least two distance values between the center point of the character to be identified and at least two boundary points when the RPA system identifies the data sheet, and then verify the business party name, financial institution name, and business-related account of the data corresponding to the specified type in the data set to be verified according to the electronic data sheet, and automatically send the generated capital matching work order to the business personnel when the data corresponding to the specified type passes the verification, or automatically send the abnormal data list to the business personnel when it fails the verification. As a result, the RPA system can accurately identify the numbers and letters in the data sheet that are difficult to distinguish, and can also accurately verify different matching situations in the electronic data sheet, and send corresponding information to the business personnel according to different verification results, thereby further improving the accuracy and reliability of the capital matching processing.
[0136] In order to implement the above embodiments, the present application also proposes an electronic device.
[0137] Figure 5 A schematic diagram of the structure of an electronic device for a method of funds allocation combining RPA and AI according to an embodiment of the present application.
[0138] like Figure 5As shown, the electronic device 200 includes:
[0139] The memory 210 and the processor 220, a bus 230 connecting different components (including the memory 210 and the processor 220), the memory 210 stores a computer program, and when the processor 220 executes the program, the method of capital allocation combining RPA and AI described in the embodiment of the present application is implemented.
[0140] Bus 230 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, 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.
[0141] The electronic device 200 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by the electronic device 200, including volatile and non-volatile media, removable and non-removable media.
[0142] The 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 / non-volatile computer system storage media. By way of example only, the storage system 260 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to bus 230 via one or more data medium 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 perform the functions of the various embodiments of the present application.
[0143] A program / utility 280 having a set (at least one) of program modules 270 may be stored, for example, in the memory 210, such 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 may include an implementation of a network environment. The program modules 270 generally perform the functions and / or methods of the embodiments described herein.
[0144] The electronic device 200 may also communicate with one or more external devices 290 (e.g., keyboard, pointing device, display 291, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 200, and / or communicate with any device that enables the electronic device 200 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via an input / output (I / O) interface 292. Furthermore, the electronic device 200 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) via a network adapter 293. As shown, the network adapter 293 communicates with other modules of the electronic device 200 via a bus 230. It should be understood that, although not shown in the figure, 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.
[0145] The processor 220 executes various functional applications and data processing by running the programs stored in the memory 210 .
[0146] It should be noted that the implementation process and technical principles of the electronic device of this embodiment refer to the aforementioned explanation of the method of capital allocation combining RPA and AI in the embodiment of the present application, and will not be repeated here.
[0147] The electronic device provided in the embodiment of the present application first performs optical character recognition on the data sheet to be processed to generate an electronic data sheet and the corresponding business personnel, and then obtains the data set to be verified corresponding to the data sheet to be processed in the financial management system, and can verify the data corresponding to the specified type in the data set to be verified according to the electronic data sheet, so that when the data corresponding to the specified type passes the verification, a fund matching work order is generated according to the data of the specified type, and the fund matching work order is sent to the business personnel. Thus, the RPA system can automatically perform OCR processing on the data sheet, and 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. When the verification passes, the fund matching work order can be automatically generated and sent to the business personnel, thereby realizing the automatic processing of fund matching through RPA technology, which not only reduces labor costs, but also improves the efficiency and reliability of generating fund matching work orders.
[0148] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium.
[0149] Among them, the computer-readable storage medium stores a computer program, and when the program is executed by the processor, it implements the method of capital allocation combining RPA and AI as described in the embodiment of the present application.
[0150] In order to implement the above-mentioned embodiments, another embodiment of the present application provides a computer program, which, when executed by a processor, implements the method of capital allocation combining RPA and AI as described in the embodiments of the present application.
[0151] In an optional implementation form, this embodiment can use any combination of one or more computer-readable media. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.
[0152] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0153] 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.
[0154] Computer program code for performing the operation of the present application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user electronic device, partially on the user electronic device, as an independent software package, partially on the user electronic device and partially on the remote electronic device, or entirely on the remote electronic device or server. In the case of a remote electronic device, the remote electronic device can be connected to the user electronic device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external electronic device (e.g., using an Internet service provider to connect through the Internet).
[0155] According to the technical solution of the present application, firstly, optical character recognition is performed on the data sheet to be processed to generate an electronic data sheet and the corresponding business personnel, and then the data set to be verified corresponding to the data sheet to be processed in the financial management system is obtained, and the data corresponding to the specified type in the data set to be verified can be verified according to the electronic data sheet, so that when the data corresponding to the specified type passes the verification, a fund matching work order is generated according to the data of the specified type, and the fund matching work order is sent to the business personnel. Thus, the RPA system can automatically perform OCR processing on the data sheet, and 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. When the verification passes, the fund matching work order can be automatically generated and sent to the business personnel, thereby realizing the automatic processing of fund matching through RPA technology, which not only reduces labor costs, but also improves the efficiency and reliability of generating fund matching work orders.
[0156] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the inventions claimed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary techniques in the art that are not invented by the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.
[0157] It should be understood that the present application is not limited to the precise structures that have been 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 present application is limited only by the appended claims.
Claims
1. A method for capital matching combining RPA and AI, characterized in that: include: S1. The Robotic Process Automation system (RPA) uses the optical character recognition (OCR) technology of artificial intelligence (AI) to recognize each character in the paper data sheet to be processed based on the distance value between the center point of the character to be recognized and at least two boundary points, so as to generate an electronic data sheet and the corresponding business personnel; S2. After the robotic process automation system RPA identifies the paper data sheet to be processed, it obtains a data set to be verified corresponding to the paper data sheet to be processed in the financial management system; S3. Verify the business-associated account of the data corresponding to the specified type in the data set to be verified according to the electronic data sheet. If the business-associated account of any data corresponding to the specified type in the electronic data sheet does not match the business-associated account of the corresponding data in the data set to be verified, detect multiple business-associated accounts corresponding to the any data in the electronic data sheet. If the multiple business-associated accounts include the business-associated account of the any data in the data set to be verified, determine that the any data has passed the verification. S4. If the data corresponding to the specified type passes the verification, a fund matching work order is generated according to the data of the specified type; S5. Sending the fund matching work order to the business personnel; The paper data sheet to be processed contains numbers and letters, and S1 includes: S11, determining a first probability that each character in the paper data sheet to be processed is a number and a second probability that each character is a letter; S12, when the difference between the first probability and the second probability corresponding to any character is less than a threshold, determining at least two distance values between the center point of any character and at least two boundary points; S13, determining candidate numbers and / or candidate letters corresponding to the any character, determining at least two target distance values corresponding to the any character according to the candidate numbers and / or candidate letters, and determining the type of the any character according to the at least two target distance values and the at least two distance values; The method also includes: when the data corresponding to the specified type fails to pass the verification, any data is added to a preset abnormal data list, the abnormal data list is sent to the business personnel, and the fund matching payment interface is automatically entered so that the business personnel can verify the data therein, wherein the specified type includes payment type 1 and / or budget type.
2. The method according to claim 1, characterized in that The S3 further includes: verifying the business party name and the financial institution name of the data corresponding to the specified type in the data set to be verified respectively according to the electronic data sheet.
3. The method according to claim 1 or 2, characterized in that After S3, it also includes: S6. If any data corresponding to the specified type fails to pass the verification, the data is added to a preset abnormal data list; S7. Send the abnormal data list to the business personnel.
4. A device for capital matching combining RPA and AI, characterized in that: include: The first generation module is used for the robotic process automation system RPA to use the optical character recognition (OCR) technology of artificial intelligence (AI) to recognize each character in the paper data sheet to be processed based on the distance value between the center point of the character to be recognized and at least two boundary points, so as to generate an electronic data sheet and the corresponding business personnel; An acquisition module, used for acquiring, after the robotic process automation system (RPA) process automation system (RPA) identifies the paper data sheet to be processed, a data set to be verified corresponding to the paper data sheet to be processed in the financial management system; a verification module, configured to verify the business-associated account of the data corresponding to the specified type in the data set to be verified according to the electronic data sheet, and if the business-associated account of any data corresponding to the specified type in the electronic data sheet does not match the business-associated account of the corresponding data in the data set to be verified, detect multiple business-associated accounts corresponding to the any data in the electronic data sheet, and if the multiple business-associated accounts include the business-associated account of the any data in the data set to be verified, determine that the any data passes the verification; A second generating module is used to generate a fund matching work order according to the data of the specified type when the data corresponding to the specified type passes the verification; A first sending module, used to send the fund matching work order to the business personnel; The paper data sheet to be processed contains numbers and letters, and the first generating module includes: A first determination unit, used to determine a first probability that each character in the paper data sheet to be processed is a number and a second probability that each character is a letter; A second determining unit, 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 the first probability and the second probability corresponding to any character is less than a threshold; A third determining unit is used to determine candidate numbers and / or candidate letters corresponding to the any character, determine at least two target distance values corresponding to the any character according to the candidate numbers and / or candidate letters, and determine the type of the any character according to the at least two target distance values and the at least two distance values; The device also includes: when the data corresponding to the specified type fails to pass the verification, any data is added to a preset abnormal data list, the abnormal data list is sent to the business personnel, and the fund matching payment interface is automatically entered so that the business personnel can verify the data therein, wherein the specified type includes payment type 1 and / or budget type.
5. The device according to claim 4, characterized in that The verification module is further used for: According to the electronic data sheet, the business party name and the financial institution name of the data corresponding to the specified type in the data set to be verified are verified respectively.
6. The device according to claim 4 or 5, characterized in that Also includes: An adding module, used for adding any data corresponding to the specified type to a preset abnormal data list if the data fails to pass the verification; The second sending module is used to send the abnormal data list to the business personnel.
7. An electronic device, characterized in that: include: A memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for capital allocation combining RPA and AI as described in any one of claims 1 to 3 is implemented.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for capital matching combining RPA and AI as described in any one of claims 1 to 3 is implemented.
