RPA-based business travel automatic monthly settlement method, device and equipment

Abstract

The invention relates to the field of artificial intelligence, and discloses an RPA-based business travel automatic monthly settlement method, device and equipment, and the method comprises the steps: automatically obtaining business travel data through robot process automation RPA, and carrying out the analysis of the business travel data, so as to obtain a first cost item and corresponding amount information; performing OCR image recognition and logic reconstruction on the archived report to obtain a second cost item and corresponding amount information; and judging a logical relationship and an arithmetic relationship between the first cost item and the corresponding second cost item, and judging whether omission or inconsistency exists or not. According to the method, the workload of manual checking is reduced, the efficiency of the reimbursement process is remarkably improved, meanwhile, the accuracy and integrity of the reimbursement data are enhanced, and the risk of human errors is reduced.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method, device and equipment for automated monthly settlement of business travel based on RPA. Background Art

[0002] At present, travel expense reimbursement is one of the important links in the financial management of various enterprises and organizations, which usually involves a lot of manual operations and data processing. In the traditional travel expense reimbursement process, travelers need to submit reimbursement applications manually, and financial personnel need to check, verify and approve the reimbursement documents one by one. This process usually includes multiple manual operations, such as logging into the business travel system, extracting relevant travel data, generating reimbursement documents, and verifying relevant bills and expenses. This process is not only time-consuming and labor-intensive, but also prone to human errors.

[0003] The manual processing of travel reimbursements faces problems such as low efficiency, prone to errors, and high costs. First, the collection and organization of data requires staff to perform complex operations such as data extraction, classification, and calculation between various systems, which can easily lead to data loss or format errors. Secondly, the manual verification and validation process is complicated, and it is easy to miss certain reimbursement documents or double-count processed travel expenses. In addition, since the process is time-consuming and it is impossible to feedback and process reimbursement applications in real time, financial reimbursement work may lag behind actual business needs. Summary of the invention

[0004] In view of this, the present application provides an RPA-based business travel automated monthly settlement method to solve the technical problems in the prior art.

[0005] According to a first aspect of the present application, a business travel automated monthly settlement method based on RPA is provided, comprising:

[0006] Automatically obtain business travel data through Robotic Process Automation (RPA) and parse the business travel data to obtain the first expense item and the corresponding amount information;

[0007] Perform OCR image recognition and logic reconstruction on the archived reimbursement vouchers to obtain the second expense item and the corresponding amount information;

[0008] Determine the logical and arithmetic relationship between the first expense item and the corresponding second expense item, and determine whether there is any omission or inconsistency;

[0009] When it is determined that there is omission in the second expense item, the relevant personnel are notified to supplement it; when it is determined that the first expense item is inconsistent with the corresponding second expense item, the relevant personnel are notified to modify it.

[0010] According to a second aspect of the present application, a business travel automated monthly settlement device based on RPA is provided, comprising:

[0011] A first acquisition module, used to automatically acquire business travel data through robotic process automation (RPA), and parse the business travel data to acquire a first expense item and corresponding amount information;

[0012] The second acquisition module is used to perform OCR image recognition and logic reconstruction on the archived reimbursement vouchers to obtain the second expense item and the corresponding amount information;

[0013] A judgment module, used to judge the logical relationship and arithmetic relationship between the first expense item and the corresponding second expense item, and to judge whether there is any omission or inconsistency;

[0014] The notification module is used to notify relevant personnel to supplement when it is determined that there is an omission in the second expense item; when it is determined that the first expense item is inconsistent with the corresponding second expense item, notify relevant personnel to modify it.

[0015] According to a third aspect of the present application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned RPA-based business travel automated monthly settlement method are implemented.

[0016] According to a fourth aspect of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned RPA-based business travel automated monthly settlement method are implemented.

[0017] By means of the above technical scheme, the present application provides a method, device, equipment and medium for automated monthly settlement of business travel based on RPA, which automatically obtains business travel data through robotic process automation RPA, parses the business travel data to obtain the first expense item and the corresponding amount information; performs OCR image recognition and logical reconstruction on the archived reimbursement vouchers to obtain the second expense item and the corresponding amount information; judges the logical relationship and arithmetic relationship between the first expense item and the corresponding second expense item, and judges whether there is an omission or inconsistency; when it is judged that the second expense item is missing, notifies the relevant personnel to supplement it; when it is judged that the first expense item is inconsistent with the corresponding second expense item, notifies the relevant personnel to modify it. The automated monthly settlement method for business travel based on RPA provided by the present invention not only reduces the workload of manual verification and significantly improves the efficiency of the reimbursement process, but also enhances the accuracy and completeness of the reimbursement data, reduces the risk of human errors, and realizes the automation and intelligence of accounting and monthly settlement reconciliation.

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application and to implement it in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 A schematic diagram of an application scenario of an RPA-based business travel automated monthly settlement method provided in an embodiment of the present application is shown;

[0021] Figure 2 A schematic diagram of a process of an RPA-based business travel automated monthly settlement method provided in an embodiment of the present application is shown;

[0022] Figure 3 A schematic diagram of a process for automatically acquiring business travel data through RPA provided in an embodiment of the present application is shown;

[0023] Figure 4 A schematic diagram of a method flow for performing OCR image recognition and logic reconstruction on archived reimbursement invoices provided in an embodiment of the present application is shown;

[0024] Figure 5 A schematic diagram of a method flow for improving OCR image recognition of archived reimbursement invoices provided in an embodiment of the present application is shown;

[0025] Figure 6 A structural schematic diagram of an RPA-based business travel automation monthly settlement device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The specific implementation of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0027] An RPA-based business travel automated monthly settlement method provided in an embodiment of the present invention can be applied to Figure 1 In the reimbursement and reconciliation scenario of business trip documents shown, the enterprise digital business travel automated monthly settlement (referred to as "monthly settlement") process usually involves multiple steps from travel data collection, reimbursement document generation to review, reconciliation and settlement. The complete process is divided into business trip application, business travel reservation, reimbursement document filling, review / approval, accounting / monthly reconciliation and tax invoice entry.

[0028] Business trip application: Before going on a business trip, business travelers need to submit a business trip application through the company's internal system and fill in relevant information such as the purpose, time, and location of the business trip. The system will review the business trip application according to the company's travel policy.

[0029] Business travel reservation: After the business trip application is approved, the traveler can book business travel services through the system, such as air tickets, hotels, etc. The business travel reservation data generated in this step, including transportation and accommodation cost information, will serve as an important basis for reimbursement verification.

[0030] Filling in reimbursement documents: After the business trip is completed, the traveler needs to fill in the reimbursement document and submit the reimbursement application. At this time, the business travel reservation information and the actual expenses incurred will be automatically retrieved by the system for preliminary data filling in reimbursement. The RPA robot will automatically extract the corresponding expense data from the business travel reservation and generate a preliminary reimbursement document.

[0031] Review / Approval: After filling out the reimbursement document, the finance department or relevant approval personnel will review the travel expense reimbursement application. In this process, the system automatically compares the business travel reservation expenses with the actual expenses recorded in the reimbursement document through intelligent verification technology to check whether there are any inconsistencies in the amount or data omissions. If there are any problems, the system will automatically mark them and notify the traveler to make modifications or supplements.

[0032] Monthly reconciliation: All approved reimbursement documents are summarized to generate the monthly settlement general ledger. The system will summarize the expenses by department, project or business unit, and generate the corresponding monthly report. The summary report includes the details of each employee's business trip expenses, the total amount of various expenses, the location and number of days of the business trip, etc. The system automatically reconciles the business travel expense data with the bill data in the financial system to ensure that each expense is correctly recorded in the financial accounts. During the reconciliation process, it is necessary to check the completeness, consistency and accuracy of the expenses and identify any non-compliant items. If abnormal entries are found (such as over-recording or omission), the system will automatically generate a report and notify the financial staff to handle it.

[0033] Tax invoice entry: After the review is passed, the traveler enters the invoice related to the actual expenses into the system. After the invoice is scanned, the OCR technology is used for text recognition, and the expense-related information is automatically extracted. The logic is reconstructed through the finite state machine, and the recognition results are matched with the data in the reimbursement document.

[0034] Through this automated travel expense reimbursement verification process, enterprises can reduce the workload of manual processing, improve the efficiency and accuracy of the reimbursement process, and monitor data problems in the reimbursement process in real time to ensure the transparency and reliability of the financial reimbursement process. The present invention optimizes the process of accounting / monthly reconciliation by providing an RPA-based business travel automated monthly settlement method, automatically obtains business travel data through robotic process automation RPA (Robotic Process Automation), and parses the business travel data to obtain the first expense item and the corresponding amount information; performs OCR (Optical Character Recognition) image recognition and logical reconstruction on the archived reimbursement vouchers to obtain the second expense item and the corresponding amount information; judges the logical relationship and arithmetic relationship between the first expense item and the corresponding second expense item, and judges whether there is omission or inconsistency; when it is judged that the second expense item is missing, notifies the relevant personnel to supplement; when it is judged that the first expense item is inconsistent with the corresponding second expense item, notifies the relevant personnel to modify. The system automatically extracts travel-related expense data (i.e., the first expense item) from the business travel system through RPA technology, including detailed information on air tickets, hotels, transportation, and other expenses. This process no longer requires manual intervention. RPA can efficiently obtain and parse this data and structure the corresponding expense information for subsequent reconciliation and verification. For archived reimbursement bills, the system uses OCR technology for image recognition to automatically extract information such as expense items and amounts in the bills (i.e., the second expense item). At the same time, the recognition results are logically reconstructed with the help of finite state machines to ensure that the context and logical relationship of the bill content can be accurately parsed. This reconstruction ensures the correct recognition of complex bill content, such as the relationship between the business trip location, expense type, and amount. The system automatically determines the logical and arithmetic relationship between the first expense item extracted from the business travel data and the second expense item identified in the reimbursement bill through intelligent algorithms. This step includes checking whether there are duplications, omissions, or inconsistent amounts. When the system determines that the second expense item is missing, it will automatically generate an exception report and notify the relevant travelers to supplement the reimbursement materials or bills. When the system finds that there is an inconsistency in the amount or other anomalies between the first expense item and the second expense item, it automatically notifies the relevant personnel to modify the reimbursement application to ensure the accuracy of the reimbursement amount and content. The RPA-based business travel automated monthly settlement method provided by the present invention not only reduces the workload of manual verification and significantly improves the efficiency of the reimbursement process, but also enhances the accuracy and completeness of the reimbursement data, reduces the risk of human error, and realizes the automation and intelligence of accounting and monthly settlement reconciliation.

[0035] The present invention is described in detail below through specific embodiments.

[0036] Embodiment 1:

[0037] like Figure 2 As shown, an RPA-based business travel automated monthly settlement method provided in an embodiment of the present invention includes:

[0038] Step 201: automatically obtain business travel data through Robotic Process Automation (RPA), and parse the business travel data to obtain a first expense item and corresponding amount information;

[0039] Step 202: Perform OCR image recognition and logic reconstruction on the archived reimbursement voucher to obtain the second expense item and the corresponding amount information;

[0040] Step 203: determine the logical relationship and arithmetic relationship between the first expense item and the corresponding second expense item, and determine whether there is any omission or inconsistency;

[0041] Step 204: when it is determined that there is omission in the second expense item, notify the relevant personnel to supplement it; when it is determined that the first expense item is inconsistent with the corresponding second expense item, notify the relevant personnel to modify it.

[0042] The present invention provides an automated monthly settlement method for business travel based on RPA. The present invention combines Robotic Process Automation (RPA) technology with Optical Character Recognition (OCR) technology and applies it to the travel expense reimbursement verification process, realizing for the first time the fully automated processing from business travel system data acquisition to ticket content recognition. RPA is responsible for automatically acquiring business travel expense data, while OCR is responsible for identifying and logically reconstructing the image content of the reimbursement ticket. This combination of technologies effectively improves the efficiency of data processing, reduces the intervention of manual operations, and can automatically process complex reimbursement data.

[0043] Embodiment 2:

[0044] Based on the first embodiment, a process for automatically obtaining business travel data through RPA is provided, such as Figure 3 As shown, the automation process is realized by RPA as follows:

[0045] Step 301: Automatically log in to the business travel system through the Robotic Process Automation (RPA) and access the preset business travel data interface or database to obtain business travel data within a specified time range;

[0046] Step 302: Screen data based on business trip record parameters and extract expenses associated with expense items;

[0047] The business trip record parameters include employee name, business trip destination, departure time and return time, and the expense items include airfare, hotel expenses and transportation expenses;

[0048] Step 303: Check the expenses associated with the expense item according to the format requirements of the expense item amount and whether the amount is missing;

[0049] Step 304: Generate a first expense item table for the expenses associated with the expense items.

[0050] A method for automatically acquiring business travel data through RPA is provided in the second embodiment of the present invention. RPA (robotic process automation) can automatically log in to the business travel management system or database and perform batch data acquisition operations by simulating human operations. This technology can replace manual extraction of data from multiple systems or platforms, such as air ticket booking information, hotel booking records, transportation costs, etc. Through automated operations, RPA can quickly and accurately acquire large quantities of business travel data, avoiding the tediousness and errors of manual operations. RPA can not only acquire business travel data in batches, but also intelligently parse web forms and Excel tables based on pre-set rules. For example, RPA can automatically classify data into different expense items (such as air ticket costs, hotel costs, transportation costs, etc.) and extract the amount information corresponding to each expense item. This intelligent data processing capability significantly reduces the need for manual intervention.

[0051] Embodiment three:

[0052] Although traditional OCR technology can efficiently recognize text in images, the recognition results are often isolated characters or lines, lacking contextual logical associations. Especially when processing complex documents (such as expense reimbursement documents, invoices, etc.), it is easy to ignore the business logic between lines and paragraphs. Embodiment 3 of the present invention provides a method for performing OCR image recognition on archived expense reimbursement documents, such as Figure 4 As shown, including:

[0053] Step 401: Perform OCR image recognition on the archived reimbursement voucher to obtain text recognition results;

[0054] Before step 401, the archived reimbursement vouchers are also preprocessed, wherein the preprocessing includes binarization, image denoising and tilt correction.

[0055] Step 402: logically reconstruct the text recognition result according to the finite state machine, obtain the text line state by analyzing the document layout information, and construct a line state machine;

[0056] Step 403: logically reconstruct the text recognition result through the state machine to form a text result with contextual logical semantics;

[0057] Step 404: Identify the logical relationship between rows through a finite state machine;

[0058] Among them, logical relationships include continuation relationships, different attribute relationships, parallel relationships and inclusion relationships.

[0059] In order to better illustrate the method of logically reconstructing the OCR recognition result based on the finite state machine, the third embodiment of the present invention takes the actual business trip expense receipt recognition as an example to illustrate as follows:

[0060] Step 1: OCR recognition of bills

[0061] Among them, OCR recognition is performed on business trip reimbursement receipts to extract the text content in the receipts. OCR technology can recognize the expense items, dates, amounts, etc. in the receipts, but these contents are usually scattered and have no contextual logic. For example: Line 1: "Air ticket fee", Line 2: "October 15, 2024", Line 3: "800 yuan", although these text contents are recognized, the logical relationship between them is not clear.

[0062] Step 2: Explicit row status extraction

[0063] Among them, the "explicit line state" is extracted for each line of text in the OCR recognition result. The explicit line state is based on the format characteristics of the text (such as numbers, punctuation, date format, etc.) and typesetting information (such as left margin, alignment, etc.) to determine the basic classification of text. In the business trip expense receipt, the explicit line state can extract the following common states:

[0064] Expense type row: such as "air ticket fee", "hotel fee", etc.; date row: such as "October 15, 2023"; amount row: such as "800 yuan". Through these features, the text recognized by OCR can be initially divided into different categories, providing a basis for subsequent logical reconstruction.

[0065] Step 3: Build the Finite State Machine

[0066] In this step, a finite state machine is constructed to describe the relationship between different elements in the reimbursement voucher (expense type, date, amount, etc.). The finite state machine contains the following states: Expense type state: Identify the type of expense, such as "airfare", "accommodation fee", etc.; Date state: Identify dates related to business trips, such as departure date, return date, etc.; Amount state: Identify the expense amount. The state transition rules of the state machine are as follows:

[0067] When an "expense type line" is identified, the state enters the expense type state. The system then expects to identify the relevant date of the expense type, so the state machine enters the date state. After identifying the date, the state machine expects the amount information of the expense, so it switches to the amount state. After completing the identification of a complete expense item, the state machine returns to the initial state and prepares to process the next expense information.

[0068] Step 4: State change and logic reconstruction

[0069] When the finite state machine starts running, the system reads the text lines recognized by OCR line by line and changes the state according to the rules. For example, when the system recognizes "air ticket fee", it enters the fee type state; then it recognizes "October 15, 2023", and the state is converted to the date state; when it recognizes "800 yuan", the state is converted to the amount state. In this process, the system gradually reconstructs this information and generates structured reimbursement document information according to the logical relationship of "fee type-date-amount".

[0070] Assume that the reimbursement document recognized by OCR is as follows:

[0071] Airfare

[0072] October 15, 2023

[0073] 800 NTD

[0074] Hotel Fees

[0075] October 16, 2023

[0076] 500 NTD

[0077] The logic processed by the finite state machine is as follows:

[0078] Line 1: "Airfare", enters the expense type state; Line 2: "October 15, 2023", the state machine enters the date state; Line 3: "800 yuan", the state machine enters the amount state. Generate complete structured information: "Airfare, October 15, 2023, 800 yuan"; Line 4: "Hotel fee", the state machine returns to the expense type state; Line 5: "October 16, 2023", the state machine enters the date state; Line 6: "500 yuan", the state machine enters the amount state. Generate complete structured information: "Hotel fee, October 16, 2023, 500 yuan".

[0079] Step 5: Logical exception handling

[0080] If there is a situation that does not comply with the state transition rules during the OCR recognition process, the system can automatically detect the anomaly and issue a prompt. For example, if "airfare" is recognized and then "500 yuan" is recognized without a date, the system can determine that the date information is missing and prompt the relevant personnel to supplement it. If "airfare" is followed by another expense item instead of a date or amount, the system can identify it as illogical and prompt for correction.

[0081] Step 6: Output structured data

[0082] Among them, through the logic reconstruction process of the finite state machine, the text results of OCR recognition are converted into structured data. This data includes information such as expense type, date, amount, etc., which can be directly used in the subsequent financial reimbursement verification and reconciliation process.

[0083] The third embodiment of the present invention is a method for reconstructing OCR recognition logic based on a finite state machine, which can effectively process complex logical relationships and context dependencies in business trip expense reimbursement documents. Through explicit line state extraction and dynamic state transition of the state machine, the system can generate structured information that conforms to business logic from isolated text lines recognized by OCR, improve the accuracy and efficiency of expense reimbursement document processing, and reduce the possibility of human errors and omissions.

[0084] Embodiment 4:

[0085] In order to further improve the accuracy of OCR text recognition of bills, OCR image recognition is performed on the archived expense account to obtain text information. In the fourth embodiment of the present invention, a model is constructed in combination with OCR confidence score and its training steps are optimized, such as Figure 5 As shown, including:

[0086] Step 501, recognized text, location information and OCR confidence score;

[0087] Step 502: Calculate the confidence score of each character based on each character box output by OCR, and associate it with the recognized character;

[0088] Step 503: Combine the confidence score of each character with the word embedding in the BERT model to generate confidence-aware word embedding;

[0089] Step 504: input the confidence-aware word embedding into the confidence-aware error detection model to classify the recognized text to determine whether there is an error in the text;

[0090] Step 505: For the detected errors, semantic-based error correction can be used to select the best correction result through candidate generation, weight allocation and scoring.

[0091] Before step 504, a step of training and generating a confidence-aware error detection model is included, specifically including:

[0092] Step 504-1, obtaining a data set including OCR output with confidence scores;

[0093] The data set with confidence scores includes the original text recognized by OCR, the correct text corresponding to the original text recognized by OCR, and the OCR confidence score of each character;

[0094] Step 504-2: Align the OCR recognized original text with the corresponding correct text character by character or word by word;

[0095] Step 504-3: Bind the OCR confidence score to each character;

[0096] Step 504-4, label each character, label the wrong character as 1, and the correct character as 0, to generate a training data set;

[0097] Step 504-5: Input the training data set into the BERT model to generate a word embedding vector that integrates confidence perception, and classify each character as correct or incorrect through the binary classification layer after the BERT model;

[0098] Among them, the word embedding vector integrating confidence perception is e ci =(1-α)·Emb(t i )+α·(1-p ocr (t i )), where t is a list of character tokens t = {t1, t2, ..., t n}, Emb is the standard embedding function, p ocr is the OCR confidence score, and α is a trainable parameter used to control the degree of noise used in the model;

[0099] Step 504-6: perform back propagation parameter optimization according to the cross entropy loss function. When the change of the cross entropy loss function before and after iteration is less than a preset threshold or the number of iterations reaches a preset number, output a confidence-aware error detection model.

[0100] Among them, the cross entropy loss function cross entropy loss function Among them, y i is the label of the character as correct or incorrect, y i is the probability of the model predicting correctly or incorrectly, N is the total number of samples, and the change in the cross entropy loss function before and after the iteration is less than the preset threshold, indicating that the training optimization space is small and the training can be stopped. Alternatively, when the number of iterations is greater than the preset number, it also means that the training can be stopped.

[0101] Embodiment 4 of the present invention integrates OCR confidence and BERT word embedding, and constructs a confidence-aware error detection model. This method can achieve accurate error detection in the text recognition process, and then automatically correct errors (automatic error correction methods belong to the prior art, for example, error correction methods based on candidate words, error correction based on contextual language models, error correction methods based on edit distance, error correction based on parts of speech and grammatical rules, etc., which will not be repeated here), significantly improving the accuracy, clarity and logical consistency of the recognition results. At the same time, by reducing the need for manual intervention, the automation level of text recognition is improved, which is suitable for OCR recognition scenarios with high precision requirements, and provides reliable technical support for various document processing.

[0102] Further, as Figures 2 to 5 The specific implementation of the method, in an embodiment of the present invention, provides a business travel automation monthly settlement device based on RPA, such as Figure 6 As shown, the device comprises:

[0103] A first acquisition module 610 is used to automatically acquire business travel data through robotic process automation (RPA), and parse the business travel data to acquire a first expense item and corresponding amount information;

[0104] The second acquisition module 620 is used to perform OCR image recognition and logic reconstruction on the archived reimbursement voucher to obtain the second expense item and the corresponding amount information;

[0105] A determination module 630, for determining the logical relationship and arithmetic relationship between the first expense item and the corresponding second expense item, and determining whether there is any omission or inconsistency;

[0106] The notification module 640 is used to notify relevant personnel to supplement when it is determined that the second expense item is missing; when it is determined that the first expense item is inconsistent with the corresponding second expense item, notify relevant personnel to modify it.

[0107] In an embodiment of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of implementing the RPA-based business travel automated monthly settlement method include:

[0108] Automatically obtain business travel data through Robotic Process Automation (RPA) and parse the business travel data to obtain the first expense item and the corresponding amount information;

[0109] Perform OCR image recognition and logic reconstruction on the archived reimbursement vouchers to obtain the second expense item and the corresponding amount information;

[0110] Determine the logical and arithmetic relationship between the first expense item and the corresponding second expense item, and determine whether there is any omission or inconsistency;

[0111] When it is determined that there is omission in the second expense item, the relevant personnel are notified to supplement it; when it is determined that the first expense item is inconsistent with the corresponding second expense item, the relevant personnel are notified to modify it.

[0112] In an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0113] Automatically obtain business travel data through Robotic Process Automation (RPA) and parse the business travel data to obtain the first expense item and the corresponding amount information;

[0114] Perform OCR image recognition and logic reconstruction on the archived reimbursement vouchers to obtain the second expense item and the corresponding amount information;

[0115] Determine the logical and arithmetic relationship between the first expense item and the corresponding second expense item, and determine whether there is any omission or inconsistency;

[0116] When it is determined that there is omission in the second expense item, the relevant personnel are notified to supplement it; when it is determined that the first expense item is inconsistent with the corresponding second expense item, the relevant personnel are notified to modify it.

[0117] It should be noted that the above embodiments only take travel reimbursement as an example to illustrate the principles and implementation steps of the embodiments of the present invention, and do not specifically limit the actual application scenarios, such as cost budgeting and funding application. The technical solution of the present invention can also be applied to extended scenarios of line loss analysis and evaluation in various substations. For the functions or steps that can be implemented by the computer-readable storage medium or computer device, please refer to the aforementioned method embodiments. To avoid repetition, they will not be described one by one here.

[0118] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0119] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0120] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A business travel automated monthly settlement method based on RPA, characterized in that: include: Automatically obtain business travel data through robotic process automation (RPA), and parse the business travel data to obtain a first expense item and corresponding amount information; Perform OCR image recognition and logic reconstruction on the archived reimbursement vouchers to obtain the second expense item and the corresponding amount information; Determine the logical relationship and arithmetic relationship between the first expense item and the corresponding second expense item, and determine whether there is any omission or inconsistency; When it is determined that there is omission in the second expense item, the relevant personnel are notified to supplement it; when it is determined that the first expense item is inconsistent with the corresponding second expense item, the relevant personnel are notified to modify it.

2. The RPA-based business travel automated monthly settlement method according to claim 1 is characterized in that: The step of automatically acquiring business travel data through robotic process automation (RPA) and parsing the business travel data to obtain the first expense item and corresponding amount information includes: Automatically log into the business travel system through Robotic Process Automation (RPA) and access the preset business travel data interface or database to obtain business travel data within a specified time range; Performing data screening based on business trip record parameters to extract expenses associated with expense items, wherein the business trip record parameters include employee name, business trip destination, departure time, and return time, and the expense items include airfare, hotel expenses, and transportation expenses; Check the expenses associated with the expense items according to the format requirements of the expense item amounts and whether the amounts are missing; A first expense item table is generated by associating the expenses with the expense items.

3. The RPA-based business travel automated monthly settlement method according to claim 1 is characterized in that: The step of performing OCR image recognition and logic reconstruction on the archived reimbursement voucher to obtain the second expense item and the corresponding amount information includes: Perform OCR image recognition on archived reimbursement receipts to obtain text recognition results; The text recognition result is logically reconstructed according to a finite state machine, the text line state is obtained by analyzing the document layout information, and a line state machine is constructed; The text recognition result is logically reconstructed by a state machine to form a text result with contextual logical semantics; The logical relationship between rows is identified through a finite state machine, wherein the logical relationship includes a continuation relationship, a different attribute relationship, a parallel relationship and an inclusion relationship.

4. The RPA-based business travel automated monthly settlement method according to claim 3 is characterized in that: Before the step of performing OCR image recognition on the archived reimbursement vouchers to obtain text recognition results, the method includes: The archived reimbursement vouchers are preprocessed, wherein the preprocessing includes binarization, image denoising and tilt correction.

5. The RPA-based business travel automated monthly settlement method according to claim 4 is characterized in that: The step of performing OCR image recognition on the archived reimbursement vouchers to obtain text recognition results includes: Perform OCR image recognition on archived expense accounts to obtain text information, including recognized text, location information, and OCR confidence scores; Based on each character box output by OCR, calculate the confidence score for each character and associate it with the recognized character; Combine the confidence score of each character with the word embedding in the BERT model to generate confidence-aware word embeddings; The confidence-aware word embedding is input into the confidence-aware error detection model to classify the recognized text to determine whether there is an error in the text; For detected errors, semantic-based error correction can be used to select the best correction result through candidate generation, weight assignment and scoring.

6. The RPA-based business travel automated monthly settlement method according to claim 3 is characterized in that: Before the step of embedding the confidence-aware word into the confidence-aware error detection model to classify the recognized text to determine whether the text has errors, the step of training and generating the confidence-aware error detection model specifically includes: Obtaining a data set with confidence scores containing OCR output, wherein the data set with confidence scores includes the original text recognized by OCR, the correct text corresponding to the original text recognized by OCR, and the OCR confidence score of each character; Align the OCR recognized original text with the corresponding correct text, character by character or word by word; Bind an OCR confidence score to each character; Label each character, label the wrong character as 1 and the correct character as 0, and generate a training data set; The training data set is input into the BERT model to generate a word embedding vector that integrates confidence perception, and each character is classified correctly or incorrectly through the binary classification layer after the BERT model. The word embedding vector that integrates confidence perception is e ci =(1-α)·Emb(t i )+α·(1-p ocr (t i )), where t is a list of character tokens t = {t1, t2, ..., t n }, Emb is the standard embedding function, p ocr is the OCR confidence score, and α is a trainable parameter used to control the degree of noise used in the model; Back propagation parameters are optimized according to the cross entropy loss function. When the change of the cross entropy loss function before and after iteration is less than a preset threshold or the number of iterations reaches a preset number, a confidence-aware error detection model is output.

7. The RPA-based business travel automated monthly settlement method according to claim 6 is characterized in that: The cross entropy loss function Among them, y i is the label of the character as true or false, is the probability that the model predicts correctly or incorrectly, and N is the total number of samples.

8. An RPA-based business travel automated monthly settlement device, characterized in that: include: A first acquisition module, configured to automatically acquire business travel data through robotic process automation (RPA), and parse the business travel data to acquire a first expense item and corresponding amount information; The second acquisition module is used to perform OCR image recognition and logic reconstruction on the archived reimbursement vouchers to obtain the second expense item and the corresponding amount information; A judgment module, used to judge the logical relationship and arithmetic relationship between the first expense item and the corresponding second expense item, and judge whether there is any omission or inconsistency; The notification module is used to notify relevant personnel to supplement when it is determined that there is omission in the second expense item; when it is determined that the first expense item is inconsistent with the corresponding second expense item, notify relevant personnel to modify it.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the RPA-based business travel automated monthly settlement method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the RPA-based business travel automated monthly settlement method as described in any one of claims 1 to 7 are implemented.

Images