Invoice Processing Using Robotic Process Automation

CSEIT2062106 | Accepted : 10 April 2020 | Published : 20 April 2020 | March-April-2020 [ 6 (2) : 216-223 ]

International Journal of Scientific Research in Computer Science, Engineering and Information Technology

DOI : https://doi.org/10.32628/CSEIT2062106

216

Sagar Sahu, Sania Salwekar, Atharva Pandit, Manoj Patil

Computer Engineering, Datta Meghe College of Engineering, Airoli, Navi Mumbai, Maharashtra, India

ABSTRACT

This paper describes our recent effort to develop a automative application to transform invoice processing in Finance

operations. As a prime example of the technology’s potential for driving efficiency, Robotic Process Automation (RPA)

can be applied to a number of finance and accounting operations, invoice processing. RPA DataBot can automate data

input, error reconciliation, and some of the decision-making required by finance staff when processing invoices. At

the same time, automation is able to limit errors in such processes and reduce the need for manual exception handling.

UiPath’s RPA DataBot are able to constantly monitor a dedicated folder where invoices are saved by employees (or

other DataBot) in PDF format. Once robots detect the presence of an invoice in the folder, they begin to extract

information from the document. Using intelligent Optical Character Recognition (OCR) and natural language

processing capabilities, DataBot are able to read out the information that is visible on the invoice. After robots extract

the key information from each invoice, they use their credentials to open the company’s database or enterprise resource

planning system, if not already open. The robots then start processing the invoices one-by-one by transferring over

the relevant invoice information. During this whole process, the DataBot are also running background activities such

as monitoring the dedicated invoice folder or its email address, performing basic checks to see if the company’s database

is open, and verifying whether vendor information (e.g. VAT number) on the invoice matches what is already in the

database.

Keywords : DataBot, Optical Character Recognition, Robotic Process Automation

I. INTRODUCTION

According to a research report by technology services

company Aberdeen Group it takes between 4 to 16 days

for companies to process an invoice from receipt through

payment approval. This conclusion might not really

come as a shock, though especially for companies and

their employees who experience the manual effort still

involved with processing invoices on a day-to-day basis.

In fact, a study by Canon Business Process Services

suggests that more than half of all invoice processing

requires at least 86-100% manual input.

In times of increasing digitization and automation, these

numbers reveal that companies are missing out on

possibilities for making their finance & accounting

departments more efficient. And the high percentages of

manual labor indicate significant inefficiencies combined

with a lack of central or standardized invoice

management processes, which can also lead to

unnecessary inconveniences like unpaid invoices (and

the associated late fees) as well as higher than necessary

labor costs.

1. Automation’s potential with invoice processing

Financial processes are critical to the overall

functionality of companies, which means that there may

be doubts regarding the capabilities and success rates of

RPA for accounts payable activities like invoice

processing. Invoices that company receive from their

suppliers sometimes, for example, arrive in multiple

different formats: as a paper copy, a Word document, a

Volume 6, Issue 2, March-April-2020 | http://ijsrcseit.com

Sagar Sahu et al

Int

J Sci Res CSE & IT, March-April-2020; 6 (2) : 216-223

217

PDF email attachment, or a fax. Moreover, a company’s

finance team is responsible for manually transferring the

data from these various invoice formats into the

company’s database and dealing with any discrepancies.

These challenges make it difficult to handle invoices in

the same way each time and, as a result, drive company

employees to process invoices manually. Moreover,

because the data in these invoices is typically

unstructured, this manual transfer process is time-

consuming and prone to errors. But do these operations

need to be done manually? In short, the answer —

perhaps unsurprisingly — is no

2. Invoice processing with UiPath

2.1 Fast, measurable outcomes :- Let’s see how businesses

can leverage UiPath’s Enterprise RPA Platform in

driving down the costs and simultaneously increasing the

efficiency and accuracy of their accounts payable

operations.

Global BPO provider uses UiPath for Citrix intensive

automation.

A global BPO provider used UiPath to reduce the

delivery effort in several of their clients’ invoice process.

This required access to their ERP system through remote

virtual environment (citrix technology). UiPath’s ability

to precisely recognize screen elements and drive seamless

automation even in the toughest scenarios such as Citrix

helped the BPO to reduce the delivery effort by 70%,

with a drop in AHT (average handling time) from 10

minutes to 3.

European Pharma company uses intelligent OCR to

process invoices in unstructured form. A European

Pharma company was using 3 FTEs to process 1800

invoices every month. Four applications, including MS

Office and e-mail, were involved, and several document

types, many of the invoices still being in paper format.

The UiPath Robot extracted the structured and semi-

structured data using intelligent OCR and performed all

validations necessary, such as the PO number, the

number of items, and the cost per item against the PO

and goods receives.

Figure 1 shows global growth in revenue using Robotic

Process Automation use cases.

Fig 1. Global Robotic Process Automation (RPA)

Market.

II. LITERATURE REVIEW

The invoicing process is an important part of a wider set

of business processes including the placing and

acceptance of an order, delivery and payment. Some

research papers regarding invoice processing system

were studied by us. These included various techniques of

invoice processing using cognitive approach, generic

system which uses OCR engine, using CBR (Case-based

reasoning) , optimization approach which makes use of

SVM, Entropy ,etc .Some of these approaches for invoice

processing system are mentioned below.

Enes Aslan, Ethem Unver, Tugrul Karakaya, Yusuf Sinan

Akgul in their paper proposed a new invoice parsing

method which consists of two-phase optimization

structure and eliminates invoice classes. The first phase

uses individual invoice part detectors such as SVM,

maximum entropy and HOG to produce candidates for

the various parts of different types of invoices. At the

second phase, the basic idea is to divide an invoice into

different parts and then arrange it together. As PBM is an

optimization based method, it can handle any type of

invoices. The proposed system is tested with real invoices

and are found to be promising for the real-world

experiences.

Ying Li, Muthu Muthiah, Arindam Routh, Chitra Dorai

describes their initiative of developing a cognitive

application to transform invoice processing system in

P2P (Procure to Pay) process by providing domain-

Volume 6, Issue 2, March-April-2020 | http://ijsrcseit.com

Sagar Sahu et al

Int

J Sci Res CSE & IT, March-April-2020; 6 (2) : 216-223

218

specific systems. Procure to pay (P2P) process consists of

two main functions i.e. transactional data is sent to

supplier as well as it includes handling of data which

includes information about orders and payment for a

product or service. A 3-month long usage tracking has

showed promising performance. Significant productivity

improvement has been achieved by the team since the

deployment of this application in production with a

client.

T. A. Bayer, H. U. Mogg-Schneider, Daimler-Benz

proposed a generic system for processing invoices that

automatically extracted the requested items with

arbitrary form layout in arbitrary domains. The given

system consists of two components OCR tool and

FRESCO. The error rate is less for FRESCO so it is used.

FRESCO component is contains the knowledge about the

domain. This generic system is used for health insurance

related invoices.

Hatem Hamza, Yolande Belaid, Abdel Belaid introduced

an invoice analysis approach using Case-Based Reasoning

(CBR). CBR is used to analyse and interpret new invoices

using previous processing experiences. Each new

documents are segmented into structures and interpreted

using structure database. A new document’s

interpretation depends on graph edit distance as well as

on string edit distance. They focus more on document

interpretation through its structure interpretation.

Mainly, CBR approach was used for accessing multiple

invoices. The final use of this system was processing

invoices for both known and unknown classes.

III. REQUIREMENT ANALYSIS

Requirements analysis involves all the tasks that are

conducted to identify the needs of different stakeholders.

Therefore requirements analysis means to analyse,

document, validate and manage software or system

requirements. High-quality requirements are

documented, actionable, measurable, testable, traceable,

helps to identify business opportunities, and are defined

to a facilitate system design. After the extensive analysis

of the problems in the system, we are familiar with the

requirement that the current system needs. The system

requirements are categorized into the functional and

non-functional requirements. These requirements are

listed below:

A. Hardware requirements

1) Minimum 4GB RAM.

2) 200 MB of free Hard Disk space.

3) Browser: Chrome(v49), Internet Explorer (v10) or

higher.

4) Processor: 3GHz or higher.

B. Software requirements :-

1) Operating System : Windows 7 and above.

2) UiPath Studio.

3) UiPath Robots.

4) UiPath Orchestra.

C. Functional requirement

Functional requirement are the functions or features that

must be included in any system to satisfy the business

needs and must be acceptable to the users. Based on this,

the functional requirements that the system must require

are as follows:

1) Name and Address of the Recipient: The Name of

Recipient is required to identify the person who has

initiated the transaction. The name should be spelled

correctly in order to avoid confusion. We require

physical address of the customer to deliver any

replacement or something else.

2) Sold By: This feature describes the seller of the product.

Basically it answers the query from where is the product

shipped and which outlet is responsible for shipping.

3) Total Amount: This field gives us the final amount of

the product.

4) Order Number: This field describes the order number

or order ID of the product. This field can immediately

help the seller outlet to identify all the product details.

5) Order Date: This field gives us the Date when the

given product was purchased.

6) Invoice Number: This field shows us the Receipt

(Invoice) number of the transaction. This number is

Volume 6, Issue 2, March-April-2020 | http://ijsrcseit.com

Sagar Sahu et al

Int

J Sci Res CSE & IT, March-April-2020; 6 (2) : 216-223

219

useful in servicing centres to identify the product

warranty or guarantee period.

7) Invoice Date: Date at which the invoice was printed.

8) Product Description: This field gives us the

information about either products or services including

prices and quantities. Often includes standard product

description and inventory number.

B. Non-functional requirement :-

Non-functional requirement is a description of features,

characteristics and attribute of the system as well as any

constraints that may limit the boundaries of the proposed

system. The non-functional requirements are essentially

based on the performance, information, economy,

control and security efficiency and services. Based on

these the non-functional requirements are as follows:

1) Security:- Security requirements ensure that the

software is protected from unauthorized access to the

system and its stored data. It considers different levels of

authorization and authentication across different user’s

roles. For instance, data privacy is a security

characteristic that describes who can create, see, copy,

change, or delete information. Security also includes

protection against viruses and malware attacks.

2) Reliability:- Reliability defines how likely it is for the

software to work without failure for a given period of

time. Reliability decreases because of bugs in the code,

hardware failures, or problems with other system

components. To measure software reliability, you can

count the percentage of operations that are completed

correctly or track the average period of time the system

runs before failing.

3) Performance:- Performance is a quality attribute that

describes the responsiveness of the system to various user

interactions with it. Poor performance leads to negative

user experience. It also jeopardizes system safety when

it’s is overloaded.

4) Availability:- Availability is gauged by the period of

time that the system’s functionality and services are

available for use with all operations. So, scheduled

maintenance periods directly influence this parameter.

And it’s important to define how the impact of

maintenance can be minimized. When writing the

availability requirements, the team has to define the most

critical components of the system that must be available

at all time.

5) Scalability:- Scalability requirements describe how the

system must grow without negative influence on its

performance. This means serving more users, processing

more data, and doing more transactions. Scalability has

both hardware and software implications. For instance,

you can increase scalability by adding memory, servers,

or disk space. On the other hand, you can compress data,

use optimizing algorithms, etc.

IV. DESIGN PROCESS

Automated invoice processing helps to save a serious

amount of time and money, compared with manual

paper invoice processing, creating efficiencies and

increasing the accuracy of captured data.

A. PROCESS DIAGRAM

Fig 2. Process Diagram of Invoice Processing Flow

This service enables your company to:

1) Capture your invoices from their original source e.g.

fax, email, electronic image or paper copy

Volume 6, Issue 2, March-April-2020 | http://ijsrcseit.com

Sagar Sahu et al

Int

J Sci Res CSE & IT, March-April-2020; 6 (2) : 216-223

220

2) Automatically extract key information from your

invoices, using clever software for import into your

financial systems

3) Validate your invoices and checking your invoice data

against data files e.g. supplier name, amount and

Purchase Order number

4) Match and check the purchase order system to make

sure the invoice matches the original order

B. FLOW DIAGRAM

Once the data is extracted or captured from the invoice

the data is sent into the system for automatic matching

against the purchase order. This process can compare just

the invoice data with that shown on the purchase order

or be expanded to include a deeper level that looks at the

receiving documents. Workflow steps can be configured

such that the responsible person will then receive an

email alert so that he or she can approve the invoice. If

there are other people involved in the approval workflow,

email alerts to them will also be automatically generated.

The typical workflow is a four-step process beginning

with:

1. Import of the images through scanning or email,

2. Identification of the vendor and business unit

associated with the invoice,

3. Data extraction, and

4. Export of the extracted data and images then receive

an email alert so that he or she can approve the invoice.

If there are other people involved in the approval

workflow, email alerts to them will also be automatically

generated. The typical workflow is a four-step process

beginning with:

Fig 3. Illustration of Invoice Processing Flow.

V. DESIGN AND IMPLEMENTATION

Regardless the size of your organization, financial

processes play an important role in the overall

functionality. These days, most people are skeptical

regarding the capabilities and success rates of RPA and

invoice processing Companies, in a nutshell, receive an

invoice from their suppliers sometimes, and usually

arrive in a plethora of different formats, including a PDF

email attachment, as a paper copy, or fax. In addition, the

finance department of an organization is majorly

responsible for manually transferring the data from a

multitude of invoice formats into the database of the

company and dealing with any incongruity.

Without a shadow of a doubt, these things really make it

difficult and allow a business to carry out the overall

process manually and on a faster rate.

Since the data in these invoices are not structured in a

proper format, this manual transfer process is time-

consuming and there are chances that a mistake could be

made.

In our proposed system DataBot will perform Invoice

automation that would free up back office

finance/procurement teams to focus on higher value

added tasks.

Invoice automation allows straight through processing

(no human interaction) most of the time for the entire

invoice process. Invoice automation involves:

A. Monitoring For Invoices

Invoices arrive in companies as PDFs, image files and

increasingly rarely as hard copy documents.

1) For digital invoices, an RPA bot or a simple email

automation tool can flag emails with invoices and

forward them for data extraction. Some companies use a

dedicated email address for invoices to further simplify

invoice monitoring.

2) For hard-copy invoices, companies are switching to

using a single address to centralize invoice scanning.

Volume 6, Issue 2, March-April-2020 | http://ijsrcseit.com

Sagar Sahu et al

Int

J Sci Res CSE & IT, March-April-2020; 6 (2) : 216-223

221

B. Invoice Capturing :-

1) Extracting relevant details (e.g. bank account, ordered

item) from the invoice. If software does not have

confidence in the results, it is sent to employees for a

manual check

2) While digitization helped automate numerous

processes, mostly rule based software was used in

digitization. Invoice capture software is different.

Invoice capture involves both reading the invoice text

with Optical Character Recognition (OCR) and

understanding its context with machine learning.

C. Evaluating Invoice Against Order Records And Other

Criteria :-

Evaluating invoice against order records and other

criteria to ensure that the payment is indeed a valid one.

Evaluations include

1) cross-checking invoice against purchase orders

2) cross-checking invoice for duplicity

3) using working capital optimization policies to decide

payment time

4) using limits to decide whether to manually process

invoice. Invoices that are abnormally large compared to

a suppliers’ usual invoices may need to be manually

verified to ensure that wrong payments are not done

D. Recording Invoice Related Information in System :-

1) Using intelligent OCR and natural language processing

capabilities, software robots are able to read out the

information that is visible on the invoice.

2) After robots extract the key information from each

invoice, they use their credentials to open the company’s

database or enterprise resource planning system, if not

already open. The robots then start processing the

invoices one-by-one by transferring over the relevant

invoice information.

E. Email Notification

1) After successfully registering each invoice, the

software robots are then able to send posting

notifications in the form of emails to the responsible

employee or to the vendor in question.

2) An email is also sent to the responsible party in case of

an exception

VI. TECHNOLOGIES USED

A. UIPATH STUDIO :-

UiPath Studio is a complete solution for application

integration, and automating third-party applications,

administrative IT tasks and business IT processes. One of

the most important notions in Studio is the automation

application.

An application is a graphical representation of a business

process. It enables you to automate rule-based processes,

by giving you full control of the execution order and the

relationship between a custom set of steps, also known as

activities in UiPath Studio. Each activity consists of a

small action, such as clicking a button, reading a file or

writing to a log panel.

The main types of supported workflows are:

1) Sequences - suitable to linear processes, enabling you

to smoothly go from one activity to another, without

cluttering your workflow.

2) Flowcharts - suitable to a more complex business logic,

enabling you to integrate decisions and connect activities

in a more diverse manner, through multiple branching

logic operators.

3) State Machines - suitable for very large workflows;

they use a finite number of states in their execution

which are triggered by a condition (transition) or activity.

4) Global Exception Handler - suitable for determining

the workflow behavior when encountering an execution

error, and for debugging processes.

B. E-MAIL ACTIVITIES PACKAGE :-

1) The Mail Activities Pack is designed to facilitate the

automation of any mail-related tasks, covering various

protocols, such as IMAP, POP3 or SMTP. UiPath also

features activities that are specialized for working with

Outlook and Exchange.

Volume 6, Issue 2, March-April-2020 | http://ijsrcseit.com

Sagar Sahu et al

Int

J Sci Res CSE & IT, March-April-2020; 6 (2) : 216-223

222

2) Activities such as Save Mail Message and Save

Attachments are not intended to be used with certain

mail protocols. Instead, they save the MailMessage object

variable retrieved from activities such as Get POP3 Mail

Message to a specified folder on the current machine

C. PDF ACTIVITIES PACKAGE

1) The PDF pack contains activities designed to extract

data from PDF and XPS files and store it into string

variables. The data can be extracted from the entire

document or from a range of pages specified under the

Range property found in each of the activities.

2) In the case of scanned documents, data extraction can

also be achieved by using OCR-based activities, Read

PDF with OCR and Read XPS With OCR. To select one

of the three OCR engines specific to UiPath, Google OCR,

Microsoft OCR and Abbyy OCR, simply drop the engine

in the body of the activity.

D. EXCEL ACTIVITIES PACKAGE :-

1) The Excel activities package aids users to automate all

aspects of Microsoft Excel, as we know it is an application

intensely used by many in all types of businesses.

2) It contains activities that enable you to read

information from a cell, columns, rows or ranges, write

to other spreadsheets or workbooks, execute macros, and

even extract formulas. You can also sort data, color code

it or append additional information.

E. UIPATH ROBOT :-

1) The Robot is an execution agent, meaning that you

have to provide it with the automation applications you

want it to run.

2) After creating an automation application in Studio, it

needs to be published locally or to Orchestrator. Once an

application is published, you can send it to the Robot

machine and start executing it.

3) This is populated by default as follows:

i) When NOT connected to Orchestrator

ii) When connected to Orchestrator - the default

Orchestrator feed

VII. RESULTS

Following are the results we obtained after performing a

series of test with real time invoices.The accuracy we

obtained is 100%.

1.This is the Sample copy of an invoice which we have

used for testing.

Fig 4: Sample copy of an invoice

2. All Invoices sent to RPA databot through email is

successfully downloaded to a dedicated folder which is

assigned during development.The databot never re-

download the invoice which has been already

downloaded previously.

Fig 5: Successful download and storing of invoices in the

dedicated folder

Volume 6, Issue 2, March-April-2020 | http://ijsrcseit.com

Sagar Sahu et al

Int

J Sci Res CSE & IT, March-April-2020; 6 (2) : 216-223

223

3.After successfully downloading the invoices the

databot correctly fetches invoices from that folder one by

one.After this it's reads all the necessary content from the

invoice using a ocr engine then it store the details in the

Excel file with 100% accuracy in their correct places.

Fig 6: Successful data entry of content in the Excel file.

4.After successfully registering each invoice, the

software robot is then able to send post notifications in

the form of email to the concerned employee or to the

vendor in question.

Fig 7: Successfully notifying the concerned employee or

vendor.

VIII. CONCLUSION

Automated invoice processing can achieve powerful

results for accounts payable departments. Thanks to

technological advancements in robotic process

automation and computer vision technologies, invoice

processing can eliminate bottlenecks within the AP

process and turn the department into the profit center it

can be. Automated invoice processing enables touchless

automation across the entire accounts payable process,

and can transform the business in just months, creating a

powerful return on investment. Any organization that

receives a large number of vendor invoices on paper can

benefit from invoice processing technology.The more

data from each invoice that you are hand- keying into

your accounting software that more benefits you can get

from each page you automate.

IX. REFERENCES

[1]. Ying Li, Muthu Muthiah, Arindam Routh and

Chitra Dorai, ”Cognitive Computing in Action to

Enhance Invoice Processing with Customized

Language Translation”, 2017, IEEE International

Conference on Cognitive Computing (ICCC), IBM.

[2]. Hatem Hamza, Yolande Belaid and Abdel Belaid,

“A Case-Based Reasoning Approach on Unknown

Class Invoice Processing”,2007, IEEE International

Conference on Image Processing, France.

[3]. T. A. Bayer, H. U. Mogg-Schneider and Daimler-

Benz, ”A Generic System For Processing

Invoices”,1997, Fourth International Conference

on Document Analysis and Recognition, Germany.

[4]. Enes Aslan, Ethem Unver, Tugrul Karakaya and

Yusuf Sinan Akgul,”An optimization approach for

invoice image analysis”,2015, Signal Processing

and Communications Application

Conference,Turkey

Cite this article as :

Sagar Sahu, Sania Salwekar, Atharva Pandit, Manoj Patil,

"Invoice Processing Using Robotic Process Automation",

International Journal of Scientific Research in Computer

Science, Engineering and Information Technology

(IJSRCSEIT), ISSN : 2456-3307, Volume 6 Issue 2, pp.

216-223, March-April 2020. Available at doi :

https://doi.org/10.32628/CSEIT2062106

Journal URL : http://ijsrcseit.com/CSEIT2062106