DE112017003926T5 - System and method for monitoring electronic documents - Google Patents

Abstract

A system and method for monitoring electronic documents. The method includes analyzing a first electronic document to determine at least one transaction parameter, the first electronic document containing at least partially unstructured data; Creating a template for the first electronic document, wherein the created template is a structured data set containing the determined at least one transaction parameter; and comparing data of the created template with data associated with a plurality of second electronic documents to identify at least one abnormality in the first electronic document.

Description

Cross-reference to related applications

This application claims the priority of the provisional U.S. Application No. 62 / 371,234 , filed on August 5, 2016. This application is also a continuation of the submission filed on November 28, 2016 U.S. Application No. 15 / 361,934 which is now pending. The content of the above applications is hereby incorporated by reference.

Technical part

The present disclosure relates generally to the monitoring of files in data systems, and more particularly to the identification of abnormalities in electronic documents.

background

Due to rapid technological growth in recent decades, communication between people around the world has become faster and more convenient. As a result, transactions previously completed over days or weeks can now be completed in seconds. A business can now complete thousands or millions of transactions each year. Some of these transactions can be major transactions.

As companies increasingly rely on technologies to manage data related to operations, such as billing and ordering data, appropriate systems for the proper management and validation of data are critical to success. Especially for large companies, the amount of data that companies use every day can be overwhelming. Accordingly, manual verification and validation of such data is at best impractical. Differences between records, however, can cause significant problems for companies, such as errors in the proper reporting of profits to the tax authorities.

Therefore, it is highly desirable for businesses to quickly identify and resolve issues in their corporate records. This problem can be particularly difficult when a company uses multiple providers to provide services and goods because records from different providers may contain different information, may be otherwise formatted, may include errors or sudden price changes, and the like. Furthermore, detecting abnormalities can be challenging when receiving business records in unstructured data formats. For example, invoices are often received as image files that show a bill scan.

There are some solutions for automatically detecting information in scanned documents (eg, invoices and receipts) or other unstructured electronic documents (eg, unstructured text files). Such solutions often face the challenge of accurately identifying and recognizing characters and other features of electronic documents. In addition, content degradation of the input unstructured electronic documents typically results in higher error rates. As a result, existing image recognition techniques are not completely accurate under ideal circumstances (i.e., very clear images), and their accuracy often decreases dramatically when the input images are less clear. In addition, missing or otherwise incomplete data can lead to errors in the subsequent use of the data. Many existing solutions can not identify missing data unless a field in a structured record is incomplete.

Also, existing image recognition solutions may not be able to pinpoint some or all special characters (for example, "!", "@", "#", "$", "©", "%", "&" etc.) Image recognition solutions may incorrectly identify a line contained in a scanned document as a number "1." As another example, some existing image recognition solutions may not recognize special characters such as the dollar sign, the yen symbol, and so on.

Furthermore, such solutions can be challenging if recognized information is prepared for later use. In particular, many of these solutions either produce an output in an unstructured format or can only produce a structured output if the input electronic documents are formatted specifically for recognition by an image recognition system. The resulting unstructured output usually can not be processed efficiently. In particular, such unstructured output may contain duplicates and may include data that requires subsequent processing prior to use.

It would therefore be advantageous to provide a solution that overcomes the deficiencies of the prior art.

Summary

The following is a summary of several exemplary embodiments of the disclosure. This summary is provided to the convenience of the reader to provide a basic understanding of such embodiments, and does not fully define the scope of the disclosure. This summary is not a comprehensive overview of all contemplated embodiments and is not intended to identify key or critical elements of all embodiments, nor to limit the scope of some or all aspects. Its sole purpose is to present some concepts of one or more embodiments in a simplified form as a prelude to the more detailed description presented later. For the sake of simplicity, the term "some embodiments" may be used herein to refer to a single embodiment or multiple embodiments of the disclosure.

Certain embodiments disclosed herein include a method for monitoring electronic documents. The method comprises: analyzing a first electronic document to determine at least one transaction parameter, the first electronic document containing at least partially unstructured data; Creating a template for the first electronic document, wherein the created template is a structured data set containing the determined at least one transaction parameter; and comparing data of the created template with data associated with a plurality of second electronic documents to identify at least one abnormality in the first electronic document.

Certain embodiments disclosed herein also include a non-transitory computer-readable medium having stored thereon instructions for causing a processing circuit to perform a method, the method comprising: analyzing a first electronic document to determine at least one transaction parameter, wherein the first electronic document contains at least partially unstructured data; Creating a template for the first electronic document, wherein the created template is a structured data set containing the determined at least one transaction parameter; and comparing data of the created template with data associated with a plurality of second electronic documents to identify at least one abnormality in the first electronic document.

Certain embodiments disclosed herein also include a system for monitoring electronic documents. The system includes: a processing circuit; and a memory, the memory including instructions that, when executed by the processing circuitry, configure the system to: analyze a first electronic document to determine at least one transaction parameter, the first electronic document at least partially unstructured data contains; creating a template for the first electronic document, wherein the created template is a structured data set containing the determined at least one transaction parameter; and comparing data of the created template with data associated with a plurality of second electronic documents to identify at least one abnormality in the first electronic document.

list of figures

• 1 ist ein Netzwerkdiagramm, das zur Beschreibung der verschiedenen offenbarten Ausführungsformen verwendet wird.
• 2 ist ein schematisches Diagramm eines Validierungssystems gemäß einer Ausführungsform.
• 3 ist ein Flussdiagramm, das ein Verfahren zum Überwachen elektronischer Dokumente gemäß einer Ausführungsform darstellt.
• 4 ist ein Flussdiagramm, das ein Verfahren zum Erstellen eines Datensatzes basierend auf mindestens einem elektronischen Dokument gemäß einer Ausführungsform darstellt.
• 5 ist ein Flussdiagramm, das ein Verfahren zum Identifizieren von Auffälligkeiten gemäß einer Ausführungsform basierend auf einer Vorlage darstellt, die für ein elektronisches Eingabedokument erstellt wurde.

The subject matter disclosed herein is particularly pointed out and expressly claimed in the claims at the end of this specification. The foregoing and other objects, features and advantages of the disclosed embodiments will become apparent from the following detailed description taken in conjunction with the accompanying drawings.

• 1 FIG. 10 is a network diagram used to describe the various disclosed embodiments. FIG.
• 2 FIG. 12 is a schematic diagram of a validation system according to an embodiment. FIG.
• 3 FIG. 10 is a flowchart illustrating a method of monitoring electronic documents according to an embodiment. FIG.
• 4 FIG. 10 is a flow chart illustrating a method of creating a data set based on at least one electronic document according to an embodiment.
• 5 FIG. 10 is a flowchart illustrating a method for identifying abnormalities according to an embodiment based on a template created for an input electronic document.

Detailed description

It is important to note that the embodiments disclosed herein are only examples of the many beneficial uses of the innovative teachings herein. In general, statements made in the description of the present application do not necessarily limit one of the various claimed embodiments. In addition, some statements may apply to some inventive features, but not to others. Unless otherwise stated, In general, singular elements can be plural and vice versa, without affecting the general public. In the drawings, like numerals refer to like parts in several views.

The various disclosed embodiments include a method and system for monitoring electronic documents. The embodiments disclosed herein may be used to detect and correct for abnormalities in the monitored electronic documents. In one embodiment, a record is created based on a first electronic input document. The electronic input document contains data of a transaction and may contain unstructured data. A template for transaction attributes is created based on the record of the electronic input document. Data from the template created for the electronic input document is compared with data from second electronic sample documents. Based on the comparison, one or more abnormalities in data values can be identified. A warning can be issued indicating the abnormalities.

The disclosed embodiments enable automatic detection of abnormalities, for example, in newly received invoices. In particular, the disclosed embodiments include providing structured record templates for electronic documents, thereby enabling efficient and accurate comparison of data contained in electronic documents that are unstructured, semi-structured, or otherwise lacking a known structure. Furthermore, the templates created for the electronic documents allow for more efficient comparisons of particular records since comparisons may be limited to comparisons between certain fields of the templates. For example, data in a "time" field of one template can be compared to data in "time" fields of other templates, without the need for comparison with other data.

1 shows an exemplary network diagram 100 , which is used to describe the various disclosed embodiments. In the example network diagram 100 are an electronic document surveillance 120 , a business system 130 , a database 140 and multiple data sources 150 - 1 to 150 N (hereinafter for the sake of simplicity, as a data source in the following 150 and together as data sources 150 designated) over a network 110 communicatively connected. The network 110 may be a wireless, cellular or wired network, a local area network (LAN), a wide area network (WAN), a metro area network (MAN), the Internet, the World Wide Web (WWW), similar networks and combinations thereof, but is not limited to this.

The company system 130 is associated with a company and may store data related to purchases made by the company or its representatives, as well as data relating to the company itself. The enterprise may be, but is not limited to, a company whose employees may purchase goods and services subject to VAT abroad. The company system 130 For example, but not limited to, a server, a database, a corporate resource planning system, a customer relationship management system, or any other system storing relevant data.

The of the enterprise system 130 stored data may include, but is not limited to, electronic documents (eg, an image file showing, for example, a scan of an invoice, a text file, a spreadsheet file, etc.). Each electronic document may include, for example, an invoice, a tax receipt, a purchase number record, a VAT reclaim request, and the like. Data contained in each electronic document may be structured, semi-structured, unstructured or a combination thereof. The structured or semi-structured data may be in a format that is subject to surveillance 120 is not recognized for electronic documents and can therefore be treated as unstructured data.

Database 140 can store templates created for electronic documents, as well as historical data related to sample data and abnormality data indicating deviations from sample data from monitoring 120 be identified for electronic documents.

The data sources 150 store at least electronic documents that can be used as proof of grant requests. The data sources 150 may include, but are not limited to, resellers' servers or devices, tax authority servers, billing servers, a database associated with a business, and the like. As a non-limiting example, the data source 150 - 1 a merchant server storing image files showing invoices for transactions made by a merchant associated with the merchant server.

In one embodiment, the monitoring is 120 for electronic documents like that configured to create a template based on transaction parameters identified using image processing of a first electronic input document indicating information related to a transaction. Each template contains one or more fields and corresponding key-values identified in the analyzed electronic document. For this purpose, the monitoring 120 for electronic documents to be configured to retrieve the input electronic document from, for example, one of the data sources 150 or the enterprise system 130 retrieves. The supervision 120 for electronic documents is configured to compare data of the created template with data from electronic documents of a second sample. The data of the second electronic sample documents may be included in templates created for the electronic sample documents. Thus, the comparison can be made with respect to data of certain fields in the templates.

Based on the comparison is the monitoring 120 for electronic documents configured to identify abnormalities in data values of the electronic input document. For example, an abnormality may be an unusual value for the price specified in the electronic input documents compared to the prices given in the electronic sample documents. The abnormalities may be identified by determining deviations of data values of the input electronic document from, for example, average values of the electronic sample documents above a threshold. The threshold may be a predetermined threshold and may be a threshold (a number, a character or a word) or may be a threshold proportion (eg, plus or minus 5% of the average).

In one embodiment, the monitoring is 120 for electronic documents, to create records based on electronic documents that contain data that at least partially lacks a known structure (eg, unstructured data, semi-structured data, or structured data having an unknown structure). For this purpose, the monitoring 120 for electronic documents, further configured to use optical character recognition (OCR) or other image processing to determine data in the electronic document. The electronic document monitoring 120 Therefore, a recognition processor (eg, the recognition processor 235 . 2 ) or communicate with it.

The electronic document monitoring 120 is configured to analyze the generated records to identify transaction parameters related to transactions specified in the electronic documents. Based on the transaction parameters of the created records, electronic document monitoring is configured to create a template for each analyzed electronic document. Each template is a structured record containing the identified transaction parameters for a transaction.

The use of structured templates to detect abnormalities enables more efficient and accurate identification of abnormalities than, for example, by using unstructured data. In particular, parts of an input electronic document can only be compared to corresponding parts of electronic sample documents (eg, parts contained in certain fields of a structured template), thereby reducing the amount of data to be compared and false positives due to the comparison of non-contiguous data. In addition, data extracted from electronic documents and organized into templates require less memory than, for example, images of scanned documents.

Based on the template that was created for the entered electronic document, the monitoring 120 for electronic documents to be configured to retrieve the electronic sample documents to be compared. Retrieving the electronic sample documents may be searching in the enterprise system 130 based on data in the template of the electronic input document. As a non-limiting example, when data in the template of the electronic input document indicates a purchase from a particular seller, the electronic sample documents may be retrieved by searching for the seller. In another non-limiting example, if data in the template of the input electronic document indicates a purchase of a particular commodity type, the electronic sample documents may be retrieved by searching for the commodity type.

In yet another embodiment, the monitoring 120 for electronic documents, further configured to validate the input electronic document based on the created template for the input electronic document. The validation may include, but is not limited to, determining whether each of the input electronic documents is complete.

The input electronic document may be determined to be complete if, for example, one or more predetermined required fields of the template contain data. For example, if at least one time, a seller ID, and a price field of the template created for the electronic input document contain data, the electronic input document may be complete.

It should be noted that the embodiments described hereinabove with reference to FIG 1 described in relation to a business system 130 are described for simplicity and without limitation of the disclosed embodiments. Multiple enterprise systems may be equally used without departing from the scope of the disclosure. Different groups of sample documents can be used for different companies, ensuring the accuracy and security of data comparisons.

2 is an exemplary schematic diagram of electronic document monitoring 120 according to one embodiment. The electronic document monitoring 120 includes a processing circuit 210 that with a memory 215 , a mass storage 220 and a network interface 240 is coupled. In one embodiment, the monitoring 120 for electronic documents an optical character recognition (OCR) processor 230 contain. The components of electronic document monitoring 120 can over a bus 250 be communicatively connected.

The processing circuit 210 may be implemented as one or more hardware logic components and circuits. By way of example and not limitation, illustrative types of hardware logic components that may be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on a chip systems (SOCs), general purpose Micro-processors, microcontrollers, digital signal processors (DSPs) and the like or any other hardware logic components that can perform calculations or other manipulations of information.

The memory 215 may be volatile (eg, RAM, etc.), non-volatile (eg, ROM, flash memory, etc.), or a combination thereof. In one configuration, computer-readable instructions for implementing one or more embodiments disclosed herein in the mass storage 220 be saved.

In another embodiment, the memory is 215 configured to store software. Software should generally be understood to mean any type of instructions, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. Instructions may include code (eg, in source code format, binary code format, executable code format, or any other suitable code format). The instructions, when executed by one or more processors, cause the processing circuitry 210 to carry out the various methods described herein. Specifically, the instructions, when executed, cause the processing circuitry 210 to monitor electronic documents as discussed herein.

The mass storage 220 may be a magnetic memory, an optical memory, and the like, and may be implemented, for example, as flash memory or other storage technology, CD-ROMs, digital versatile disks (DVDs), or any other medium that may be used to provide the desired information to save.

The OCR processor 230 may, but is not limited to, a feature and / or pattern recognition processor (RP). 235 which is designed to identify patterns, features, or both in unstructured datasets. In particular, the OCR processor 230 in one embodiment, configured to identify at least characters in the unstructured data. The identified characters can be used to create a record containing data needed to verify a request.

The network interface 240 enables electronic document monitoring 120 , with the enterprise system 130 , the database 140 , the data sources 150 or a combination thereof, for example, to retrieve and receive electronic documents, store data and send notifications, and the like.

It should be understood that the embodiments described herein are not limited to those described in U.S. Pat 2 are limited to specific architectures, and other architectures may equally be used without departing from the scope of the disclosed embodiments.

3 is an exemplary flowchart 300 , which is a method for monitoring electronic documents according to an embodiment. In one embodiment, the method may be of monitoring 120 for electronic documents.

at S310 A record is created based on an electronic input document with information related to a transaction. The electronic input document may include, but is not limited to, unstructured data, semi-structured data, structured data having a structure that is not foreseen or unannounced, or a combination thereof. In an exemplary implementation, the electronic input document may be an electronic invoice. For example, the record may include a transaction amount of $ 100, a time stamp indicating the date of January 1, 2016, and a name of a supplier, "ABC Shipping Co."

In one embodiment S310 analyzing the input electronic document using optical character recognition (OCR) to determine data in the input electronic document, identifying key fields in the data, identifying values in the data, or a combination thereof. The creation of records based on electronic documents will be described herein below with reference to 4 described.

at S320 the record of the entered electronic document is analyzed. In one embodiment, analyzing the input data set may include, but is not limited to, determining transaction parameters, such as at least one entity identifier (eg, a consumer business identifier, a merchant company identifier, or both), information related to the transaction (e.g. Date, time, price, type of goods or services sold, etc.) or both. In an exemplary implementation, the determined transaction parameters include at least one transaction amount (eg, a price, an amount, or both), a time indication, and a vendor identifier (eg, a name or an identification number). For example, the transaction parameters may include the transaction amount, the time reference, and the name of the supplier.

at S330 A template is created based on the record of the input electronic document. The template may be a data structure that includes, but is not limited to, a variety of fields. The fields may contain the identified transaction parameters. The fields can be predefined.

Creating templates from electronic documents allows faster processing due to the structured nature of the templates created. For example, query and manipulation operations can be performed more efficiently on structured datasets than datasets lacking such a structure. When organizing information from electronic documents into structured records, the space required to store information contained in electronic documents can be significantly reduced. Electronic documents are often images that require more memory than data sets that contain the same information. For example, records representing data from 100,000 electronic image documents can be stored as records in a text file. The size of such a text file would be considerably smaller than the size of the 100,000 images.

at S340 For example, data from the created electronic input document template is compared to data associated with multiple electronic sample documents to identify one or more abnormalities in the electronic input document. The abnormalities can be unusual data values in the template created for the electronic input document. Each of the electronic sample documents contains data of a transaction. In an exemplary implementation, the electronic sample documents contain images that show scanned bills for a company's past transactions.

The data of the created template may be directly compared with corresponding data of the set of electronic sample documents or may be compared to one or more representative data for the group of electronic sample documents. The representative data may include, but is not limited to, an average, standard deviation, median, mode, and the like.

The input electronic document template data may be compared to data from one or more selected groups of electronic sample documents (eg, a group selected from a database of electronic sample documents), whereby abnormalities with respect to various normal sample data values may be identified. For example, data of the input electronic document may be compared with a first group of electronic sample documents showing transactions relating to a particular seller and a second group of electronic sample documents showing transactions for the same product.

Identifying anomalies in an input electronic document based on data from electronic Sample documents will be discussed below with reference to 5 described.

If one or more abnormalities are identified in S350, a warning is generated. The alert can indicate the identified abnormalities and the conspicuous electronic input document. For example, the warning may be sent to the enterprise system 110 . 1 , or a user device that is associated with a company. If in some implementations S340 has led to a null value (that is, if no abnormalities have been detected), a warning may not be generated.

In S360 A check is made as to whether additional electronic input documents should be analyzed for abnormalities, and if so, the execution is called S310 continued. Otherwise the execution is terminated. In some implementations, electronic input documents can be monitored in real-time for abnormalities as they are received, so that abnormalities are identified and alarms are generated almost immediately after receipt of new electronic input documents.

By way of non-limiting example, an electronic bill is presented which illustrates the purchase of cocoa beans by a confectionery company. A record will be created with an amount of 340 USD paid for the cocoa beans, a time stamp dated 9 February 2016 and the seller's name "Bean Harvesters, Inc.". The record is analyzed to determine the transaction parameters in the record. A template with the determined transaction parameters is created. The template contains the "Purchase Price," "Purchase Date" and "Seller Name" fields, with each field containing the respective transaction parameters, which are related to the price of $ 340, the date of February 9, 2016 and the name "Bean Harvesters, Inc . ".

The price of $ 340 is compared to an average price of $ 125 associated with a group of electronic sample documents showing purchases by Bean Harvesters in December 2015 and January 2016. The electronic sample documents include purchase prices of $ 114, $ 117, $ 125, $ 133 and $ 136, respectively. Based on the comparison, it is found that the price of the purchase on February 9, 2016 above a threshold of $ 100 deviates from the average price and therefore an unusual price was determined. A warning message is generated stating that the 9 February 2016 invoice is unusual and will be sent for review.

4 is an exemplary flowchart S310 , which illustrates a method for generating a data set based on an electronic document according to an embodiment.

at S410 the electronic document is received. However, retrieving the electronic document may include receiving the electronic document (e.g., receiving a scanned image) or retrieving the electronic document (eg, retrieving the electronic document from a consumer enterprise system, a merchant company system, or a database) not limited to this.

at S420 the electronic document is analyzed. The analysis may include the use of optical character recognition (OCR) to determine characters in the electronic document.

at S430 Identify key fields and values in the electronic document based on the analysis. The key field may include, but is not limited to, the name and address of the merchant, date, currency, merchandise or service being sold, a transaction identifier, an invoice number, and so forth. An electronic document can contain unnecessary details that are not considered key-values. As an example, a logo of the merchant may not be required and is therefore not a key value. In one embodiment, a list of key fields may be predefined, and data items that may correspond to the key fields are extracted. Then a cleaning process is performed to ensure that the information is accurately presented. For example, if the OCR would result in data represented as "1211212005," the cleaning process will convert that data to 12/12/2005. As another example, if a name is represented as "Mo $ den", it changes to "Mosden." The cleaning process may be performed using external information resources such as dictionaries, calendars, and the like.

In a further embodiment, it is checked whether the extracted data parts are complete. For example, if the merchant name can be identified but its address is missing, the key field for the merchant address is incomplete. An attempt is made to complete the missing key field values. This experiment may involve querying external systems and databases, correlating with previously analyzed invoices, or a combination thereof. Examples of external systems and databases may include business directories, universal product code (UPC) databases, and tracking systems and so on. In one embodiment S430 to a complete set of predefined key fields and their respective values.

at S440 a structured record is created. The structured record contains the identified key fields and values.

5 is an exemplary flowchart S340 , which illustrates a method for identifying anomalies based on a template created for an electronic input document according to an embodiment.

at S510 electronic sample documents or templates for electronic sample documents are retrieved. The electronic sample documents can be retrieved based on data specified in one or more fields of the template created for the electronic input document.

In an exemplary implementation, each retrieved set of electronic sample documents may contain electronic documents related to the same merchant, the same type of purchased goods or services, the use of the same payment method (eg, a particular credit card number), periods of time Combination thereof (for example, electronic documents indicating the same dealer's purchases in the first week of each month) and the like. Comparing data from an input electronic document with data from electronic sample documents using common parameters may allow for increased efficiency in detecting abnormalities when the common parameter is likely to indicate consistent sample data. For example, it can be expected that purchases from the same merchant will be consistently at the same price, so if previous purchases from a particular merchant have an average price of $ 1,000 for the company, a purchase price of $ 1,400 from that merchant will indicate an abnormality can. The data of the input electronic document can be compared with data from several groups of electronic sample documents, which can identify abnormalities regarding various potential sources of abnormalities and thus a more complete set of abnormalities for the electronic input document.

For this purpose can S510 in one embodiment, searching based on data in the template for an input electronic document in one or more data sources for the electronic sample documents with which the input electronic document is to be compared. As a non-limiting example, a merchant identification number "12345" indicated in a "Merchant ID" field of the submission of the input electronic document may be used as a search query to retrieve the electronic specimen documents based on, for example, metadata of the electronic specimen documents to find the merchant identification number "12345". As a result, only data of electronic sample documents for transactions concerning the same merchant is compared with the input electronic document.

In the optional step S520 a template can be created for each electronic sample document. Each template is a structured electronic document with the transaction parameters specified in the electronic sample document. Creating electronic sample document templates can save on computational resources because the templates require less memory to save than the original electronic sample documents, such as image files.

at S530 Data of the input electronic document is compared with data of each group of electronic sample documents. The comparison of data of the created templates of the electronic sample documents with data of the input electronic document enables a more efficient comparison of data than for example by comparing unstructured or otherwise unorganized data. In particular, data relative to particular fields of the templates may be compared rather than, for example, all data of the input electronic document with all data of the groups of electronic sample documents. In an exemplary implementation, data displayed in a "Price" field, in a "Quantity" field, or both, of the input electronic document may be compared to corresponding data of the electronic sample documents. The corresponding data may include data indicated in corresponding fields of the electronic sample document templates or data otherwise representative of the electronic sample documents (eg, averages, most frequently occurring values, averages, and the like). For this purpose, S530 may include selecting one or more representative values of the electronic sample documents for comparison with one or more corresponding values of the template of the electronic input document based on the fields including the corresponding values of the input electronic document.

at S540 Based on the comparison, one or more abnormalities can be identified. The abnormalities may be identified based on one or more thresholds, and different thresholds may be applied, e.g. For example, different compared transaction parameters (eg, a price threshold may differ from a threshold for the quantity). If the comparison did not show any deviations above the respective thresholds, S540 may result in a null value (ie indicating no abnormality).

Each conspicuousness is identified based on a deviation of a transaction parameter of the input electronic document from the transaction parameters of one of the groups of electronic sample documents above the threshold. The threshold may be a value (eg, a number, a word, a character, etc.), a share, and the like. The deviation may be determined based on a deviation from one of the values of one of the electronic sample documents, or may be determined based on a deviation from an average or otherwise representative value for the electronic sample documents. For example, for an average of 2000 watermelons ordered per month, as indicated in "number" fields of the electronic sample documents, a template of an electronic document indicating 10,000 watermelons in a "quantity" field may indicate a discrepancy and thus a conspicuousness.

It should be understood that any reference to an element herein using a term such as "first," "second," etc. generally does not limit the amount or order of those elements. Rather, these terms are generally used herein as a convenient method of distinguishing between two or more elements or instances of an element. A reference to the first and second elements therefore does not mean that only two elements may be used there, or that the first element must in some way be in front of the second element. Unless otherwise stated, a set of elements includes one or more elements.

As used herein, the term "at least one of" followed by a list of elements means that each of the listed elements may be used individually, or any combination of two or more of the listed elements may be used. For example, when it is described that a system includes "at least one of A, B and C", the system can only contain A; B alone; C alone; A and B in combination; B and C in combination; A and C in combination; or A, B and C in combination.

The various embodiments disclosed herein may be implemented as hardware, firmware, software, or any combination thereof. Moreover, the software is preferably implemented as an application program concretely embodied on a program storage device or computer readable medium consisting of parts or particular devices and / or a combination of devices. The application program can be uploaded to and executed by a machine with a suitable architecture. Preferably, the machine is implemented on a computer platform that includes hardware, such as one or more central processing units ("CPUs"), memory, and input / output interfaces. The computer platform may also include an operating system and a microcode. The various methods and functions described herein may be either part of the microcode or part of the application program, or any combination thereof that may be executed by a CPU, whether or not such computer or processor is explicitly shown. In addition, various other peripheral units may be connected to the computer platform, such as an additional data storage unit and a printing unit. In addition, a non-transitory computer readable medium is any computer readable medium except a transitory propagation signal.

All examples and conditions cited herein are for educational purposes to assist the reader in understanding the principles of the disclosed embodiment and concepts contributed by the inventor to promote the prior art, and are to be construed without limitation to such specific examples and conditions. In addition, all statements contained herein, embodying principles, aspects, and embodiments of the disclosed embodiments, as well as specific examples thereof, are intended to encompass both structural and functional equivalents thereof. In addition, it is intended that such equivalents include both currently known equivalents and equivalents developed in the future, i. H. all developed elements that perform the same function regardless of the structure.

QUOTES INCLUDE IN THE DESCRIPTION

This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• US 62371234 [0001]
• US 15361934 [0001]

Claims (19)

A method of monitoring electronic documents, comprising: Analyzing a first electronic document to determine at least one transaction parameter, the first electronic document containing at least partially unstructured data; Creating a template for the first electronic document, wherein the created template is a structured data set containing the determined at least one transaction parameter; and Comparing data of the created template with data associated with a plurality of second electronic documents to identify at least one abnormality in the first electronic document. Method according to Claim 1 wherein determining the at least one transaction parameter further comprises: identifying at least one key field and at least one value in the first electronic document; Creating a record based on the first electronic document, wherein the created record includes the at least one key field and the at least one value; and analyzing the created dataset, wherein the at least one transaction parameter is determined based on the analysis. Method according to Claim 2 wherein identifying the at least one key field and the at least one value further comprises: analyzing the first electronic document to determine data in the first electronic document; and extracting at least a portion of the determined data based on a predetermined list of key fields, wherein the at least one portion of the determined data matches at least one key field of the predetermined list of key fields. Method according to Claim 3 wherein analyzing the first electronic document further comprises: performing optical character recognition on the first electronic document. Method according to Claim 1 wherein comparing data of the created template with data associated with a plurality of second electronic documents further comprises: comparing a first value of the at least one transaction parameter with a second value associated with the plurality of second electronic documents identifying an abnormality if the difference between the first value and the second value satisfies at least one threshold. Method according to Claim 5 , wherein the second value is selected for comparison based on the field of the template containing the first value. Method according to Claim 1 , further comprising: generating an alarm indicating the identified at least one abnormality. Method according to Claim 1 wherein the at least one transaction parameter includes a transaction amount, a time indication, and a vendor identifier, wherein the at least one abnormality includes an unusual value of the transaction amount compared to transaction amounts specified in the second electronic documents. Method according to Claim 1 where each electronic document is an electronic invoice. A non-transitory computer readable medium having instructions stored thereon for causing a processing circuit to perform a method, the method comprising: analyzing a first electronic document to determine at least one transaction parameter, the first electronic document containing at least partially unstructured data; Creating a template for the first electronic document, wherein the created template is a structured data set containing the determined at least one transaction parameter; and comparing data of the created template with data associated with a plurality of second electronic documents by at least one of Identify conspicuousness in the first electronic document. A system for validating a transaction represented by an electronic document, comprising: a processing circuit; and a memory, the memory including instructions that, when executed by the processing circuitry, configure the system to: analyzing a first electronic document to determine at least one transaction parameter, the first electronic document containing at least partially unstructured data; creating a template for the first electronic document, wherein the created template is a structured data set containing the determined at least one transaction parameter; and Data of the created template are compared with data associated with a plurality of second electronic documents to identify at least one abnormality in the first electronic document. System after Claim 11 wherein the system is further configured to: identify at least one key field and at least one value in the first electronic document; Creating, based on the first electronic document, a record, the created record including the at least one key field and the at least one value; and analyzing the created record, wherein the at least one transaction parameter is determined based on the analysis. System after Claim 12 wherein the system is further configured to: analyze the first electronic document to determine data in the first electronic document; and extracting, based on a predetermined list of key fields, at least a portion of the determined data, wherein the at least a portion of the determined data matches at least one key field of the predetermined list of key fields. System after Claim 13 wherein the system is further configured to: perform optical character recognition on the first electronic document. System after Claim 11 wherein the system is further configured to: compare a first value of the at least one transaction parameter to a second value associated with the plurality of second electronic documents, wherein an abnormality is detected when the difference between the first value and the second value is at least one Threshold met. System after Claim 15 , wherein the second value is selected for comparison based on the field of the template containing the first value. System after Claim 11 wherein the system is further configured to: retrieve the plurality of second electronic documents based on the at least one transaction parameter. System after Claim 11 wherein the system is further configured to: generate an alert indicating the identified at least one abnormality. System after Claim 11 wherein the at least one transaction parameter comprises a transaction amount, a time indication, and a vendor identifier, wherein the at least one abnormality includes an unusual value of the transaction amount compared to transaction amounts specified in the second electronic documents.

Images