Purchase Order Matching

Abstract

An approach is provided for using a purchase order system to verify information on invoices. One or more text fields represented in invoice image data are compared to purchase order data from a purchase order system. If the one or more text fields represented in the invoice image data do not match the purchase order data from the purchase order system, then the one or more text fields represented in the invoice image data are designated for special processing. If the one or more text fields represented in the invoice image data match the purchase order data from the purchase order system, then the invoice is designated as verified. The approach also includes the ability for a user to supplement invoice data with additional data, such as codes used by business organizations, and for automatic correction of errors in text fields using data maintained by the purchase order system.

What is claimed is: 
     
         1 . One or more non-transitory computer-readable media storing instructions which, when processed by one or more processors, cause:
 retrieving invoice image data that represents an invoice;   obtaining one or more text fields represented in the invoice image data;   verifying the one or more text fields represented in the invoice image data by comparing the one or more text fields represented in the invoice image data to purchase order data from a purchase order system;   in response to determining that the one or more text fields represented in the invoice image data do not match the purchase order data from the purchase order system, then designating the one or more text fields represented in the invoice image data for special processing; and   in response to determining that the one or more text fields represented in the invoice image data match the purchase order data from the purchase order system, then:
 designating the invoice as verified, 
 generating and providing to a client device user interface data which, when processed at the client device, allow a user to add one or more additional text fields to the one or more text fields to generate revised text field data, and 
 transmit the revised text field data to an accounting system for processing. 
   
     
     
         2 . The one or more non-transitory computer-readable media of  claim 1 , wherein the one or more additional text fields include one or more of a cost code, a location code or a project code. 
     
     
         3 . The one or more non-transitory computer-readable media of  claim 1 , further storing additional instructions which, when processed by the one or more processors, causes:
 storing, as invoice data in association with invoice identification data that uniquely identifies the invoice, the one or more text fields represented in the invoice image data, and   generating and providing to a client device additional user interface data which, when processed at the client device, allow a user to search for and retrieve, based upon the invoice identification data that uniquely identifies the invoice, the one or more text fields represented in the invoice image data.   
     
     
         4 . The one or more non-transitory computer-readable media of  claim 1 , further storing additional instructions which, when processed by the one or more processors, causes:
 generating and providing to a client device additional user interface data which, when processed at the client device, allow a user to search for one or more candidate code values, wherein selection of a particular candidate code value from the one or more candidate code values causes the particular candidate code value to be included in the revised text field data.   
     
     
         5 . The one or more non-transitory computer-readable media of  claim 1 , wherein allowing a user to add one or more additional text fields to the one or more text fields to generate revised text field data includes presenting to the user for selection a plurality of codes that are specific to the user and in response to a selection by the user of one or more codes from the plurality of codes that are specific to the user, causing the selected one or more codes to be added to the one or more text fields to generate the revised text field data. 
     
     
         6 . The one or more non-transitory computer-readable media of  claim 1 , further storing additional instructions which, when processed by the one or more processors, causes:
 determining, based upon a semantic analysis performed on the one or more text fields represented in the invoice image data, one or more candidate code values,   the user interface data includes the one or more candidate code values, and   processing of the user interface data at the client device causes the one or more candidate code values to be displayed as user-selectable options which, when selected, are included in the revised text field data.   
     
     
         7 . The one or more non-transitory computer-readable media of  claim 1 , further storing additional instructions which, when processed by the one or more processors, causes:
 in response to determining that a particular text field represented in the invoice image data does not match the purchase order data from the purchase order system, then automatically correcting the particular text field based upon corresponding data from the purchase order system.   
     
     
         8 . The one or more non-transitory computer-readable media of  claim 1 , further storing additional instructions which, when processed by the one or more processors, causes:
 in response to determining that differences between a particular text field represented in the invoice image data and corresponding data in the purchase order data from the purchase order system exceed a threshold, then automatically correcting the particular text field based upon corresponding data from the purchase order system.   
     
     
         9 . An apparatus comprising:
 one or more processors; and   one or more memories storing instructions which, when processed by the one or more processors, cause:
 retrieving invoice image data that represents an invoice; 
 obtaining one or more text fields represented in the invoice image data; 
 verifying the one or more text fields represented in the invoice image data by comparing the one or more text fields represented in the invoice image data to purchase order data from a purchase order system; 
 in response to determining that the one or more text fields represented in the invoice image data do not match the purchase order data from the purchase order system, then designating the one or more text fields represented in the invoice image data for special processing; and 
 in response to determining that the one or more text fields represented in the invoice image data match the purchase order data from the purchase order system, then:
 designating the invoice as verified, 
 generating and providing to a client device user interface data which, when processed at the client device, allow a user to add one or more additional text fields to the one or more text fields to generate revised text field data, and 
 transmit the revised text field data to an accounting system for processing. 
 
   
     
     
         10 . The apparatus of  claim 9 , wherein the one or more additional text fields include one or more of a cost code, a location code or a project code. 
     
     
         11 . The apparatus of  claim 9 , wherein the one or more memories further store additional instructions which, when processed by the one or more processors, causes:
 storing, as invoice data in association with invoice identification data that uniquely identifies the invoice, the one or more text fields represented in the invoice image data, and   generating and providing to a client device additional user interface data which, when processed at the client device, allow a user to search for and retrieve, based upon the invoice identification data that uniquely identifies the invoice, the one or more text fields represented in the invoice image data.   
     
     
         12 . The apparatus of  claim 9 , wherein the one or more memories further store additional instructions which, when processed by the one or more processors, causes:
 generating and providing to a client device additional user interface data which, when processed at the client device, allow a user to search for one or more candidate code values, wherein selection of a particular candidate code value from the one or more candidate code values causes the particular candidate code value to be included in the revised text field data.   
     
     
         13 . The apparatus of  claim 9 , wherein allowing a user to add one or more additional text fields to the one or more text fields to generate revised text field data includes presenting to the user for selection a plurality of codes that are specific to the user and in response to a selection by the user of one or more codes from the plurality of codes that are specific to the user, causing the selected one or more codes to be added to the one or more text fields to generate the revised text field data. 
     
     
         14 . The apparatus of  claim 9 , wherein the one or more memories further store additional instructions which, when processed by the one or more processors, causes:
 determining, based upon a semantic analysis performed on the one or more text fields represented in the invoice image data, one or more candidate code values,   the user interface data includes the one or more candidate code values, and   processing of the user interface data at the client device causes the one or more candidate code values to be displayed as user-selectable options which, when selected, are included in the revised text field data.   
     
     
         15 . The apparatus of  claim 9 , wherein the one or more memories further store additional instructions which, when processed by the one or more processors, causes:
 in response to determining that a particular text field represented in the invoice image data does not match the purchase order data from the purchase order system, then automatically correcting the particular text field based upon corresponding data from the purchase order system.   
     
     
         16 . The apparatus of  claim 9 , wherein the one or more memories further store additional instructions which, when processed by the one or more processors, causes:
 in response to determining that differences between a particular text field represented in the invoice image data and corresponding data in the purchase order data from the purchase order system exceed a threshold, then automatically correcting the particular text field based upon corresponding data from the purchase order system.   
     
     
         17 . A computer-implemented method comprising:
 retrieving invoice image data that represents an invoice;   obtaining one or more text fields represented in the invoice image data;   verifying the one or more text fields represented in the invoice image data by comparing the one or more text fields represented in the invoice image data to purchase order data from a purchase order system;   in response to determining that the one or more text fields represented in the invoice image data do not match the purchase order data from the purchase order system, then designating the one or more text fields represented in the invoice image data for special processing; and   in response to determining that the one or more text fields represented in the invoice image data match the purchase order data from the purchase order system, then:
 designating the invoice as verified, 
 generating and providing to a client device user interface data which, when processed at the client device, allow a user to add one or more additional text fields to the one or more text fields to generate revised text field data, and 
 transmit the revised text field data to an accounting system for processing. 
   
     
     
         18 . The computer-implemented method of  claim 17 , wherein allowing a user to add one or more additional text fields to the one or more text fields to generate revised text field data includes presenting to the user for selection a plurality of codes that are specific to the user and in response to a selection by the user of one or more codes from the plurality of codes that are specific to the user, causing the selected one or more codes to be added to the one or more text fields to generate the revised text field data. 
     
     
         19 . The computer-implemented method of  claim 17 , further comprising:
 determining, based upon a semantic analysis performed on the one or more text fields represented in the invoice image data, one or more candidate code values,   the user interface data includes the one or more candidate code values, and   processing of the user interface data at the client device causes the one or more candidate code values to be displayed as user-selectable options which, when selected, are included in the revised text field data.   
     
     
         20 . The computer-implemented method of  claim 17 , further comprising:
 in response to determining that a particular text field represented in the invoice image data does not match the purchase order data from the purchase order system, then automatically correcting the particular text field based upon corresponding data from the purchase order system.