US 12,462,311 B2
Systems and methods for automatically recommending account codes
Hongyang Yu, Sydney (AU); Sandip Mandlecha, Pune (IN); Tim Durkin, Daly City, CA (US); Neha Arora, San Mateo, CA (US); Rebecca Mengell, Dublin, CA (US); Shashank Dass, Castro Valley, CA (US); and Keeyoung Kim, Seoul (KR)
Assigned to Coupa Software Incorporated, Foster City, CA (US)
Filed by COUPA SOFTWARE INCORPORATED, San Mateo, CA (US)
Filed on Nov. 29, 2022, as Appl. No. 18/070,930.
Prior Publication US 2024/0177244 A1, May 30, 2024
Int. Cl. G06Q 40/12 (2023.01)
CPC G06Q 40/12 (2013.12) 18 Claims
OG exemplary drawing
 
1. A computer implemented method of detecting account codes and displaying the detected account codes on a graphical user interface comprising:
receiving, by a recommendation engine of a recommendation system communicatively coupled over a data communication network, one or more invoice data comprising at least one of one or more invoice descriptions and one or more invoice characters from one or more user computers, each of the one or more invoice descriptions and the one or more invoice characters defines contexts and patterns, wherein each of the one or more invoice data comprising a supplier-customer information that corresponds to a supplier-customer transaction;
analyzing, by the recommendation engine, the at least one of the one or more invoice descriptions and the one or more invoice characters associated with the corresponding contexts and patterns;
determining, by the recommendation engine, that an amount of the one or more invoice characters is more than a preset threshold number of characters based on the analysis, for performing:
matching, by the recommendation engine, each of the one or more invoice data, comprising the one or more invoice characters, that is associated with a supplier-customer information with one or more predefined historical invoice data that corresponds to the same supplier-customer information, wherein each of the contexts and the patterns associated with each of the one or more invoice data is matched with one or more predefined contexts and patterns of the one or more predefined historical invoice data that corresponds to the same supplier-customer information;
computing, by the recommendation engine, a similarity score for each of the one or more invoice data associated with the supplier-customer information based on the matching with the one or more predefined historical invoice data that corresponds to the same supplier-customer information; and
displaying, by the recommendation engine on the graphical user interface, one or more first recommendations including one or more first account codes based on the computed similarity score of each of the one or more invoice data that is corresponding supplier-customer information to map the one or more first account codes to each of the one or more invoice data based on the similarity score;
determining, by the recommendation engine, that an amount of the one or more invoice characters is not more than the preset threshold number of characters based on the analysis, for performing:
filtering, by the recommendation engine, the one or more invoice descriptions of the one or more invoice data based on predetermined constraints to extract one or more filtered invoice data comprising filtered description lines and to generate a training corpus for a pre-trained Natural Language Processing (NLP) model;
identifying, by the recommendation engine, one or more categories associated with each of the filtered description lines of the one or more filtered invoice data by classifying the filtered description lines with the pre-trained NLP model;
matching, by the recommendation engine, each of the identified one or more categories, including corresponding contexts and patterns that are associated with a supplier-customer information with one or more predefined historical categories associated with predefined invoice description of the one or more predefined historical invoice data that corresponds to the same supplier-customer information, wherein each of the contexts and the patterns associated with each of the filtered description lines of the one or more filtered invoice data is matched with one or more predefined contexts and patterns of the one or more predefined historical invoice data that corresponds to the same supplier-customer information;
computing, by the recommendation engine, a categorical similarity score for each of the one or more categories associated with the supplier-customer information based on the matching with the one or more predefined historical categories associated with the predefined invoice description that corresponds to the same supplier-customer information; and
displaying, by the recommendation engine on the graphical user interface, one or more second recommendations including one or more second account codes based on the computed categorical similarity score of each of the one or more categories to map the one or more second account codes to the one or more invoice data.