Coupa Software Incorporated

In an embodiment, a system disclosed herein receives input information relating to an unmanned aerial vehicle, ground delivery assets, and user preferences or configurations for delivery routes. The system processes the inputted information and determines an optimized delivery route that utilizes the unmanned aerial vehicle and the ground delivery assets. In an embodiment, a computer-implemented method, comprises accessing a drone definition table and a drone assignment table of a database system; accessing digitally stored delivery route data specifying a plurality of nodes connected by edges, the nodes being ordered from a starting point to a last node, wherein each of the nodes represents a delivery location, wherein each of the nodes comprises a service attribute specifying ground-only delivery or ground/drone delivery; selecting, from the delivery route data, a particular node having the service attribute specifying ground/drone delivery and that is next in order with respect to the starting point; removing the particular node from the delivery route data; determining a drone flight time associated with a distance, from a preceding node to a subsequent node, with respect to the particular node; based on the drone definition table and the drone assignment table, determining whether the drone flight time exceeds a maximum drone flight time of a particular drone; in response to determining that the drone flight time exceeds the maximum drone flight time, restoring the particular node in the delivery route data; and, otherwise, writing, to one or more sortie tables in the database, one or more sortie records corresponding to a sortie of the particular drone that can occur between the preceding node and the subsequent node; repeating the selecting, removing, determining, restoring, and writing steps for a plurality of other particular nodes in the delivery route data having the service attribute specifying ground/drone delivery.

The computer-implemented method utilizes machine learning models to classify input data records. The method includes selecting machine learning models from a plurality of machine learning models using a router model and generating classification inferences for each selected model. The classification inferences include factors indicating the probability of the input data record belonging to various candidate classes. Any one of the plurality of machine learning models is configured to use a weight matrix calculated as the sum of a base weight matrix and a model-associated difference matrix obtained as a product of two low-rank matrices. The classification inferences from selected models are then combined to create an overall classification inference, providing factors related to the probability of the input data belonging to each candidate class. This method enables effective classification by leveraging multiple machine learning models.

A computer-implemented method for validating supplier data is provided. The method includes accessing a spend management interface of a spend management system. The spend management interface may receive supplier data from a supplier computer via user interface widgets of the spend management interface. A country identifier is received from the supplier computer via a country widget and a currency identifier is received via a currency widget of the user interface widgets. One or more parameters associated with the country identifier and currency identifier are identified within a validation database of the spend management system and customized user interface widgets are generated based on the one or more parameters. The spend management interface is electronically updated to present the customized user interface widgets to the supplier computer. Supplier data is received from the supplier computer via the customized user interface widgets and the supplier data is programmatically validated.

The present disclosure provides for a method of automatically updating a digitally stored model of an electronic contract over the lifetime of a contract, including a step of receiving an update to an attribute of a digitally stored contract model. Further, retrieving, from a digital data store, model description data and a plurality of answer values. Based on the model description data and answer values, creating a graph of answer data and variables required in the electronic contract as nodes and edges, where nodes represent the answer data and variables, and edges represent dependencies of the nodes. Next, removing edges that are determined from first variables to second variables that the first variables had been declared as using. From the update to the attributes of the contract model, removing one or more nodes corresponding to the one or more variables that are not directly referenceable by the document.

A computer implemented method comprising receiving invoice data comprising at least one of invoice descriptions and invoice characters from user computers, each of the invoice descriptions and invoice characters defines contexts and patterns, wherein each of the invoice data comprising a supplier-customer information that corresponds to a supplier-customer transaction; analyzing the at least one of the invoice descriptions and the invoice characters with corresponding contexts and patterns; determining that amount of the invoice characters is more than a threshold number of characters, for performing: matching invoice data, invoice characters with predefined historical invoice data that corresponds to the same supplier-customer information; computing a similarity score for each of the invoice data; and displaying recommendations including first account codes to map the one or more first account codes to each of the one or more invoice data based on the similarity score; determining that amount of the invoice characters is not more than the threshold number of characters, for performing: filtering the invoice descriptions of the invoice data based on predetermined constraints to extract filtered invoice data comprising filtered description lines; identifying categories associated with each of the filtered description lines of the filtered invoice data; matching each of the identified categories, including corresponding contexts and patterns that is 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 are matched with predefined contexts and patterns of the predefined historical invoice data that corresponds to the same supplier-customer information; computing a categorical similarity score for each of the categories associated with the supplier-customer information; and displaying on the graphical user interface, second recommendations including second account codes based on the computed categorical similarity score of each of the categories to map the second account codes to the invoice data.

Commodity category values can be determined automatically for suppliers in an e-procurement system using a computer-implemented process that is supplier-focused and uses successive heuristics, supplemented with machine learning models that predict category and subcategory values based on supplier names and invoice descriptions. Embodiments can support community intelligence applications to enable buyer computers to query and obtain lists of suppliers corresponding to categories and to generate graphs or charts that aggregate historic invoice data based on canonical category values that have been determined for suppliers.

Input data provides an order of the quantity of finished goods to a site. Software is programmed for: accessing data defining an architecture of the supply chain network with sites, and a location of each site; enumerating one or more path solutions along the supply chain network to fulfill the order, each path solution comprising path fragments connecting two sites, a path fragment defining movement of a sub-quantity of the finished goods or raw materials; determining a cost associated with each of the plurality of path fragments, the cost comprising a duty rate, the duty rate associated with a particular path fragment based on the locations of the two sites connected by the particular path fragment and the sub-quantity of the finished goods or finished goods raw materials moved between the two sites; determining one or more optimal path solutions; and outputting the optimal path solutions for display.

A computer-implemented method for validating supplier data is provided. The method includes accessing a spend management interface of a spend management system. The spend management interface may receive supplier data from a supplier computer via user interface widgets of the spend management interface. A country identifier is received from the supplier computer via a country widget and a currency identifier is received via a currency widget of the user interface widgets. One or more parameters associated with the country identifier and currency identifier are identified within a validation database of the spend management system and customized user interface widgets are generated based on the one or more parameters. The spend management interface is electronically updated to present the customized user interface widgets to the supplier computer. Supplier data is received from the supplier computer via the customized user interface widgets and the supplier data is programmatically validated.

The present disclosure provides for a method of automatically updating a digitally stored model of an electronic contract over the lifetime of a contract, including a step of receiving an update to an attribute of a digitally stored contract model. Further, retrieving, from a digital data store, model description data and a plurality of answer values. Based on the model description data and answer values, creating a graph of answer data and variables required in the electronic contract as nodes and edges, where nodes represent the answer data and variables, and edges represent dependencies of the nodes. Next, removing edges that are determined from first variables to second variables that the first variables had been declared as using. From the update to the attributes of the contract model, removing one or more nodes corresponding to the one or more variables that are not directly referenceable by the document.

A computer-implemented method is disclosed. The method includes obtaining a candidate pair of a plurality of digitally stored documents from a document database. The method automatically computes relative positional differences between each digitally stored document of the candidate pair. The method compares the relative positional differences with a similarity function to form a difference similarity vector for the candidate pair. The difference similarity vector includes components corresponding to each relative positional difference. The method aggregates the components of the difference similarity vector to determine a final score for the candidate pair. The method determines a document-level similarity metric from the final score. The method determines whether the document-level similarity metric is above a threshold value and then classifies the candidate pair based on determining that the document-level similarity metric is above the threshold value to de-duplicate the plurality of digitally stored documents in the candidate pair.