Back to results
US 2021/0342920 A1Published application
Adaptively enhancing procurement data
AssigneeCoupa Software Incorporated
InventorsMicky G. Keck, Jeffrey T. Crowder, Sundaresan R. Kadayam, John M. Kitson, Mark W. Reed
Life of this patent
Estimating the term…
Abstract
Embodiments disclosed herein may provide capabilities for multi-source data gathering, adaptive item cross referencing, data preparation and data extraction. These capabilities may allow the creation item master records which can provide richer information than available from any one discrete source. Additional functionality which may be provided in some embodiments could also include providing commodity based predictive pricing and/or a visual spend map.
Claims17
A computer-implemented method comprising:
- obtaining, via upload to a computer system or from live data sources, a plurality of unstructured purchase data having as mandatory fields only line item title, date, and spend amount, the purchase data being related to purchases of a plurality of items in a plurality of commodity groups and offered by a plurality of suppliers;
- for each purchase line item represented in the purchase data, the computer system executing:
- determining a plurality of field-level data quality scores for a plurality of data fields in each purchase line item;
- weighting the plurality of field-level data quality scores;
- determining a row-level quality score based on a sum of the weighted field-level data quality scores;
- based on the row-level quality score, enriching the purchase line item in the purchase data based on product attributes obtained from an item master database, to form an enriched purchase dataset;
- processing the enriched purchase dataset using a hierarchical classifier using additional semantic data elements to output a series of natural spend clusters corresponding to product categories represented in the enriched purchase dataset;
- displaying the natural spend clusters in a treemap visualization of a graphical user interface of a computer display device;
- in response to user input via a control device to select a particular cluster in the visualization and to drag the particular cluster to another cluster, combining the particular cluster and the another cluster, and automatically morphing the visualization to reflect the combining.
6 more elements
A computer-implemented method comprising:
- using a processor, crawling a plurality of data sources selected from among manufacturer data, retail website data, UPC data, open-source catalog data sources, and retailer data dumps to obtain unstructured item data from the plurality of data sources, the item data being related to a plurality of items in a plurality of commodity groups and offered by a plurality of suppliers;
- creating a plurality of intermediate data records having a structured form and populated with the unstructured item data from the plurality of data sources;
- determining that at least one of the plurality of items is offered by both a first supplier and a second supplier of the plurality of suppliers based on identification information associated with the at least one item, the at least one item offered by the first supplier being associated with a field value that does not match a corresponding field value of the at least one item offered by the second supplier;
- determining that the field value associated with the at least one item offered by the first supplier has a data quality score higher than a data quality score of the corresponding field value of the at least one item offered by the second supplier;
- creating a master record comprising a plurality of item records from the intermediate data records, each of the plurality of item records having one or more values for one or more of a plurality of predefined attributes, a first item record of the plurality of item records corresponding to the at least one item offered by the first and second suppliers and having a value of the one or more values that corresponds to the field value associated with the at least one item offered by the first supplier;
- defining baskets representing common items in a plurality of commodity groups, each basket defining at least twenty items;
- tracking, by the processor, pricing for each item of the items in the baskets for multiple suppliers and averaging the pricing for each supplier to yield a blended price for the basket;
- tracking percentage changes in the blended price for each of the baskets;
- using the blended price for each of the baskets and the percentage changes to create a predictive model to estimate likely price changes over time;
- receiving a request to add a specific item of the items in one of the baskets to a purchase list associated with a user account;
- determining, for the specific item, an expected price trend based on the predictive model;
- displaying, in a graphical user interface, a visual indicator specifying that a lower price is predicted and presenting an option to choose a certain item from the set of items to add to the purchase list or to replace the specific item in the purchase list.
9 more elements
Dependencies are inferred from the claim text.