Automated deal guide structure identification

Patent metadata

Field	Value
Publication number	US-10475083-B1
Application number	US-201314038629-A
Country	US
Kind code	B1
Filing date	Sep 26, 2013
Priority date	Sep 26, 2013
Publication date	Nov 12, 2019
Grant date	Nov 12, 2019

Abstract

A method, apparatus, and computer program product are disclosed for updating a structure database. The method includes accessing a corpus of machine readable text generated based on a plurality of promotions, wherein each of the plurality of promotions comprises at least one promotion option associated with at least one service, and extracting features from the promotion options, the features being mapped to services associated with respective promotion options from which the features are extracted. The method further includes identifying one or more components associated with the extracted features, tagging, using a processor, each promotion option with every component associated with at least one feature of the promotion option, and updating a structure database using the tagged promotion options. A corresponding apparatus and computer program product are also provided.

First claim

What is claimed is:

1. A method for providing a service configured to parse constituent elements of previously offered promotion options in order to provide foundational structures for populating and updating a structure database, the structure database configured for use in automatically generating and evaluating merits of future promotions to provide automatic approval thus enabling a merchant to quickly and efficiently generate promotion structures without delay of waiting on human approval, the method comprising:
accessing a corpus of machine readable text, by a processor from a structure database, the corpus of machine readable text generated from a plurality of promotions, wherein each of the plurality of promotions comprises at least one promotion option associated with at least one service, and wherein each promotion option is associated with one or more features and one or more first components, each of the one or more features comprising of one or more descriptive words, and the one or more components associated with a plurality of groupings of features, each of the plurality of groupings identified as being indicative of an equivalent meaning;
extracting, via the processor, a set of features from the promotion options, the set of features extracted according to a thematic concept, the set of features being extracted being those terms that occur with a frequency above a predefined threshold,
wherein the predefined thresholds for extracted single terms, bigrams, and trigrams are different,
wherein the predefined thresholds for extracting different n-gram terms is based on a statistical distribution of term frequency such that each threshold is a topmost quintile of single terms, bigrams, or trigrams within a particular service hierarchy, and
wherein the predefined threshold for extracted single terms being greater than the predefined threshold for trigrams, the features being mapped to services associated with respective promotion options from which the features are extracted;
based on the set of extracted features, identifying, via the processor, one or more components associated with at least one grouping of features matching a subset of the extracted features, wherein each component of the one or more components comprises a term or phrase that is equivalent to a group comprising a subset of the features;
tagging, via the processor, each promotion option with every component associated with at least one grouping of features matching the subset of the extracted features of the promotion option;
updating the structure database using the tagged promotion options such that tags associated with each promotion option are updated to include every component having been identified as associated with at least one grouping of features matching any of a plurality of subsets of the extracted features of the promotion option;
identifying a promotion option to provide to merchants, the identified promotion options comprising pricing bands, value bands, and discount bands, wherein the promotion option is identified by:
scoring the promotion option as a function of metric variables, a weighting of each metric variable being configurable and able to support different business objectives of the merchant; and
receiving a business objective of the merchant, the business objecting being at least one of eBPM (e-bookings per thousand featured engaged subscribers), ePPM (profit per thousand featured engaged subscribers), QPM (quantity per thousand featured engaged subscribers), and WAPP (a weighted average price point); and

periodically re-performing, via the processor, the accessing, extracting, tagging, and updating steps to include new promotion options upon approval and use of a new promotion to ensure maximal extraction of features as increased promotion data is generated for component construction.

2. The method of claim 1 , further comprising normalizing the promotion options prior to extracting the one or more features.

3. The method of claim 2 , wherein normalizing the promotion options comprises at least one operation selected from the group of:
removing stop words; and
substituting original words with equivalent standardized words.

4. The method of claim 1 , wherein extracting features from a target promotion option comprises:
analyzing a frequency with which single terms, bigrams, and trigrams occur in the target promotion option; and
extracting single terms, bigrams, and trigrams based on the frequency with which the single terms, bigrams, and trigrams occur in the target promotion option.

5. The method of claim 4 , wherein extracting single terms, bigrams, and trigrams comprises:
extracting a first number of most frequently occurring single terms;
extracting a second number of most frequently occurring bigrams; and
extracting a third number of most frequently occurring trigrams.

6. The method of claim 5 , wherein the first number, the second number, and the third number are equal to each other.

7. The method of claim 4 , wherein extracting single terms, bigrams,
and trigrams comprises extracting the single terms, bigrams, and trigrams that occur with frequencies that satisfy one or more predefined thresholds.

8. The method of claim 1 , wherein identifying the one or more components associated with the extracted features comprises:
selecting one or more components based on terms occurring among the extracted features;
defining groups of extracted features based on the selected one or more components; and
associating each extracted feature with one of the selected components based on the defined groups.

9. The method of claim 8 , wherein identifying the one or more components associated with the extracted features is performed by the processor.

10. The method of claim 1 , wherein updating the structure database using the tagged promotion options comprises, for each tagged promotion option:
generating a promotion structure comprising the tagged components;
associating the promotion structure with the at least one service associated with the tagged promotion option; and
storing the promotion option structure in the structure database.

11. The method of claim 10 , wherein generating the promotion structure further comprises developing a new title for the promotion structure based on at least one of term equivalencies, region, peer group, or market segment.

12. An apparatus for providing a service configured to parse constituent elements of previously offered promotion options in order to provide foundational structures for populating and updating a structure database, the structure database configured for use in automatically generating and evaluating merits of future promotions to provide automatic approval thus enabling a merchant to quickly and efficiently generate promotion structures without delay of waiting on human approval, the apparatus comprising a processor and a memory, the memory storing computer program code that, when executed by the processor, causes the apparatus to:
access a corpus of machine readable text, by the processor from a structure database, the corpus of machine readable text generated from a plurality of promotions, wherein each of the plurality of promotions comprises at least one promotion option associated with at least one service, and wherein each promotion option is associated with one or more features and one or more first components, each of the one or more features comprising of one or more descriptive words, and the one or more components associated with a plurality of groupings of features, each of the plurality of groupings identified as being indicative of an equivalent meaning;
extract, via the processor, a se

Assignees

• Groupon Inc

Inventors

• Nkengla Mechie
• Kochar Kavita
• Shariff Shafiq
• L'Huillier Gaston
• Parekh Rajesh
• Jennings Logan Tyler

Classifications

• G06Q30/0276 Primary

  Advertisement creation · CPC title