Automated deal guide structure identification

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 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,
• 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, identify, 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;
• tag, via the processor, each promotion option with every component associated at least one grouping of features matching the subset of the extracted features of the promotion option;
• update 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;
• identify 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-perform 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.

A computer program product 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 computer program product comprising a non-transitory computer-readable storage medium storing computer program code that, when executed by an apparatus, causes the apparatus to:

• access 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;
• extract, 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, identify, 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;
• tag, 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;
• and
• update 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;
• identify 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-perform 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.