Method for systematic mass normalization of titles

A system for generating a database of labeled canonical titles, the system comprising:

• a memory;
• and
• a processor configured to:
• receive a set of canonical titles;
• generate a set of canonical n-grams for each canonical title, wherein each canonical n-gram includes one or more contiguous words in the canonical title;
• assign a set of canonical attributes to each canonical n-gram in the set of canonical n-grams, wherein the set of canonical attributes assigned to each canonical n-gram is the same;
• assign a set of canonical labels to one or more canonical attributes for each canonical n-gram;
• and
• store in the memory each canonical title in the database of labeled canonical titles along with the generated set of canonical n-grams, the set of canonical attributes assigned to each of the canonical n-grams, and the set of canonical labels assigned to each of the canonical attributes.

A method of mapping a raw title to a canonical title in a database of labeled canonical titles, the method comprising:

• receiving a raw title;
• generating a set of raw n-grams for the raw title, wherein each raw n-gram includes one or more contiguous words in the raw title;
• assigning a set of raw attributes to each raw n-gram in the set of raw n-grams, wherein the set of raw attributes is the same as a set of canonical attributes associated with canonical titles stored in the database of labeled canonical titles;
• assigning a set of raw labels to one or more of the raw attributes for each raw n-gram;
• and
• determining one or more best match canonical titles in the database of labeled canonical titles based on a comparison of the raw attributes and the raw labels to the set of canonical attributes and a set of canonical labels associated with each of the canonical titles in the database of labeled canonical titles.

A system for mapping a raw title to a canonical title in a database of labeled canonical titles, the system comprising:

• a memory;
• and
• a processor configured to:
• receive a raw title;
• generate a set of raw n-grams for the raw title, wherein each raw n-gram includes one or more contiguous words in the raw title;
• assign a set of raw attributes to each raw n-gram in the set of raw n-grams, wherein the set of raw attributes is the same, and the set of raw attributes is the same as a set of canonical attributes associated with canonical titles stored in the memory in the database of labeled canonical titles;
• assign a set of raw labels to one or more of the raw attributes for each raw n-gram;
• and
• determine one or more best match canonical titles in the database of labeled canonical titles based on a comparison of the raw attributes and the raw labels to the set of canonical attributes and a set of canonical labels associated with each of the canonical titles in the database of labeled canonical titles.

A method for generating a database of labeled canonical data, including

• designating a set of canonical data;
• generating a set of canonical n-grams for each canonical data item, wherein each canonical n-gram includes one or more contiguous words in the canonical data item;
• assigning a set of canonical attributes to each canonical n-gram in the set of canonical n-grams;
• assigning a set of canonical labels to one or more of the canonical attributes for each canonical n-gram;
• and
• storing at least one of each canonical data item, the set of canonical n-grams generated for each canonical data item, the set of canonical attributes assigned to each of the canonical n-grams, or the set of canonical labels assigned to each of the canonical attributes in the database of labeled canonical data.

A method of mapping raw data to canonical data in a database of labeled canonical data, the method comprising:

• receiving a raw data item;
• generating a set of raw n-grams for the raw data item, wherein each raw n-gram includes one or more contiguous words in the raw data item;
• assigning a set of raw attributes to each raw n-gram in the set of raw n-grams, wherein the set of raw attributes is the same as the set of canonical attributes associated with the canonical data items stored in the database of labeled canonical data items;
• assigning a set of raw labels to one or more of the raw attributes for each raw n-gram;
• and
• determining one or more best match canonical data items in the database of labeled canonical data based on a comparison of the raw attributes and the raw labels to the set of canonical attributes and a set of canonical labels associated with each of the canonical data items in the database of labeled canonical data.