METHOD AND SYSTEM FOR LISTING CATEGORIZATION
First Claim
1. A method comprising:
- accessing a category structure, the category structure including a plurality of categories for items;
accessing a set of training data from a plurality of listings from at least one of supply data or demand data, the supply data generated from seller activity of a plurality of users in a networked system, the demand data generated from buyer activity of the plurality of users in the networked system, each listing including a category from the category structure; and
providing the set of training data to a categorization application for training, the categorization application capable of building listing statistics by applying a classifier to the set of training data and recommending a category from the category structure for a new listing by utilizing the listing statistics.
1 Assignment
0 Petitions
Accused Products
Abstract
Embodiments of a method and system for listing categorization are disclosed. A category structure may be accessed. The category structure may include a plurality of categories for items. A set of training data may be accessed from a plurality of listings from at least one of supply data and/or demand data. The supply data may be generated from seller activity of a plurality of users in a networked system. The demand data may be generated from buyer activity of the plurality of users in the networked system. Each listing may include a category from the category structure. The set of training data may be provided to a categorization application for training. The categorization application may be capable of building listing statistics by applying a classifier to the set of training data and recommending a category from the category structure for a new listing by utilizing the listing statistics.
-
Citations
33 Claims
-
1. A method comprising:
-
accessing a category structure, the category structure including a plurality of categories for items; accessing a set of training data from a plurality of listings from at least one of supply data or demand data, the supply data generated from seller activity of a plurality of users in a networked system, the demand data generated from buyer activity of the plurality of users in the networked system, each listing including a category from the category structure; and providing the set of training data to a categorization application for training, the categorization application capable of building listing statistics by applying a classifier to the set of training data and recommending a category from the category structure for a new listing by utilizing the listing statistics. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A method comprising
automatically generating a set of training data for a category structure by applying a classifier to listing data from a plurality of listings from at least one of supply data or demand data, the supply data generated from seller activity of a plurality of users in a networked system, the demand data generated from buyer activity of the plurality of users in the networked system, each listing including a category from the category structure; - and
training a categorization application with the set of newly generated training data. - View Dependent Claims (9, 10, 11)
- and
-
12. A method comprising:
-
accessing a description of listing, the listing including a title and a description associated with the title, the description including a plurality of sentences; and automatically extracting relevant listing information from the description, the listing relevant information being information that is relevant to the listing. - View Dependent Claims (13, 14, 15, 16, 17)
-
-
18. A method comprising:
-
receiving a listing of an item in a networked system; determining a category suggestion for the listing of the item from listing statistics, the listing statistics built by applying a classifier to a set of training data; receiving adaptive information regarding the category suggestion; and adjusting a calculation performed by the classifier from the adaptive information. - View Dependent Claims (19, 20, 21)
-
-
22. A machine-readable medium comprising instructions, which when executed by a machine, cause the machine to:
-
access a category structure, the category structure including a plurality of categories for items; access a set of training data from a plurality of listings from at least one of supply data or demand data, the supply data generated from seller activity of a plurality of users in a networked system, the demand data generated from buyer activity of the plurality of users in the networked system, each listing including a category from the category structure; and provide the set of training data to a categorization application for training, the categorization application capable of building listing statistics by applying a classifier to the set of training data and recommending a category from the category structure for a new listing by utilizing the listing statistics. - View Dependent Claims (23)
-
-
24. A machine-readable medium comprising instructions, which when executed by a machine, cause the machine to:
-
automatically generate a set of training data for a category structure by applying a classifier to listing data from a plurality of listings from at least one of supply data or demand data, the supply data generated from seller activity of a plurality of users in a networked system, the demand data generated from buyer activity of the plurality of users in the networked system, each listing including a category from the category structure; and train a categorization application with the set of newly generated training data. - View Dependent Claims (25)
-
-
26. A machine-readable medium comprising instructions, which when executed by a machine, cause the machine to:
-
access a description of listing, the listing including a title and a description associated with the title, the description including a plurality of sentences; and automatically extract relevant listing information from the description, the listing relevant information being information that is relevant to the listing. - View Dependent Claims (27)
-
-
28. A machine-readable medium comprising instructions, which when executed by a machine, cause the machine to:
-
receive a listing of an item in a networked system; determine a category suggestion for the listing of the item from listing statistics, the listing statistics built by applying a classifier to a set of training data; receive adaptive information regarding the category suggestion; and adjust a calculation performed by the classifier from the adaptive information. - View Dependent Claims (29)
-
-
30. A system comprising:
one or more machine-readable mediums comprising associated information for a training application program and for a categorization application program, the associated information for the training application program to cause a machine to dynamically create a set of training data and the associated information for the categorization application program to cause a machine to use the dynamically created set of training data to recommend a category for a new listing in a networked-based marketplace.
-
31. A computerized method comprising:
-
dynamically creating an initial set of training data for a categorization application; using the dynamically created initial set of training data to train the categorization application; dynamically creating an updated set of training data for the categorization application; and retraining the categorization application using the updated set of training data.
-
-
32. A computerized system comprising:
one or more application servers comprising a training application to create a set of training data and a categorization application to be trained with the set of training data to suggest a category for one or more items in a networked-based marketplace. - View Dependent Claims (33)
Specification