Navigating a taxonomy using search queries

Patent metadata

Field	Value
Publication number	US-9842162-B1
Application number	US-69823510-A
Country	US
Kind code	B1
Filing date	Feb 2, 2010
Priority date	Feb 2, 2010
Publication date	Dec 12, 2017
Grant date	Dec 12, 2017

Abstract

Disclosed are various embodiments for navigating a taxonomy using search queries. An unstructured search query is parsed in order to identify one or more categories of a taxonomy of a collection of items. Each one of the one or more categories is associated with a confidence score. When the confidence score meets a threshold, a pool of items is selected from a respective one of the one or more categories. When no confidence score meets the threshold, the pool of items is selected from the collection of items.

First claim

Therefore, the following is claimed:

1. A non-transitory computer-readable medium storing a program executable in a computing device, wherein when executed the program causes the computing device to at least:
obtain an unstructured search query from a client;
identify at least one category according to the unstructured search query, each of the at least one category being in a taxonomy of a catalog of products;
generate a confidence score for each of the at least one category based at least in part on a matching of at least a portion of the unstructured search query to data associated with the respective category, and an identification of at least one refinement in the unstructured search query that is associated with the respective category, the confidence score being generated using a weighted combination of a plurality of factors, a first factor of the plurality of factors comprising a quality of text match of the data associated with the respective category with the unstructured search query and a second factor of the plurality of factors comprising a number of refinements identified in the unstructured search query that are associated with the respective category, and the data associated with the respective category comprising a description of the respective category, and the quality of text match being based at least in part on a frequency that the at least a portion of the unstructured search query occurs within the description;
identify the at least one refinement by translating at least one keyword from the unstructured search query into at least one criterion for selecting products from the respective category, wherein the translation is configured to translate a plurality of synonyms into the at least one criterion;
select a first pool of products from the respective category according to the at least one refinement when the respective confidence score meets a threshold and no other confidence score meets the threshold;
select a second pool of products from the catalog of products when no confidence score meets the threshold or when a plurality of the confidence scores meet the threshold; and
generate a network page listing at least a portion of the first or second pool of products that has been selected, the network page including a disambiguation tool when no confidence score meets the threshold, the disambiguation tool providing a user interface for selecting one category from the at least one category.

2. The non-transitory computer-readable medium of claim 1 , wherein the confidence score is further generated based at least in part on user profile data and aggregate user behavior data.

3. The non-transitory computer-readable medium of claim 1 , wherein, when executed, the program further causes the computing device to at least parse the unstructured search query into a plurality of terms.

4. The non-transitory computer-readable medium of claim 3 , wherein the at least one category is identified according to at least one of the plurality of terms.

5. A system, comprising:
at least one computing device; and
an item search application executable in the at least one computing device, wherein when executed the item search application causes the at least one computing device to at least:
parse an unstructured search query to identify at least one category of a taxonomy of a collection of items generate a confidence score for each of the at least one category, each of the at least one category being associated with a confidence score, the confidence score being generated using a weighted combination of a plurality of factors, a first factor of the plurality of factors comprising a quality of text match of items in a respective category with the unstructured search query and a second factor of the plurality of factors comprising a number of refinements identified in the unstructured search query that are associated with the respective category, and data associated with the respective category comprising a description of the respective category, and the quality of text match being based at least in part on a frequency that at least a portion of the unstructured search query occurs within the description;
identify at least one refinement from the unstructured search query by translating at least one keyword from the unstructured search query into at least one criterion for selecting items from the respective category of the at least one category, wherein the translation is configured to translate a plurality of synonyms into the at least one criterion;
applying the at least one refinement to select a first pool of items from the respective category when the confidence score meets a threshold;
applying the at least one refinement to select a second pool of items from the collection of items when no confidence score meets the threshold; and
generate a network page listing at least a portion of the first or second pool of items that has been selected, the network page including a disambiguation tool when no confidence score meets the threshold, the disambiguation tool providing a user interface for selecting one category from the at least one category.

6. The system of claim 5 , wherein selecting the first pool of items from the respective category further comprises selecting the first pool of items from the respective category when no other confidence score meets the threshold, and wherein when executed the item search application further causes the at least one computing device to select the second pool of items from the collection of items when a plurality of the confidence scores meet the threshold.

7. The system of claim 5 , wherein selecting the first pool of items from the respective category further comprises selecting the first pool of items based at least in part on a matching of text from the unstructured search query with text describing at least one item from the respective category.

8. The system of claim 5 , wherein the at least one refinement comprises an attribute value associated with at least one item from the respective category.

9. The system of claim 5 , wherein the at least one criterion comprises an attribute and an attribute value associated with the attribute.

10. The system of claim 5 , wherein when executed the item search application further causes the at least one computing device to at least generate the confidence score for the respective category based at least in part on the at least one refinement.

11. The system of claim 5 , wherein when executed the item search application further causes the at least one computing device to at least match text from the unstructured search query with the data describing the respective category.

12. The system of claim 5 , wherein when executed the item search application further causes the at least one computing device to at least generate the confidence score for the respective category based at least in part on user profile data.

13. The system of claim 5 , wherein the network page includes a link to a detailed network page for an item from the first or second pool of items that has been selected, the detailed network page preselecting at least one attribute for the item according to a refinement identified from the unstructured search query.

14. A method, comprising:
identifying, in at least one computing device, a plurality of categories in a taxonomy of a collection of items by matching at least one term in a user-provided unstructured search query with metadata associated with respective categories in the taxonomy;
identifying, in the at least one computing device, a refinement in the user-provided unstructured search query that is associated with at least o

Assignees

• Hotchkies Blair L
• Mills Brent Robert
• Pounds Jennica Jane
• Saifullah Sikandar
• Indrei Alexandru I
• Patrikios Jason P
• Parshall Daniel R
• Lichterman David Aaron
• Teodorescu Dan Catalin
• Forde Sean P
• Amazon Tech Inc

Inventors

• Hotchkies Blair L
• Mills Brent Robert
• Pounds Jennica Jane
• Saifullah Sikandar
• Indrei Alexandru I
• Patrikios Jason P
• Parshall Daniel R
• Lichterman David Aaron
• Teodorescu Dan Catalin
• Forde Sean P

Classifications

• G06F16/374 Primary

  Thesaurus · CPC title

• G06F16/30

  of unstructured textual data (document management systems G06F16/93) · CPC title

• G06F17/3061

  Physics · mapped topic

• G06F17/30737 Primary

  Physics · mapped topic