Automatic identification of related search keywords
View Patent ↗Keyword expansion is used to expand a particular keyword into multiple related keyword candidates using a collection of data that relates to search queries performed using one or more search engines. The data identifies search terms from associated search queries. A particular keyword is identified and one or more candidate keywords related to the particular keyword are identified based on the data.
1. A method comprising:
collecting, using a computer, data indicative of search terms associated with one or more search queries;
identifying, in the search terms, a particular keyword;
identifying, using the computer, remaining search terms as candidate keywords related to the particular keyword; and
generating a confidence score for a candidate keyword, the confidence score comprising a ratio of (i) a number of times the candidate keyword and the particular keyword appeared in a same search query of the one or more search queries, to (ii) a number of times the candidate keyword appeared in the one or more search queries.
2. The method of claim 1 , further comprising identifying the one or more search queries based on the one or more search queries being received from a particular location.
3. The method of claim 2 , wherein identifying the one or more search queries is further based on the one or more search queries being performed within a predetermined time.
4. The method of claim 2 , further comprising determining the particular location based on an originating address associated with the one or more search queries.
5. The method of claim 2 , further comprising determining the particular location based on data stored on a device from which at least one of the one or more search queries originates.
6. The method of claim 1 , wherein the search terms comprise elements that are related to each other.
7. The method of claim 1 , wherein identifying the particular keyword comprises at least one of (i) identifying one or more stems of at least one of the search terms, or (ii) identifying a misspelling of at least one of the search terms.
8. The method of claim 1 , further comprising analyzing, from the one or more search queries, data for patterns of similar search tendencies.
9. The method of claim 1 , further comprising rating the candidate keywords based on confidence scores.
10. An apparatus comprising:
one or more processing devices; and
one or more machine-readable storage devices for storing instructions that are executable by the one or more processing devices to perform operations comprising:
collecting data indicative of search terms associated with one or more search queries;
identifying, in the search terms, a particular keyword;
identifying remaining search terms as candidate keywords related to the particular keyword; and
generating a confidence score for a candidate keyword, the confidence score comprising a ratio of (i) a number of times the candidate keyword and the particular keyword appeared in a same search query of the one or more search queries, to (ii) a number of times the candidate keyword appeared in the one or more search queries.
11. The apparatus of claim 10 , wherein the candidate keyword comprises a first candidate keyword, and wherein the operations further comprise:
collecting information relating to usage trends among the search terms; and
using the information relating to the usage trends in identifying at least one of the search terms as a second candidate keyword.
12. The apparatus of claim 10 , wherein the operations further comprise:
assigning a weighting to the candidate keyword based on a ratio of a cost for using the candidate keyword in a pay-per-click advertising arrangement to a frequency-of-use metric.
13. One or more machine-readable storage devices for storing instructions that are executable by one or more processing devices to perform operations comprising:
collecting data indicative of search terms associated with one or more search queries;
identifying, in the search terms, a particular keyword;
identifying remaining search terms as candidate keywords related to the particular keyword; and
generating a confidence score for a candidate keyword, the confidence score comprising a ratio of (i) a number of times the candidate keyword and the particular keyword appeared in a same search query of the one or more search queries, to (ii) a number of times the candidate keyword appeared in the one or more search queries.
14. The one or more machine-readable storage devices of claim 13 , wherein the operations further comprise:
identifying the one or more search queries based on the one or more search queries being received from a particular location.
15. The one or more machine-readable storage devices of claim 14 , wherein identifying the one or more search queries is further based on the one or more search queries being performed within a predetermined time.
16. The one or more machine-readable storage devices of claim 14 , wherein the operations further comprise:
determining the particular location based on an originating address associated with the one or more search queries.
17. The one or more machine-readable storage devices of claim 14 , wherein the operations further comprise:
determining the particular location based on data stored on a device from which at least one of the one or more search queries originates.
18. The one or more machine-readable storage devices of claim 13 , wherein the search terms comprise elements that are related to each other.