APPLICATION SEARCH QUERY CLASSIFIER

• US 20130325892A1
• Filed: 08/03/2012
• Published: 12/05/2013
• Est. Priority Date: 05/31/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Edwards, Catherine A., Braunstein, Alexander F., Mok, Eva H., Hernandez-Gardiol, Natalia
• Granted Patent: US 9,405,832 B2
• Time in Patent Office: Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results

Abstract

A user can input a search query. By assessing terms in the search query, the search query can be categorized (e.g., as a navigational, functional or browse query). The categorization can depend on an analysis of terms in the search query, a preliminary search, and/or empirical data tied to previous and similar searches. For example, searches estimated to be directed to finding a specific app can be categorized as navigational, based on capitalized letters, quotation marks, a short number of words in the query, and a tight distribution of apps typically downloaded subsequent to viewing results from the search. Based on the categorization, a search strategy can be identified. Search strategies can differentially weight and/or use text-based strategies.

Claims

1. A method of responding to a search query requesting relevant software applications from a database of software applications, the method comprising:

receiving, at a server, the search query from an electronic device of a user, the search query including one or more terms;

analyzing the one or more terms to assign a first search category to the search request, the first search category being selected from a plurality of potential categories, wherein the potential categories include a navigational category and a functional category;

determining a search technique based on the first search category, the navigational category being searched based on text associated with the software applications in the database, and the functional category being searched based on a function of the software application in the database;

using the determined search technique to search, at the server, the database for one or more relevant software applications based on the search request; and

sending, to the electronic device, a list of the one or more relevant software applications.

2. The method of claim 1 wherein analyzing the one or more terms comprises:

identifying a set of previous search queries from other users including the term or an equivalent term;

identifying, for each search query in the set of previous search queries, an application selected or downloaded by a respective other user subsequent to receiving results from the previous search query; and

analyzing a distribution over the selected or downloaded applications.

3. The method of claim 2, wherein analyzing the distribution includes:

determining a statistical value of the distribution; and

comparing the statistical value to a threshold,

wherein the functional category is assigned to the search request when the statistical value exceeds the threshold.

4. The method of claim 3, wherein the statistical value is an area under the distribution for the N most selected or downloaded software applications, where N is an integer greater than three.

5. The method of claim 1, wherein determining the search technique based on the first search category comprises searching for the one or more terms within titles, metadata or text associated with the software applications in the database.

6. The method of claim 1, wherein assigning the search query to a search-type category comprises searching for the term in a look-up table.

7. The method of claim 6, wherein the look-up table is repeatedly updated based on an identification of which applications were selected or downloaded by users subsequent to presentations of search-query results to the users.

8. The method of claim 1, wherein the term comprises a set of words.

9. The method of claim 1, wherein the server is remote from the electronic device, and wherein initiating the presentation of the results of the search to the user of the electronic device comprises transmitting the results of the search to the electronic device.

10. A method of categorizing search queries requesting relevant software applications from a database of software applications, the method comprising:

receiving, at a server, first data from each of a set of devices identifying one or more search-query terms, the one or more search-query terms being the same or equivalent across the set of devices;

receiving, at the server, second data from each of the set of devices indicating that a first user of the respective device requested a download of a software application or viewed additional information about the software application not available in a primary search-results presentation;

associating each app within a set of software applications with the one or more search-query terms, wherein the set of software applications comprises the software applications that were requested for download or for which additional information was viewed across all devices within the set of devices;

generating a distribution over the set of software applications;

analyzing the distribution; and

associating the one or more search-query terms with a search category selected from a plurality of potential categories, wherein the association of the one or more search-query terms with the search category is based on the analysis of the distribution, and wherein one of the potential categories is associated with an prediction that a second user who subsequently inputs the one or more search-query terms is to seeking access a software application already known to the second user.

11. The method of claim 10 wherein the second data indicates that a first user of the respective device requested a download of a software application.

12. The method of claim 10 wherein the first data and the second data are received, from each device, within a single signal.

13. The method of claim 10 wherein analyzing the distribution comprises determining a proportion of the software applications within the set of software applications accounted for by a subset of the set of software applications.

14. The method of claim 10 wherein analyzing the distribution comprises determining a proportion of the software applications within the set of software applications accounted for by a single software application within the set of software applications.

15. The method of claim 10 wherein analyzing the distribution comprises comparing a value associated with the distribution to a threshold.

16. The method of claim 10 further comprising:

receiving, at the server, a search query from a second device, the search query including the one or more search-query terms;

determining a search technique based on the search category;

using the determined search technique to search, at the server, a database for one or more relevant software applications based on the search request; and

sending, to the second device, a list of the one or more relevant software applications.

17. A computer-readable storage medium containing program instructions, which when executed by a processor cause the processor to execute a method of responding to a search query requesting relevant software applications from a database of software applications, the method comprising:

receiving, at a server, the search query from an electronic device of a user, the search query including one or more terms;

analyzing the one or more terms to assign a search category to the search request, the search category being selected from a plurality of potential search categories, wherein each category of the plurality of potential search categories relates to a different search technique for searching the database of software applications, wherein a first search technique emphasizes exact textual matches more than a second search technique emphasizes exact textual matches, and wherein the analysis utilizes empirical data associated with the one or more terms;

determining a search technique based on the search category;

using the determined search technique to search, at the server, the database for one or more relevant software applications based on the search request; and

sending, to the electronic device, a list of the one or more relevant software applications.

18. The computer-readable medium of claim 17 wherein the first search technique comprises a navigational search technique and the second search technique comprises a functional search technique.

19. The computer-readable medium of claim 17 wherein the empirical data includes data identifying other users'"'"' downloads of software applications subsequent to initiating same or equivalent search queries.

20. The computer-readable medium of claim 17 wherein the analysis further depends on a capitalization, number of words, or punctuation used in the search query.

21. An system of categorizing search queries requesting relevant software applications from a database of software applications, the system comprising:

a network interface configured to wirelessly communicate with a remote server;

a processor; and

a computer-readable storage medium containing program instructions, which when executed by the processor cause the processor to execute a method of interacting with a traffic service, the method comprising;

receiving first data from each of a set of devices identifying one or more search-query terms, the one or more search-query terms being the same or equivalent across the set of devices;

receiving second data from each of the set of devices indicating that a first user of the respective device requested a download of a software application or viewed additional information about the software application not available in a primary search-results presentation;

associating each app within a set of software applications with the one or more search-query terms, wherein the set of software applications comprises the software applications that were requested for download or for which additional information was viewed across all devices within the set of devices;

generating a distribution over the set of software applications;

analyzing the distribution; and

associating the one or more search-query terms with a search category selected from a plurality of potential categories, wherein the association of the one or more search-query terms with the search category is based on the analysis of the distribution, and wherein one of the potential categories is associated with an prediction that a second user who subsequently inputs the one or more search-query terms is to seeking access a software application already known to the second user.

22. The system of claim 21 wherein the second data indicates that a first user of the respective device purchased a software application.

23. The system of claim 22 wherein the first data and the second data are received, from each device, within different signals.

24. The system of claim 21 wherein analyzing the distribution comprises determining a proportion of the software applications within the set of software applications accounted for by a subset of the set of software applications.

25. The system of claim 21 wherein analyzing the distribution comprises comparing a first value associated with the distribution to a first threshold and comparing a second value associated with the distribution to a second threshold.