Method, apparatus and system of intelligent navigation

• US 9,842,170 B2
• Filed: 12/13/2016
• Issued: 12/12/2017
• Est. Priority Date: 06/12/2010
• Status: Active Grant

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Pan, Chunxiang
• Primary Examiner(s): NGUYEN, KIM T
• Application Number:
  US15/377,716
• Publication Number:
  US 20170091339A1
• Time in Patent Office: 364 Days
• Field of Search: 707706, 707722
• CPC Class Codes: G06F 16/1734 Details of monitoring file system events, e.g. by the use of hooks, filter drivers, logs
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

The present disclosure describes a method, an apparatus and a system of intelligent navigation. In one embodiment, a method includes: receiving a user inquiry from a client terminal; searching a navigation dictionary based on the user inquiry to obtain a recommendation result corresponding to the user inquiry, the navigation dictionary including an editor recommendation based on user behavior information; and sending the recommendation result to the client terminal. The present disclosure can enhance the accuracy, relevancy, richness and intelligence of the intelligent navigation, and reduce user search time as well as the search loading on the server.

Claims

1. A method implemented by one or more computing devices, the method comprising:

sending a user inquiry to a web site from a client device, wherein the user inquiry includes a search keyword; and

receiving a recommendation result at the client device responsive to the user inquiry,

wherein the web site;

generates an editor recommendation that includes an index keyword and a number of recommended categories of a plurality of categories, the number of recommended categories being based on user behavior information, the plurality of categories less the number of recommended categories leaving a number of remaining categories, the plurality of categories being associated with the index keyword and having a number of clicks made by the client device;

determines whether the clicks of a remaining category that has a largest number of clicks is greater than the clicks of a recommended category that has a smallest number of clicks;

replaces the recommended category that has the smallest number of clicks with the remaining category when the clicks of the remaining category that has the largest number of clicks is greater than the clicks of the recommended category that has the smallest number of clicks; and

stores the index keyword and the number of recommended categories in a navigation dictionary when the clicks of the remaining category that has the largest number of clicks is less than the clicks of the recommended category that has the smallest number of clicks, and stores the index keyword and the number of recommended categories in the navigation dictionary after the recommended category that has the smallest number of clicks has been replaced when the clicks of the remaining category that has the largest number of clicks is greater than the clicks of the recommended category that has the smallest number of clicks.

2. The method as recited in claim 1, wherein:

the web site searches the navigation dictionary with the search keyword to find the index keyword; and

when found, transmits the index keyword and the number of recommended categories that are associated with the index keyword to the client device as the recommendation result.

3. The method as recited in claim 2, wherein the web site replaces the recommended category that has the smallest number of clicks with the remaining category that has the largest number of clicks.

4. The method as recited in claim 2, and further comprising:

generating a user behavior log based on the user behavior information, the user behavior log including a search log, a product clicking log, a purchase log, and a navigation area log;

generating reference data based on the search log, the product clicking log, and the purchase log; and

generating the editor recommendation based on the reference data.

5. The method as recited in claim 4, wherein the reference data based on the search log includes a plurality of search keywords, a plurality of search categories, and search data, an editor recommendation being generated when the search data is greater than a predetermined threshold, the editor recommendation including an index keyword from the plurality of search keywords in the reference data, an index category from the plurality of search categories in the reference data, and a recommended category from categories in the search data having a greatest value.

6. The method as recited in claim 4, wherein the reference data based on the purchase log includes a plurality of search keywords, a plurality of search categories, and purchase data, an editor recommendation being generated when the purchase data is greater than a predetermined threshold, the editor recommendation including an index keyword from the plurality of search keywords in the reference data, an index category from the plurality of search categories in the reference data, and a recommended category from categories in the purchase data having a greatest value.

7. The method as recited in claim 4, wherein the reference data based on the product clicking log includes a plurality of search keywords, a plurality of search categories, and clicking data, an editor recommendation being generated when the clicking data is greater than a predetermined threshold, the editor recommendation including an index keyword from the plurality of search keywords in the reference data, an index category from the plurality of search categories in the reference data, and a recommended category from categories in the clicking data having a greatest value.

8. The method as recited in claim 4, wherein the search log includes times of searches, a first set of user-entered keywords, and search categories, the product clicking log includes times of clicks, a second set of user-entered keywords, and selected products, the purchase log includes times of purchases and a third set of user-entered keywords, and the navigation area clicking log includes times of clicks in a navigation area, a fourth set of user-entered keywords, and selected categories.

9. The method as recited in claim 1, wherein the user inquiry further includes a search category, and the navigation dictionary further stores an index category associated with the index keyword.

10. The method as recited in claim 9, wherein the web site:

searches the navigation dictionary with the search keyword and the search category to find the index keyword and the index category; and

when found, transmits the index keyword, the index category, and the number of recommended categories that are associated with the index keyword and the index category to the client device as the recommendation result.

11. The method as recited in claim 10, wherein the navigation dictionary additionally stores a recommendation type that is associated with the index keyword.

12. The method as recited in claim 11, wherein the recommendation type includes one of a category only, a feature only, and a combination of a category and a feature.

13. A system comprising:

a memory that stores machine instructions;

a display device; and

a processor that executes the machine instructions to;

send a user inquiry to a web site, wherein the user inquiry includes a search keyword; and

receive a recommendation result from the web site responsive to the user inquiry,

wherein the web site;

generates an editor recommendation that includes an index keyword and a number of recommended categories from a plurality of categories, the number of recommended categories being based on user behavior information, the plurality of categories less the number of recommended categories leaving a number of remaining categories, the plurality of categories being associated with the index keyword and having a number of clicks made by the client device;

determines whether the clicks of a remaining category that has a largest number of clicks is greater than the clicks of a recommended category that has a smallest number of clicks;

replaces the recommended category that has the smallest number of clicks with a remaining category when the clicks of the remaining category that has the largest number of clicks is greater than the clicks of the recommended category that has the smallest number of clicks; and

stores the index keyword and the number of recommended categories in a navigation dictionary when the clicks of the remaining category that has the largest number of clicks is less than the clicks of the recommended category that has the smallest number of clicks, and stores the index keyword and the number of recommended categories in the navigation dictionary after the recommended category that has the smallest number of clicks has been replaced when the clicks of the remaining category that has the largest number of clicks is greater than the clicks of the recommended category that has the smallest number of clicks.

14. The system as recited in claim 13, wherein:

the web site searches the navigation dictionary with the search keyword to find the index keyword; and

when found, transmits the index keyword and the number of recommended categories that are associated with the index keyword to the system as the recommendation result.

15. The system as recited in claim 13,

wherein the user inquiry further includes a search category, and the navigation dictionary further stores an index category associated with the index keyword.

16. The system as recited in claim 15, wherein the web site:

searches the navigation dictionary with the search keyword and the search category to find the index keyword and the index category; and

when found, transmits the index keyword, the index category, and the number of recommended categories that are associated with the index keyword and the index category to the system as the recommendation result.

17. The system as recited in claim 16, wherein the navigation dictionary additionally stores a recommendation type that is associated with the index keyword.

18. The system as recited in claim 17, wherein the recommendation type includes one of a category only, a feature only, and a combination of a category and a feature.