METHODS, SYSTEMS, AND MEDIA FOR PROVIDING SEARCH SUGGESTIONS

• US 20160246805A1
• Filed: 02/20/2015
• Published: 08/25/2016
• Est. Priority Date: 02/20/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Long, Eileen Margaret Peters, Lawry, James
• Granted Patent: US 10,169,488 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9532 Query formulation
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods, systems, and media for providing search suggestions are provided. In accordance with some embodiments, the method comprises: receiving user input that includes a partial search query; identifying a group of candidate search suggestions; determining whether each candidate search suggestion is included on a list of search suggestions that are prohibited, wherein the list is generated by: receiving previously submitted search queries and search results; determining, for each of the search queries, a number of search results associated with a particular content rating; determining whether the number meets a threshold value; and in response to determining that the number does not meet the threshold value, inserting the search query to the list; generating a modified group of search suggestions by removing search suggestions that are on the list; and causing a subset of the modified group of search suggestions to be presented as the remaining portion of the search query.

Claims

1. A method for providing search suggestions, comprising:

receiving user input that includes one or more characters of a partial search query;

identifying a group of candidate search suggestions corresponding to the one or more characters of the partial search query, wherein each candidate search suggestion is a prediction of a complete search query;

determining whether each candidate search suggestion from the group of candidate search suggestions is included on a list of search suggestions that have been determined to be disallowed, wherein the list is generated by;

receiving previously submitted search queries and a plurality of search results associated with each of the previously submitted search queries;

determining, for each of the previously submitted search queries, a number of search results associated with a particular content rating;

determining, for each of the previously submitted search queries, whether the number of search results associated with the particular content rating meets a predetermined threshold value; and

in response to determining that the number of search results associated with the particular content rating does not meet the predetermined threshold value for the previously submitted search query, inserting the previously submitted search query to the list;

generating, from the group of candidate search suggestions, a modified group of search suggestions by removing one or more search suggestions that are included on the list of search suggestions that have been determined to be disallowed; and

causing a subset of the modified group of search suggestions to be presented on the user device as the remaining portion of the partial search query.

2. The method of claim 1, wherein each candidate search suggestion in the group of candidate search suggestions begins with the one or more characters of the partial search query.

3. The method of claim 1, further comprising ranking the modified group of search suggestions, wherein the subset of the modified group of search suggestions is determined based on the ranking, and wherein the subset of the modified group of search suggestions is presented based on the ranking.

4. The method of claim 3, wherein the ranking is performed based at least in part on a relevance of search results associated with a search suggestion to a particular demographic.

5. The method of claim 1, further comprising:

determining a plurality search queries from the group of previously submitted search queries that are similar;

averaging the number of search results associated with the particular content rating for each of the plurality of search queries to calculate an updated number of search results; and

in response to determining that the updated number of search results does not meet the predetermined threshold, inserting the plurality of search queries to the list.

6. The method of claim 1, further comprising:

determining whether each candidate search suggestion is on a second list of not allowed search suggestions, wherein the second list is associated with a user account authenticated on the user device; and

removing search suggestions that are on the second list from the group of candidate search suggestions.

7. The method of claim 1, further comprising:

storing the number of search results associated with the particular content rating and a safety score based on the number of search results associated with the particular content rating in association with each search query in the list; and

storing the list.

8. The method of claim 1, wherein receiving the previously submitted search queries and the plurality of search results associated with each of the previously submitted search queries further comprises identifying the plurality of search results associated with each of the previously submitted search queries.

9. A system for providing search suggestions, the system comprising:

a hardware processor that is programmed to;

receive user input that includes one or more characters of a partial search query;

identify a group of candidate search suggestions corresponding to the one or more characters of the partial search query, wherein each candidate search suggestion is a prediction of a complete search query;

determine whether each candidate search suggestion from the group of candidate search suggestions is included on a list of search suggestions that have been determined to be disallowed, wherein the hardware processor is programmed to;

receive previously submitted search queries and a plurality of search results associated with each of the previously submitted search queries;

determine, for each of the previously submitted search queries, a number of search results associated with a particular content rating;

determine, for each of the previously submitted search queries, whether the number of search results associated with the particular content rating meets a predetermined threshold value; and

in response to determining that the number of search results associated with the particular content rating does not meet the predetermined threshold value for the previously submitted search query, insert the previously submitted search query to the list;

generate, from the group of candidate search suggestions, a modified group of search suggestions by removing one or more search suggestions that are included on the list of search suggestions that have been determined to be disallowed; and

cause a subset of the modified group of search suggestions to be presented on the user device as the remaining portion of the partial search query.

10. The system of claim 9, wherein each candidate search suggestion in the group of candidate search suggestions begins with the one or more characters of the partial search query.

11. The system of claim 9, wherein the hardware processor is further programmed to rank the modified group of search suggestions, wherein the subset of the modified group of search suggestions is determined based on the ranking, and wherein the subset of the modified group of search suggestions is presented based on the ranking.

12. The system of claim 11, wherein the ranking is performed based at least in part on a relevance of search results associated with a search suggestion to a particular demographic.

13. The system of claim 9, wherein the hardware processor is further programmed to:

determine a plurality search queries from the group of previously submitted search queries that are similar;

average the number of search results associated with the particular content rating for each of the plurality of search queries to calculate an updated number of search results; and

in response to determining that the updated number of search results does not meet the predetermined threshold, insert the plurality of search queries to the list.

14. The system of claim 9, wherein the hardware processor is further programmed to:

determine whether each candidate search suggestion is on a second list of not allowed search suggestions, wherein the second list is associated with a user account authenticated on the user device; and

remove search suggestions that are on the second list from the group of candidate search suggestions.

15. The system of claim 9, wherein the hardware processor is further programmed to:

store the number of search results associated with the particular content rating and a safety score based on the number of search results associated with the particular content rating in association with each search query in the list; and

store the list.

16. The system of claim 9, wherein the hardware processor is further programmed to identify the plurality of search results associated with each of the previously submitted search queries.

17. A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for providing search suggestions, the method comprising:

receiving user input that includes one or more characters of a partial search query;

identifying a group of candidate search suggestions corresponding to the one or more characters of the partial search query, wherein each candidate search suggestion is a prediction of a complete search query;

determining whether each candidate search suggestion from the group of candidate search suggestions is included on a list of search suggestions that have been determined to be disallowed, wherein the list is generated by;

receiving previously submitted search queries and a plurality of search results associated with each of the previously submitted search queries;

determining, for each of the previously submitted search queries, a number of search results associated with a particular content rating;

determining, for each of the previously submitted search queries, whether the number of search results associated with the particular content rating meets a predetermined threshold value; and

in response to determining that the number of search results associated with the particular content rating does not meet the predetermined threshold value for the previously submitted search query, inserting the previously submitted search query to the list;

generating, from the group of candidate search suggestions, a modified group of search suggestions by removing one or more search suggestions that are included on the list of search suggestions that have been determined to be disallowed; and

causing a subset of the modified group of search suggestions to be presented on the user device as the remaining portion of the partial search query.

18. The non-transitory computer-readable medium of claim 17, wherein each candidate search suggestion in the group of candidate search suggestions begins with the one or more characters of the partial search query.

19. The non-transitory computer-readable medium of claim 17, wherein the method further comprises ranking the modified group of search suggestions, wherein the subset of the modified group of search suggestions is determined based on the ranking, and wherein the subset of the modified group of search suggestions is presented based on the ranking.

20. The non-transitory computer-readable medium of claim 19, wherein the ranking is performed based at least in part on a relevance of search results associated with a search suggestion to a particular demographic.

21. The non-transitory computer-readable medium of claim 17, wherein the method further comprises:

determining a plurality search queries from the group of previously submitted search queries that are similar;

averaging the number of search results associated with the particular content rating for each of the plurality of search queries to calculate an updated number of search results; and

in response to determining that the updated number of search results does not meet the predetermined threshold, inserting the plurality of search queries to the list.

22. The non-transitory computer-readable medium of claim 17, wherein the method further comprises:

determining whether each candidate search suggestion is on a second list of not allowed search suggestions, wherein the second list is associated with a user account authenticated on the user device; and

removing search suggestions that are on the second list from the group of candidate search suggestions.

23. The non-transitory computer-readable medium of claim 17, wherein the method further comprises:

storing the number of search results associated with the particular content rating and a safety score based on the number of search results associated with the particular content rating in association with each search query in the list; and

storing the list.

24. The non-transitory computer-readable medium of claim 17, wherein receiving the previously submitted search queries and the plurality of search results associated with each of the previously submitted search queries further comprises identifying the plurality of search results associated with each of the previously submitted search queries.