Method and system for providing query suggestions

• US 10,467,291 B2
• Filed: 05/02/2016
• Issued: 11/05/2019
• Est. Priority Date: 05/02/2016
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: Oath Inc. (Verizon Communications Inc.)
• Inventors: Zhang, Yuan, Chen, Zhongqiang, Zhu, Shenhong
• Primary Examiner(s): Ly, Anh
• Application Number:
  US15/144,196
• Publication Number:
  US 20170316023A1
• Time in Patent Office: 1,282 Days
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus

Abstract

The present teaching relates to providing query suggestions. A query is received from a user. A plurality of suggestions with respect to the query are obtained. One or more garbled suggestions are identified from the plurality of suggestions. One or more identified garbled suggestions are removed from the plurality of suggestions. The plurality of suggestions with removed one or more garbled suggestions are provided to the user in response to the query.

Claims

1. A method implemented on a computing device having at least one processor, storage, and a communication platform connected to a network for providing query suggestions, the method comprising:

receiving a query from a user;

obtaining a plurality of suggestions with respect to the query;

identifying one or more of the plurality of suggestions that are garbled, wherein each of the one or more of the plurality of suggestions comprises at least one repeated word, the identifying being based on a model trained to recognize a linguistic connection between the at least one repeated word;

removing the one or more of the plurality of suggestions; and

providing the plurality of suggestions without the one or more of the plurality of suggestions to the user in response to the query.

2. The method of claim 1, wherein the at least one repeated word comprises one repeated word, identifying the one or more of the plurality of suggestions further comprises:

determining whether a suggestion of the plurality of suggestions comprises one repeated word; and

when it is determined that the suggestion comprises one repeated word,

generating a plurality of groups of words of the suggestion, each comprising an instance of the one repeated word;

determining a correlation among the plurality of groups of words; and

determining whether the suggestion is a garbled suggestion based on the correlation, wherein the garbled suggestion comprises a suggestion that causes confusion.

3. The method of claim 2, wherein generating the plurality of groups of words of the suggestion further comprises:

assigning a part of speech (POS) tag to each word of the suggestion; and

integrating one or more words to form a group based on the assigned POS tags.

4. The method of claim 2, wherein the correlation indicates whether two groups of words are connected via at least a conjunction word.

5. The method of claim 1, wherein the at least one repeated word comprises at least two repeated words, identifying the one or more of the plurality of suggestions further comprises:

determining whether a suggestion of the plurality of suggestions comprises at least two repeated word; and

when it is determined that the suggestion comprises at least two repeated words,

determining whether the suggestion comprises at least one conjunction word; and

if the suggestion comprises no conjunction word,

generating a first set of groups of words of the suggestion, each comprising an instance of the at least two repeated words;

transforming the first set of groups of words to a second set of groups of words;

determining whether there are two identical groups of words from the second set of groups of words;

if there are two identical groups of words from the second set of groups of words,

determining that the suggestion is a garbled suggestion, the garbled suggestion comprising a suggestion that causes confusion; and

if there are no two identical groups of words from the second set of groups of words,

determining that the suggestion is not the garbled suggestion.

6. The method of claim 5, further comprising:

if the suggestion comprises at least one conjunction word,

generating one or more segments of the suggestion separated by the at least one conjunction word;

determining whether at least one of the one or more segments is a garbled segment; and

when it is determined that at least one of the one or more segments is a garbled segment, determining that the suggestion is the garbled suggestion.

7. The method of claim 6, wherein determining whether the at least one of the one or more segments is the garbled segment further comprises:

generating a first set of groups of words of the suggestion for each of the one or more segments, each comprising an instance of the at least two repeated words;

transforming the first set of groups of words to a second set of groups of words;

determining whether there are two identical groups of words from the second set of groups of words;

if there are two identical groups of words from the second set of groups of words,

determining that the segment is the garbled suggestion; and

if there are no two identical groups of words from the second set of groups of words,

determining that the segment is not the garbled suggestion.

8. A system having at least one processor, storage, and a communication platform for providing query suggestions, the system comprising:

an interface implemented on the at least one processor and configured to receive a query from a user;

a suggesting engine implemented on the at least one processor and configured to obtain a plurality of suggestions with respect to the query; and

a garbled suggestion filter implemented on the at least one processor and configured to

identify one or more of the plurality of suggestions that are garbled, wherein each of the one or more of the plurality of suggestions comprises at least one repeated word, the identifying being based on a model trained to recognize a linguistic connection between the at least one repeated word; and

remove the one or more of the plurality of suggestions,

wherein the suggesting engine is further configured to provide the plurality of suggestions without the one or more of the plurality of suggestions to the user in response to the query.

9. The system of claim 8, wherein the at least one repeated word comprises one repeated word, the garbled suggestion filter is further configured to:

determine whether a suggestion of the plurality of suggestions comprises one repeated word; and

when it is determined that the suggestion comprises one repeated word,

generate a plurality of groups of words of the suggestion, each comprising an instance of the repeated word;

determine a correlation among the plurality of groups of words; and

determine whether the suggestion is a garbled suggestion based on the correlation, wherein the garbled suggestion comprises a suggestion that causes confusion.

10. The system of claim 9, wherein the garbled suggestion filter is further configured to:

assign a part of speech (POS) tag to each word of the suggestion; and

integrate one or more words to form a group based on the assigned POS tags.

11. The system of claim 9, wherein the correlation indicates whether two groups of words are connected via at least a conjunction word.

12. The system of claim 8, wherein the at least one repeated word comprises at least two repeated words, the garbled suggestion filter is further configured to:

determine whether a suggestion of the plurality of suggestions comprises at least two repeated word; and

when it is determined that the suggestion comprises at least two repeated words, determine whether the suggestion comprises at least one conjunction word; and

if the suggestion comprises no conjunction word,

generate a first set of groups of words of the suggestion, each comprising an instance of the at least two repeated words;

transform the first set of groups of words to a second set of groups of words;

determine whether there are two identical groups of words from the second set of groups of words;

if there are two identical groups of words from the second set of groups of words,

determine that the suggestion is a garbled suggestion, wherein the garbled suggestion comprises a suggestion that causes confusion; and

if there are no two identical groups of words from the second set of groups of words,

determine that the suggestion is not the garbled suggestion.

13. The system of claim 12, wherein the garbled suggestion filter is further configured to:

if the suggestion comprises at least one conjunction word,

generate one or more segments of the suggestion separated by the at least one conjunction word;

determine whether at least one of the one or more segments is a garbled segment; and

when it is determined that at least one of the one or more segments is a garbled segment, determine that the suggestion is the garbled suggestion.

14. The system of claim 13, wherein the garbled suggestion filter being configured to determine whether the at least one of the one or more segments is the garbled segment comprises the garbled suggestion filter being further configured to:

generate a first set of groups of words of the suggestion for each of the one or more segments, each comprising an instance of the at least two repeated words;

transform the first set of groups of words to a second set of groups of words;

determine whether there are two identical groups of words from the second set of groups of words;

if there are two identical groups of words from the second set of groups of words,

determine that the segment is the garbled suggestion; and

if there are no two identical groups of words from the second set of groups of words,

determine that the segment is not the garbled suggestion.

15. A non-transitory machine-readable storage medium having information recorded thereon for providing query suggestions, wherein the information, when read by the machine, causes the machine to perform the following:

receiving a query from a user;

obtaining a plurality of suggestions with respect to the query;

identifying one or more of the plurality of suggestions that are garbled, wherein each of the one or more of the plurality of suggestions comprises at least one repeated word, the identifying being based on a model trained to recognize a linguistic connection between the at least one repeated word;

removing the one or more of the plurality of suggestions; and

providing the plurality of suggestions without the one or more of the plurality of suggestions to the user in response to the query.

16. The medium of claim 15, wherein the information associated with identifying the one or more of the plurality of suggestions, when read by the machine, causes the machine to further perform the following:

determining whether a suggestion of the plurality of suggestions comprises one repeated word, wherein the at least one repeated word comprises one repeated word; and

when it is determined that the suggestion comprises one repeated word,

generating a plurality of groups of words of the suggestion, each comprising an instance of the repeated word;

determining a correlation among the plurality of groups of words; and

determining whether the suggestion is a garbled suggestion based on the correlation, wherein the garbled suggestion comprises a suggestion that causes confusion.

17. The medium of claim 16, wherein the information associated with generating the plurality of groups of words of the suggestion, when read by the machine, causes the machine to further perform the following:

assigning a part of speech (POS) tag to each word of the suggestion; and

integrating one or more words to form a group based on the assigned POS tags.

18. The medium of claim 16, wherein the correlation indicates whether two groups of words are connected via at least a conjunction word.

19. The medium of claim 15, wherein the information associated with identifying the one or more of the plurality of suggestions, when read by the machine, causes the machine to further perform the following:

determining whether a suggestion of the plurality of suggestions comprises at least two repeated word, wherein the at least one repeated word comprises at least two repeated word; and

when it is determined that the suggestion comprises at least two repeated words, determining whether the suggestion comprises at least one conjunction word;

if the suggestion comprises no conjunction word,

generating a first set of groups of words of the suggestion, each comprising an instance of the at least two repeated words;

transforming the first set of groups of words to a second set of groups of words;

determining whether there are two identical groups of words from the second set of groups of words;

if there are two identical groups of words from the second set of groups of words,

determining that the suggestion is a garbled suggestion, wherein the garbled suggestion comprises a suggestion that causes confusion; and

if there are no two identical groups of words from the second set of groups of words,

determining that the suggestion is not the garbled suggestion; and

if the suggestion comprises at least one conjunction word,

generating one or more segments of the suggestion separated by the at least one conjunction word;

determining whether at least one of the one or more segments is a garbled segment; and

when it is determined that at least one of the one or more segments is the garbled segment,

determining that the suggestion is the garbled suggestion.

20. The medium of claim 19, wherein the information associated with determining whether the at least one of the one or more segments is the garbled segment, when read by the machine, causes the machine to further perform the following:

generating a first set of groups of words of the suggestion for each of the one or more segments, each comprising an instance of the at least two repeated words;

transforming the first set of groups of words to a second set of groups of words;

determining whether there are two identical groups of words from the second set of groups of words;

if there are two identical groups of words from the second set of groups of words, determining that the segment is the garbled suggestion; and

if there are no two identical groups of words from the second set of groups of words, determining that the segment is not the garbled suggestion.