Search query intent

• US 10,296,659 B2
• Filed: 09/26/2016
• Issued: 05/21/2019
• Est. Priority Date: 09/26/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: DeLuca, Lisa Seacat, Gert van der stockt, Stefan A.
• Primary Examiner(s): Reyes, Mariela
• Assistant Examiner(s): Jacobs, Edward
• Application Number:
  US15/275,574
• Publication Number:
  US 20180089332A1
• Time in Patent Office: 967 Days
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/90328 using search space presentation or visualization, e.g. category or range presentation and selection
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

A method and system for improving a search query process is provided. The method includes analyzing via a natural language classifier (NLC) circuit of a hardware device, a partial search phase entered in a search field of a graphical user interface with respect to a search query for specified subject matter. A subject based intent classification associated with the search query is determined and compared to intent based data of an intent data repository. In response, an autocomplete phrase associated with the subject based intent classification and the partial search phrase is generated and presented to a user via the graphical user interface.

Claims

1. A Website search query improvement method comprising:

analyzing, by a processor enabling a natural language classifier (NLC) circuit of an embedded hardware device, a partial search phrase entered in a search field of a graphical user interface (GUI) with respect to a search query for specified subject matter;

continuously detecting, by the NLC circuit via execution of an automated natural language search query, all possible patterns of the partial search phrase;

matching, by the NLC circuit, all of the detected possible patterns with respect to information within an autocomplete result repository database;

executing, by the NLC circuit, a deep learning process for automated prediction of classes and categories for the partial search phrase;

triggering, by the NLC circuit, an action with respect to software application execution;

determining via application of an application programming interface (API), by the processor executing the NLC circuit with respect to results of the analyzing, a subject based intent classification associated with the search query for content classifications defined within a ground truth for the Website;

determining, by the NLC circuit, that said subject based intent classification comprises a confidence factor of less than 100 percent confidence with respect to the subject based intent classification being correct;

comparing, by the processor, the subject based intent classification to intent based data of an intent data repository;

generating, by said processor based on results of said determining that said subject based intent classification comprises a confidence factor of less than 100 percent confidence and said comparing, a subset of search results of search results data, wherein said subset of search results correlates to said subject based intent classification;

automatically generating, by the processor based on results of the comparing, the matching, the executing, the triggering, the generating, and the detecting, an autocomplete phrase associated with the subject based intent classification and the partial search phrase;

presenting, by said processor to a user via an autocomplete selection mechanism comprising a specialized circuit and the GUI, the autocomplete phrase in combination with additional autocomplete phrases and a single percentage value of said confidence factor, wherein said single percentage value comprises a single composite value indicating a top intent subject classification value associated with said autocomplete phrase in combination with additional autocomplete phrases, and wherein said single percentage value of said confidence factor is presented in a specified arrangement, via said GUI, adjacent to and in between said partial search phrase entered in said search field and said autocomplete phrase in combination with additional autocomplete phrases;

executing, by said processor, an improved Web based search with respect to said autocomplete phrase;

directing, by said processor based on results of said executing, a Web application to a specified Web location associated with said autocomplete phrase and said Website;

presenting, by said processor based on results of said directing, classes of information associated with said autocomplete phrase, wherein said classes of information are configured to enable said triggering;

receiving, by said processor, additional context associated with an additional subset of results determined to be more relevant to said user; and

refining, by said processor executing an auto complete circuit of said embedded hardware device, said additional subset of results based on a specific determined intent of the user thereby yielding a tailored list of auto-completion results for said partial search phrase.

2. The method of claim 1, wherein the intent based data comprises data retrieved during previous search queries associated with the subject based intent classification.

3. The method of claim 1, further comprising:

transmitting, by the processor to the intent data repository, said autocomplete phrase, wherein the autocomplete phrase is stored in the intent data repository.

4. The method of claim 1, wherein the query is associated with a specified Website network.

5. The method of claim 1, wherein the presenting the autocomplete phrase comprises presenting a confidence percentage value with the autocomplete phrase, and wherein the confidence percentage value is associated with a confidence factor with respect to the intent classification.

6. The method of claim 1, wherein the autocomplete phrase comprises a portion of the partial search phrase.

7. The method of claim 1, further comprising:

providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable code in the hardware device, the code being executed by the computer processor to implement;

the determining, the comparing, the automatically generating, and the presenting.

8. A computer program product, comprising a computer readable hardware storage device storing a computer readable program code, said computer readable program code comprising an algorithm that when executed by a processor of a hardware device implements a Website search query improvement method, the method comprising:

analyzing, by the processor enabling a natural language classifier (NLC) circuit of an embedded hardware device, a partial search phrase entered in a search field of a graphical user interface (GUI) with respect to a search query for specified subject matter;

continuously detecting, by the NLC circuit via execution of an automated natural language search query, all possible patterns of the partial search phrase;

matching, by the NLC circuit, all of the detected possible patterns with respect to information within an autocomplete result repository database;

executing, by the NLC circuit, a deep learning process for automated prediction of classes and categories for the partial search phrase;

triggering, by the NLC circuit, an action with respect to software application execution;

determining via application of an application programming interface (API), by the processor executing the NLC circuit with respect to results of the analyzing, a subject based intent classification associated with the search query for content classifications defined within a ground truth for the Website;

determining, by the NLC circuit, that said subject based intent classification comprises a confidence factor of less than 100 percent confidence with respect to the subject based intent classification being correct;

comparing, by the processor, the subject based intent classification to intent based data of an intent data repository;

generating, by said processor based on results of said determining that said subject based intent classification comprises a confidence factor of less than 100 percent confidence and said comparing, a subset of search results of search results data, wherein said subset of search results correlates to said subject based intent classification;

automatically generating, by the processor based on results of the comparing, the matching, the executing, the triggering, the generating, and the detecting, an autocomplete phrase associated with the subject based intent classification and the partial search phrase;

presenting, by said processor to a user via an autocomplete selection mechanism comprising a specialized circuit and the GUI, the autocomplete phrase in combination with additional autocomplete phrases and a single percentage value of said confidence factor, wherein said single percentage value comprises a single composite value indicating a top intent subject classification value associated with said autocomplete phrase in combination with additional autocomplete phrases, and wherein said single percentage value of said confidence factor is presented in a specified arrangement, via said GUI, adjacent to and in between said partial search phrase entered in said search field and said autocomplete phrase in combination with additional autocomplete phrases;

executing, by said processor, an improved Web based search with respect to said autocomplete phrase;

directing, by said processor based on results of said executing, a Web application to a specified Web location associated with said autocomplete phrase and said Website;

presenting, by said processor based on results of said directing, classes of information associated with said autocomplete phrase, wherein said classes of information are configured to enable said triggering;

receiving, by said processor, additional context associated with an additional subset of results determined to be more relevant to said user; and

refining, by said processor executing an auto complete circuit of said embedded hardware device, said additional subset of results based on a specific determined intent of the user thereby yielding a tailored list of auto-completion results for said partial search phrase.

9. The computer program product of claim 8, wherein the intent based data comprises data retrieved during previous search queries associated with the subject based intent classification.

10. The computer program product of claim 8, wherein said method further comprises:

transmitting, by the processor to the intent data repository, said autocomplete phrase, wherein the autocomplete phrase is stored in the intent data repository.

11. The computer program product of claim 8, wherein the query is associated with a specified Website network.

12. The computer program product of claim 8, wherein the presenting the autocomplete phrase comprises presenting a confidence percentage value with the autocomplete phrase, and wherein the confidence percentage value is associated with a confidence factor with respect to the intent classification.

13. The computer program product of claim 12, wherein the method further comprises:

presenting, by the processor, additional suggested autocomplete phrases associated with the said confidence percentage value and the autocomplete phrase.

14. A hardware device comprising a processor coupled to a computer-readable memory unit, the memory unit comprising instructions that when executed by the processor executes a Website search query improvement method comprising:

analyzing, by said processor enabling a natural language classifier (NLC) circuit of an embedded hardware device, a partial search phrase entered in a search field of a graphical user interface (GUI) with respect to a search query for specified subject matter;

continuously detecting, by the NLC circuit via execution of an automated natural language search query, all possible patterns of the partial search phrase;

matching, by the NLC circuit, all of the detected possible patterns with respect to information within an autocomplete result repository database;

executing, by the NLC circuit, a deep learning process for automated prediction of classes and categories for the partial search phrase;

triggering, by the NLC circuit, an action with respect to software application execution;

determining via application of an application programming interface (API), by the processor executing the NLC circuit with respect to results of the analyzing, a subject based intent classification associated with the search query for content classifications defined within a ground truth for the Website;

determining, by the NLC circuit, that said subject based intent classification comprises a confidence factor of less than 100 percent confidence with respect to the subject based intent classification being correct;

comparing, by the processor, the subject based intent classification to intent based data of an intent data repository;

generating, by said processor based on results of said determining that said subject based intent classification comprises a confidence factor of less than 100 percent confidence and said comparing, a subset of search results of search results data, wherein said subset of search results correlates to said subject based intent classification;

automatically generating, by the processor based on results of the comparing, the matching, the executing, the triggering, the generating, and the detecting, an autocomplete phrase associated with the subject based intent classification and the partial search phrase;

presenting, by said processor to a user via an autocomplete selection mechanism comprising a specialized circuit and the GUI, the autocomplete phrase in combination with additional autocomplete phrases and a single percentage value of said confidence factor, wherein said single percentage value comprises a single composite value indicating a top intent subject classification value associated with said autocomplete phrase in combination with additional autocomplete phrases, and wherein said single percentage value of said confidence factor is presented in a specified arrangement, via said GUI, adjacent to and in between said partial search phrase entered in said search field and said autocomplete phrase in combination with additional autocomplete phrases;

executing, by said processor, an improved Web based search with respect to said autocomplete phrase;

directing, by said processor based on results of said executing, a Web application to a specified Web location associated with said autocomplete phrase and said Website;

presenting, by said processor based on results of said directing, classes of information associated with said autocomplete phrase, wherein said classes of information are configured to enable said triggering;

receiving, by said processor, additional context associated with an additional subset of results determined to be more relevant to said user; and

refining, by said processor executing an auto complete circuit of said embedded hardware device, said additional subset of results based on a specific determined intent of the user thereby yielding a tailored list of auto-completion results for said partial search phrase.

15. The hardware device of claim 14, wherein the intent based data comprises data retrieved during previous search queries associated with the subject based intent classification.

16. The hardware device of claim 14, wherein said method further comprises:

transmitting, by the processor to the intent data repository, said autocomplete phrase, wherein the autocomplete phrase is stored in the intent data repository.

17. The hardware device of claim 14, wherein the query is associated with a specified Website network.