Providing search results based on natural language classification confidence information

• US 10,268,734 B2
• Filed: 09/30/2016
• Issued: 04/23/2019
• Est. Priority Date: 09/30/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: DeLuca, Lisa Seacat
• Primary Examiner(s): Cao, Phuong Thao
• Application Number:
  US15/281,529
• Publication Number:
  US 20180095964A1
• Time in Patent Office: 935 Days
• Field of Search: 707731
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A computer-implemented method includes: receiving, by a computing device, a search query from a client device; obtaining, by the computing device, classification and confidence information by applying natural language classification to the search query; generating, by the computing device, search results based on the classification and confidence information, wherein a ratio of the search results is based on the classification and confidence information; and providing, by the computing device, the search results to the client device.

Claims

1. A computer-implemented method comprising:

receiving, by a computing device, a search query from a client device;

obtaining, by the computing device, classification and confidence information by applying natural language classification to the search query;

generating, by the computing device, search results based on the classification and confidence information, wherein;

the classification and confidence information indicates a plurality of classifications associated with the search query and respective confidence levels associated with each of the plurality of classifications,

the generating comprises filtering a total number of documents included in the search results such that the ratio of the search results associated with each classification to the total number of documents included in the search results matches the respective confidence levels,

the obtaining the classification and confidence information comprises providing the search query to a natural language classification server with a host identifier to cause the natural language classification server to apply a custom natural language classification algorithm, associated with the host identifier, that has been preconfigured for a host server, based on resources previously provided by the host server to the natural language classification server, to direct the natural language classification server to apply the natural language classification to the search query; and

receiving the classification and confidence information from the natural language classification server; and

providing, by the computing device, the search results to the client device.

2. The method of claim 1, wherein the search results are ranked based on the classification and confidence information.

3. The method of claim 1, wherein the custom natural language classification algorithm includes a custom index of words or phrases that map to candidate classifications.

4. The method of claim 1, further comprising, generating an initial set of search results based on the search query, wherein generating the search results based on the classification and confidence information comprises filtering the initial set of search results based on the classification and confidence information.

5. The method of claim 1, wherein the classification information relates to a subject or intent of the search query and the confidence information relates to a likelihood that the search query related to the subject or intent.

6. The method of claim 1, wherein the search query is received via a search toolbar on a web page or application associated with a host or service provider.

7. The method of claim 1, wherein a service provider at least one of creates, maintains, deploys and supports the computing device.

8. The method of claim 1, wherein steps of claim 1 are provided by a service provider on a subscription, advertising, and/or fee basis.

9. The method of claim 1, wherein the computing device includes software provided as a service in a cloud environment.

10. The method of claim 1, further comprising deploying a system for generating search results based on the classification and confidence information, comprising providing a computer infrastructure operable to perform the steps of claim 1.

11. The method of claim 1, wherein the classification and confidence information is obtained from the search query.

12. The method of claim 11, wherein the classification and confidence information is not obtained from the search results.

13. The method of claim 12, wherein the classification and confidence information is obtained independently of user instruction defining the classification and confidence information.

14. The method of claim 1, wherein the resources previously provided by the host server to the natural language classification server include at least one selected from a group consisting of:

products;

support; and

content.

15. A computer program product for generating search results based on classification and confidence information, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

receive a search query from a client device;

obtain classification and confidence information, wherein the obtaining comprises;

providing the search query to a natural language classification server with a host identifier to cause the natural language classification server to apply a custom natural language classification algorithm, associated with the host identifier, that has been custom tailored for a host server, based on resources previously provided by the host server to the natural language classification server, to direct the natural language classification server to apply the natural language classification to the search query and generate the classification and confidence information on behalf of the computing device, and

receiving the classification and confidence information from the natural language classification server, wherein the classification information relates to a subject or intent of the search query and the confidence information relates to a likelihood that the search query related to the subject or intent;

generate search results based on the classification and confidence information, wherein;

the classification and confidence information indicates a plurality of classifications associated with the search query and respective confidence levels associated with each of the plurality of classifications;

the generating comprises filtering a total number of documents included in the search results such that the ratio of the search results associated with each classification to the total number of documents included in the search results matches the respective confidence levels; and

provide the search results to the client device.

16. The computer program product of claim 15, wherein the custom natural language classification algorithm includes a custom index of words or phrases that map to candidate classifications.

17. The computer program product of claim 15, wherein generating the search results includes ranking the search results based on the classification and confidence information.

18. The computer program product of claim 15, wherein the classification and confidence information is obtained independently of a user instruction defining classification and confidence information.

19. A system comprising:

a CPU, a computer readable memory and a computer readable storage medium associated with a computing device;

program instructions to receive a search query from a client device;

program instructions to provide the search query to a natural language classification server with a host identifier to cause the natural language classification server to apply a custom natural language classification algorithm, associated with the host identifier, that has been custom tailored for a host server, based on resources previously provided by the host server to the natural language classification server, to direct the natural language classification server to apply the natural language classification to the search query and generate classification and confidence information based on receiving the search query, wherein the classification information relates to a subject or intent of the search query and the confidence information relates to a likelihood that the search query related to the subject or intent;

program instructions to receive the classification and confidence information from the natural language classification server;

program instructions to generate an initial set of search results based on the search query;

program instructions to filter a total number of documents included in the initial search results such that the ratio of the search results associated with each classification to the total number of documents included in the initial search results matches the respective confidence levels wherein;

the classification and confidence information indicates a plurality of classifications associated with the search query and respective confidence levels associated with each of the plurality of classifications; and

program instructions to provide the filtered search results to the client device,

wherein the program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.

20. The system of claim 19, wherein the classification and confidence information is obtained independently of a user instruction defining classification and confidence information.