Natural language search using facets

Patent metadata

Field	Value
Publication number	US-10776408-B2
Application number	US-201715403300-A
Country	US
Kind code	B2
Filing date	Jan 11, 2017
Priority date	Jan 11, 2017
Publication date	Sep 15, 2020
Grant date	Sep 15, 2020

Abstract

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a query for a search result and identifying at least one entity in the query, discovering a facet-entity mapping corresponding to the entity from a knowledgebase. A facet in the facet-entity mapping is a property configured in the knowledgebase and an entity is an instance of the facet. The facet-entity mapping is displayed for the user and the query is searched from content, and the search result presented based on the facet and the entity from the facet-entity mapping.

First claim

What is claimed is:

1. A computer implemented method for a facet-based search, comprising:
obtaining, by one or more processor of a computer, a query for a search result from a user;
identifying at least one entity in the query, by use of an entity extraction application programming interface (API) utilizing machine learning based natural language processing tools, the entity extraction API returns, as the at least one entity, top-matching predefined classes present in the query and contents of one or more domain subject to the facet-based search, wherein an entity of the at least one entity is an instance of a facet amongst a plurality of facets that are configured in a knowledgebase for classification of the contents of the one or more domain;
discovering a facet-entity mapping corresponding to the identified entity in the query, the facet-entity mapping being available from the knowledgebase, the facet-entity mapping comprising the entity and the facet; and
displaying the facet-entity mapping before transmitting the query for the search result from the user.

2. The computer implemented method of claim 1 , further comprising;
setting the facet and the entity from the facet-entity mapping to modify the search result for the user, based on a feedback by the user on the facet-entity mapping responsive to the displaying.

3. The computer implemented method of claim 2 , further comprising:
filtering out content having a corresponding facet that is unrelated to the facet of the facet-entity mapping from searching by the query for the search result.

4. The computer implemented method of claim 3 , wherein the filtering is performed during one occasion selected from the group consisting of: as the user is typing the query, as the user is speaking the query, when the user pauses during entry of the query, and on hover of a portion of the query.

5. The computer implemented method of claim 1 , further comprising:
ascertaining that no facet-entity mapping is remaining for the facet-based search that the user had de-selected the displayed facet-entity mapping by use of a feedback by the user on the facet-entity mapping responsive to the displaying; and
generating and presenting the search result based on at least one keyword from the query.

6. A computer program product comprising:
a computer readable storage medium readable by one or more processor and storing instructions for execution by the one or more processor for performing a method for a facet-based search, comprising:
obtaining, by the one or more processor, a query for a search result from a user;
identifying at least one entity in the query, by use of an entity extraction application programming interface (API) utilizing machine learning based natural language processing tools, the entity extraction API returns top-matching predefined classes present in the query and contents of one or more domain subject to the facet-based search, wherein an entity of the at least one entity is an instance of one or more facet amongst a plurality of facets that are configured in a knowledgebase for classification of the contents of the one or more domain;
discovering one or more facet-entity mapping corresponding to the identified entity in the query, the one or more facet-entity mapping being available from the knowledgebase, the one or more facet-entity mapping comprising the entity and each of the one or more facet;
displaying, the one or more facet-entry mapping before transmitting the query for the search result from the user.

7. A system comprising:
a memory;
one or more processor in communication with the memory; and
program instructions executable by the one or more processor via the memory to perform a method for a facet-based search, comprising:
obtaining, by the one or more processor, a query for a search result from a user;
identifying at least one entity in the query, by use of an entity extraction application programming interface (API) utilizing machine learning based natural language processing tools, the entity extraction API returns, as the at least one entity, top-matching predefined classes present in the query and contents of one or more domain subject to the facet-based search, wherein an entity of the at least one entity is an instance of a facet that is a configured property in a knowledgebase for classification of the contents of the one or more domain;
discovering a facet-entity mapping corresponding to the identified entity in the query, the facet-entity mapping being available from the knowledgebase, the facet-entity mapping comprising the entity and the facet; and
displaying, the facet-entry mapping before transmitting the query for the search result from the user.

8. The system of claim 7 , wherein the displaying of the discovered facet-entity mapping includes a corresponding turn-off button such that the user may provide a feedback that de-selects the discovered facet-entity mapping.

9. The system of claim 8 , further comprising;
setting the facet and the entity from the facet-entity mapping to modify the search result for the user.

10. The system of claim 9 , wherein retrieve and rank criteria for the facet-based search are set based on the facet and the entity, further comprising:
filtering out content having a corresponding facet that is unrelated to the facet of the facet-entity mapping from searching by the query for the search result, wherein the filtering is performed during one occasion selected from the group consisting of: as the user is typing the query, as the user is speaking the query, when the user pauses during entry of the query, and on hover of a portion of the query.

11. The computer implemented method of claim 1 , the displaying comprising;
providing at least one turn-off button respectively corresponding to each of at least one facet-entity mapping including the facet-entity mapping from the discovering in order for the user to give a feedback by turning off each of the facet-entity mapping individually to thereby adjust facets applicable for the query in the facet-based search.

12. The computer implemented method of claim 11 , further comprising:
configuring the facet and the entity from the facet-entity mapping as one of retrieve-and-rank criteria for the search result, wherein the retrieve-and-rank criteria are applicable for limiting a scope of subject content to search and for ordering matches in the search result.

13. The computer implemented method of claim 3 , further comprising:
generating the search result by searching for the facet-entity mapping of the query against a subject content resulting from the filtering.

14. The computer implemented method of claim 13 , wherein the subject content comprises content respective to the one or more domain.

15. The computer implemented method of claim 11 , further comprising:
obtaining the feedback from the user via the turn-off button corresponding to the facet-entity mapping;
obtaining a search command for the query from the user;
identifying the search result by searching for selected facet-entity mapping of the query against a subject content, wherein the selected facet-entity mapping results from the feedback, wherein the subject content includes content respective to the one or more domain;
filtering out content having a corresponding facet that is unrelated to the facet of the facet-entity mapping from the search result from the identifying the search result; and
presenting the search result on the query to the user in order of retrieve and rank criteria for the search result from the filtering.

16. The computer imple

Assignees

• Int Buesiness Machines Corporation
• IBM

Inventors

• Altaf Faheem
• Deluca Lisa Seacat
• Srinivas Raghuram

Classifications

• G06F16/3323

  using document space presentation or visualization, e.g. category, hierarchy or range presentation and selection · CPC title

• G06F16/36

  Creation of semantic tools, e.g. ontology or thesauri · CPC title

• G06F16/338

  Presentation of query results · CPC title

• G06F16/3326 Primary

  using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages · CPC title

• G06F16/3329

  Natural language query formulation · CPC title