Filter recommendation based on historical search result selection

Patent metadata

Field	Value
Publication number	US-11544324-B2
Application number	US-202117181453-A
Country	US
Kind code	B2
Filing date	Feb 22, 2021
Priority date	Feb 22, 2021
Publication date	Jan 3, 2023
Grant date	Jan 3, 2023

Abstract

Techniques for suggesting filters for query terms based on previously selected query results are disclosed. Common characteristics of previously selected query results are presented as a filter. A system trains a machine learning model by obtaining historical data including query characteristics and selected query results. Based on the historical data, the system trains the machine learning model to associate the first filter field with the first search term. The system receives a first query for execution. The system applies the machine learning model to the first query to identify the first filter field as a suggestion. The system: recommends the first field for filtering a first set of search results corresponding to the first query. Responsive to receiving user input selecting a first value for the first filter field, the system filters using the first value to generate a set of filtered search results, and presents the filtered search results.

First claim

What is claimed is:

1. One or more non-transitory machine-readable media storing instructions which, when executed by one or more processors, causing execution of operations comprising:
training a machine learning model to suggest filtering fields for executing a query at least by:
obtaining sets of historical data, each set of historical data comprising (a) query characteristics corresponding to a corresponding query, and (b) a search result selected from a plurality of search results corresponding to the query;
identifying a search result characteristic that is common across selected search results for queries associated with a same particular set of query characteristics;
identifying a first filter field, of a plurality of available filter fields, that includes functionality to select a subset of search results corresponding to the search result characteristic;
training the machine learning model (a) to associate the first filter field with the particular set of query characteristics without (b) associating a second filter field, of the plurality of available filter fields, with the particular set of query characteristics;

receiving a first query for execution;
determining that the first query is associated with particular set of query characteristics;
applying the machine learning model to the particular set of query characteristics associated with the first query, wherein the machine learning model identifies the first filter field a suggestion without identifying the second filter field as a suggestion;
based on the applying operation: recommending the first field for filtering a first set of search results corresponding to the first query without recommending the second filter field;
receiving user input selecting a first value for the first filter field;
filtering the first set of search results corresponding to the first query based on the first value for the first filter field to generate a filtered set of search results;
presenting the filtered set of search results.

2. The media of claim 1 , wherein the particular set of query characteristics comprises characteristics of a query requestor.

3. The media of claim 1 , wherein the particular set of query characteristics comprises a query term.

4. The media of claim 1 , wherein the sets of historical data are associated with queries from a single user.

5. The media of claim 1 , the operations further comprising recommending a candidate filter value as the first value for the first filter field based on the sets of historical data.

6. The media of claim 1 , the operations further comprising:
subsequent to identifying the first filter field as a suggestion, determining the first value as a suggestion, wherein the first value is a filter field value determined at least in part based on the identified first filter field;
wherein recommending the first field for filtering the first set of search results corresponding to the first query further comprises recommending the first value.

7. The media of claim 1 , wherein training the machine learning model comprises training the machine learning model to associate the first value for the first filter field with the first search term, and wherein the recommending the first filter field comprises recommending the first value for the first filter field for filtering the first set of search results.

8. The media of claim 1 , the operations further comprising:
recommending a candidate filter value as the first value for the first filter field;
wherein the particular set of query characteristics comprises characteristics of one or more of: (a) a query requestor or (b) a query term;
wherein the sets of historical data are associated with queries from a single user.

9. A method comprising:
training a machine learning model to suggest filtering fields for executing a query at least by:
obtaining sets of historical data, each set of historical data comprising (a) query characteristics corresponding to a corresponding query, and (b) a search result selected from a plurality of search results corresponding to the query;
identifying a search result characteristic that is common across selected search results for queries associated with a same particular set of query characteristics;
identifying a first filter field, of a plurality of available filter fields, that includes functionality to select a subset of search results corresponding to the search result characteristic;
training the machine learning model (a) to associate the first filter field with the particular set of query characteristics without (b) associating a second filter field, of the plurality of available filter fields, with the particular set of query characteristics;

receiving a first query for execution;
determining that the first query is associated with particular set of query characteristics;
applying the machine learning model to the particular set of query characteristics associated with the first query, wherein the machine learning model identifies the first filter field a suggestion without identifying the second filter field as a suggestion;
based on the applying operation: recommending the first field for filtering a first set of search results corresponding to the first query without recommending the second filter field;
receiving user input selecting a first value for the first filter field;
filtering the first set of search results corresponding to the first query based on the first value for the first filter field to generate a filtered set of search results;
presenting the filtered set of search results,
wherein the method is performed by at least one device including a hardware processor.

10. The method of claim 9 , wherein the particular set of query characteristics comprises characteristics of a query requestor.

11. The method of claim 9 , wherein the particular set of query characteristics comprises a query term.

12. The method of claim 9 , wherein the sets of historical data are associated with queries from a single user.

13. The method of claim 9 , further comprising recommending a candidate filter value as the first value for the first filter field based on the sets of historical data.

14. The method of claim 9 , further comprising:
subsequent to identifying the first filter field as a suggestion, determining the first value as a suggestion, wherein the first value is a filter field value determined at least in part based on the identified first filter field;
wherein recommending the first field for filtering the first set of search results corresponding to the first query further comprises recommending the first value.

15. The method of claim 9 , wherein training the machine learning model comprises training the machine learning model to associate the first value for the first filter field with the first search term, and wherein the recommending the first filter field comprises recommending the first value for the first filter field for filtering the first set of search results.

16. A system comprising:
at least one device including a hardware processor;
the system being configured to perform operations comprising:
training a machine learning model to suggest filtering fields for executing a query at least by:
obtaining sets of historical data, each set of historical data comprising (a) query characteristics corresponding to a corresponding query, and (b) a search result selected from a plurality of search results corresponding to the query;
identifying a search result characteristic that is common across selected search results for queries associated with a same particular se

Assignees

• Oracle Int Corp

Inventors

• Li Garrick
• Cooperman Hillel Noah
• Candland Kathleen Maguire
• Naghshin Rozita
• Singh Rohit Kumar

Classifications

• G06F16/90335

  Query processing · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F16/9032 Primary

  Query formulation · CPC title

• G06F16/90324 Primary

  using system suggestions · CPC title