Smart filters and search

Patent metadata

Field	Value
Publication number	US-11720560-B2
Application number	US-202117181434-A
Country	US
Kind code	B2
Filing date	Feb 22, 2021
Priority date	Feb 22, 2021
Publication date	Aug 8, 2023
Grant date	Aug 8, 2023

Abstract

Techniques for suggesting a filter field based on a user input are disclosed. A system trains a machine learning model by obtaining historical data including sets of user search input, including a first search term and a first value for a first filter field. 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, causes performance of operations comprising:
training a machine learning model to suggest filtering fields for executing a query at least by:
obtaining historical data comprising sets of user input for executing searches, wherein a particular set of user input, in the sets of user input, comprises (a) a first search term and (b) a first value for a first filter field, the first filter field being selected from a plurality of filter fields comprising the first filter field and a second filter field;
based on the historical data, training the machine learning model to associate the first filter field with the first search term without associating the second filter field with the first search term;

receiving a first query for execution, the first query comprising the first search term;
applying the machine learning model to the first search term in the first query, wherein the machine learning model identifies the first filter field as a suggestion without identifying the second filter field as a suggestion, wherein the machine learning model does not associate any value with the first filter field;
based on the applying operation: recommending the first filter field for filtering a first set of search results corresponding to the first query without recommending the second filter field and without recommending any value for the first 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 operations further comprise:
determining whether the machine learning model associates any value with the first filter field,
wherein recommending the first filter field without recommending any value for the first filter field is performed based on determining the machine learning model does not associate any value with the first filter field,
wherein training the machine learning model comprises training the machine learning model to associate a second value for a second filter field with a second search term,
wherein the operations further comprise:
receiving a second query comprising the second search term;
applying the machine learning model to the second search term in the second query;
based on applying the machine learning model to the second search term: recommending the second filter field for filtering a second set of search results corresponding to the second query;
determining whether the machine learning model associates any value with the second filter field; and
based on determining that the machine learning model associates the second value with the second filter field, recommending the second value for the second filter field for filtering the second set of search results.

3. The media of claim 2 , the operations further comprising:
receiving a second query comprising the second search term;
applying the machine learning model to the second search term in the second query;
based on applying the machine learning model to the second search term: recommending the second filter field for filtering a second set of search results corresponding to the second query; and
recommending a particular value for the second filter field based on the second query.

4. The media of claim 3 , the operations further comprising:
subsequent to identifying the second filter field as a suggestion, determining the second value as a suggestion, wherein the second value is a filter field value determined at least in part based on the identified second filter field;
wherein recommending the second filter field for filtering the second set of search results corresponding to the second query further comprises recommending the second value.

5. The media of claim 1 , the operations further comprising:
subsequent to presenting the filtered set of search results: receiving a second query for execution, the second query comprising a second search term;
recommending a second filter field for further filtering the filtered search results, the second filter field being recommended based on the first search term and the second search term;
receiving user input selecting a particular value for the second filter field;
further filtering the filtered search results based on the particular value for the second filter field to generate a twice-filtered set of search results;
presenting the twice-filtered set of search results.

6. The media of claim 1 , the operations further comprising:
based on the filtered set of search results, selecting one or more candidate filter fields to be applied to the filtered set of search results.

7. The media of claim 1 , the operations further comprising:
associating the first filter field with a particular icon;
wherein recommending the first filter field for filtering comprises displaying the first filter field in association with the particular icon.

8. The media of claim 1 , the operations further comprising:
associating the first filter field with a particular icon, wherein recommending the first filter field for filtering comprises displaying the first filter field in association with the particular icon;
based on the filtered set of search results, selecting one or more candidate filter fields to be applied to the filtered set of search results;
subsequent to presenting the filtered search results: receiving a second query for execution, the second query comprising a second search term;
recommending a second filter field for further filtering the filtered search results, the second filter field being recommended based on the first search term and the second search term;
receiving user input selecting a particular value for the second filter field;
further filtering the filtered search results based on the particular value for the second filter field to generate a twice-filtered set of search results;
presenting the twice-filtered set of search results.

9. One or more non-transitory machine-readable media storing instructions which, when executed by one or more processors, cause:
training a machine learning model to suggest filtering fields for executing a query at least by:
obtaining historical data comprising sets of user input for executing searches;
wherein each set of user input, in the sets of user input, defines one or more values for one or more filter fields for filtering a set of search results;
wherein the sets of user input are received from (a) a single user associated with a particular set of user characteristics or (b) a set of users associated with the same particular set of user characteristics;
based on the historical data training the machine learning model to (a) associate a first filter field, of a plurality of filter fields available for executing the searches, with searches executed by users associated with the particular set of user characteristics without (b) associating a second filter field, of the plurality of filter fields available for executing the searches, with searches executed by users associated with the particular set of user characteristics;

receiving a first query for execution, the first query being received from a first user;
determining that the first user is associated with the particular set of user characteristics;
responsive to determining that the first user is associated with the particular set of user characteristics:
applying the machine learning model to the particular set of user characteristics, whe

Assignees

• Oracle Int Corp

Inventors

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

Classifications

• G06F16/24539 Primary

  using cached or materialised query results · CPC title

• G06F3/04817

  using icons (graphical or visual programming using iconic symbols G06F8/34) · CPC title

• G06F16/248

  Presentation of query results · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F16/3322 Primary

  using system suggestions (G06F16/3325 takes precedence) · CPC title