US 12,705,539 B2Granted

User interfaces and rule discovery and automation

AssigneesRakuten Mobile, Inc., Rakuten Symphony, Inc.

InventorsSandeep Kumar Nayak, Raja Jain

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system includes a medium configured to store instructions thereon; and a processor. The processor is configured to execute the instructions for instructing a display to display a first rule definition GUI displaying first attributes associated with a first rule, receiving a first multi-source dataset, training a machine learning tool using the first multi-source dataset, wherein the first set of attributes associated with the rule is used as input features for the machine learning model, dividing the first multi-source dataset into a set of clusters using a first unsupervised clustering technique, wherein the set of clusters includes: a first cluster; and a second cluster, determining second attributes associated with a second rule based on the set of clusters, determining a similarity of the first attributes of the first rule and the second attributes of the second rule, delivering, in response to the similarity exceeding a first threshold, a first recommendation.

Claims20

Dependent claims

A system comprising:

a non-transitory computer readable medium configured to store instructions thereon;
and
a processor connected to the non-transitory computer readable medium, wherein the processor is configured to execute the instructions for:
instructing a display to display a first rule definition graphical user interface (GUI) displaying first attributes associated with a first rule;
receiving a first multi-source dataset, wherein the first multi-source dataset comprises:
the first set of attributes associated with the first rule;
a first set of requests comprising a first set of characteristics;
training a machine learning tool using the first multi-source dataset;
wherein the first set of attributes associated with the rule is used as input features for the machine learning model;
dividing the first multi-source dataset into a set of clusters using a first unsupervised clustering technique, wherein the set of clusters comprises:
a first cluster;
a second cluster;
determining second attributes associated with a second rule based on the set of clusters;
determining a similarity of the first attributes of the first rule and the second attributes of the second rule;
delivering, in response to the similarity exceeding a first threshold, a first recommendation, wherein the delivering the first recommendation comprises:
instructing the display to display a second rule definition graphical user interface (GUI) displaying the second attributes associated with the second rule;
and
receiving an indication to approve or commit the second rule.

15 more elements

A method comprising:

instructing a display to display a first rule definition graphical user interface (GUI) displaying first attributes associated with a first rule;
receiving a first multi-source dataset, wherein the first multi-source dataset comprises:
the first set of attributes associated with the first rule;
a first set of requests comprising a first set of characteristics;
training a machine learning tool using the first multi-source dataset;
wherein the first set of attributes associated with the rule is used as input features for the machine learning model;
dividing the first multi-source dataset into a set of clusters using a first unsupervised clustering technique, wherein the set of clusters comprises:
a first cluster;
a second cluster;
determining second attributes associated with a second rule based on the set of clusters;
determining a similarity of the first attributes of the first rule and the second attributes of the second rule;
delivering, in response to the similarity exceeding a first threshold, a first recommendation, wherein the delivering the first recommendation comprises:
instructing the display to display a second rule definition graphical user interface (GUI) displaying the second attributes associated with the second rule;
and
receiving an indication to approve or commit the second rule.

12 more elements

A non-transitory computer readable medium configured to store instructions that when executed cause a processor to perform operations comprising:

instructing a display to display a first rule definition graphical user interface (GUI) displaying first attributes associated with a first rule;
receiving a first multi-source dataset, wherein the first multi-source dataset comprises:
the first set of attributes associated with the first rule;
a first set of requests comprising a first set of characteristics;
training a machine learning tool using the first multi-source dataset;
wherein the first set of attributes associated with the rule is used as input features for the machine learning model;
dividing the first multi-source dataset into a set of clusters using a first unsupervised clustering technique, wherein the set of clusters comprises:
a first cluster;
a second cluster;
determining second attributes associated with a second rule based on the set of clusters;
determining a similarity of the first attributes of the first rule and the second attributes of the second rule;
delivering, in response to the similarity exceeding a first threshold, a first recommendation, wherein the delivering the first recommendation comprises:
instructing the display to display a second rule definition graphical user interface (GUI) displaying the second attributes associated with the second rule;
and
receiving an indication to approve or commit the second rule.

12 more elements

Dependencies are inferred from the claim text.