Predicting an effect of performing an action on a node of a geographical network

Patent metadata

Field	Value
Publication number	US-10142187-B2
Application number	US-201615141138-A
Country	US
Kind code	B2
Filing date	Apr 28, 2016
Priority date	Apr 29, 2015
Publication date	Nov 27, 2018
Grant date	Nov 27, 2018

Abstract

A device may include one or more processors. The device may receive first information identifying a plurality of nodes and transactions associated with the plurality of nodes. The transactions may be between nodes, of the plurality of nodes, and entities of a plurality of entities. The device may determine geographical locations corresponding to the plurality of nodes. The device may determine second information, based on the first information, that may identify nodes, of the plurality of nodes, that are associated with shared entities. The device may generate, based on the geographical locations and the second information, a geographical network. The device may select a selected node, of the geographical network, on which to perform an action. The device may determine third information based on predicting future performance of the geographical network assuming that the action is performed. The device may store or provide the third information.

First claim

What is claimed is:

1. A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, executing instructions to:
receive transaction information identifying a plurality of nodes and transactions associated with the plurality of nodes,
the transactions being between nodes, of the plurality of nodes, and entities of a plurality of entities;

determine geographical locations corresponding to the plurality of nodes;
determine node information based on the transaction information,
the node information identifying nodes, of the plurality of nodes, that are associated with shared entities,
a shared entity being an entity that has performed transactions with at least two nodes of the plurality of nodes;

generate, based on the geographical locations and the node information, a geographical network that includes the at least two nodes;
select an anchor node of the plurality of nodes;
associate the anchor node with the geographical network;
identify proximate nodes, of the plurality of nodes, that are within a particular distance of the anchor node; and
selectively add one or more proximate nodes to the geographical network based on the node information,
a particular proximate node, of the one or more proximate nodes, to be added to the geographical network when the particular proximate node is associated with a shared entity value that satisfies a threshold,
the threshold being based on a quantity of shared entities that have performed one or more transactions with any node of the geographical network, and

the particular proximate node not to be added to the geographical network when the particular proximate node is not associated with a shared entity value that satisfies the threshold,

train one or more predictive models based on:
the transaction information,
the node information, and
the geographical network,
the one or more predictive models for predicting future performance of the at least two nodes;

select a node, of the at least two nodes, on which to perform an action;
determine first performance information for the plurality of nodes based on predicting the future performance of the at least two nodes assuming that the action is performed,
the first performance information being determined based on information outputted by the one or more predictive models; and

store or provide the first performance information.

2. The device of claim 1 , where the one or more processors, when selecting the node, are to:
select the node based on the node information,
the selected node being selected based on the selected node being associated with a shared entity value that satisfies a threshold,
the threshold being based on a quantity of shared entities that have performed one or more transactions with any node of the geographical network.

3. The device of claim 1 , where:
the one or more predictive models are to receive, as input, the transaction information relating to a particular node of the plurality of nodes, and
the one or more predictive models are to output information identifying a quantity of entities that have performed transactions with the particular node and that are predicted to perform a transaction with another node of the geographical network if the particular node is deactivated.

4. The device of claim 3 , where the one or more processors, when selecting the node, are to:
select the node based on the information outputted by the one or more predictive models.

5. The device of claim 1 , where the one or more processors, when selecting the node, are to:
select the node based on past performance of the selected node.

6. The device of claim 1 , where the one or more processors are to:
determine second performance information based on predicting future performance of the at least two nodes assuming that the action is not performed;
determine that the action is to be performed based on comparing the first performance information and the second performance information; and
cause the action to be performed.

7. A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
receive input information identifying a plurality of nodes,
the input information identifying a plurality of transactions between nodes, of the plurality of nodes, and entities of a plurality of entities,
the input information identifying locations corresponding to the plurality of nodes;

determine overlap information based on the input information,
the overlap information identifying nodes, of the plurality of nodes, that are associated with shared entities,
a shared entity being an entity that has performed transactions with at least two nodes of the plurality of nodes;

generate a geographical network including a set of nodes, of the plurality of nodes, based on each node of the set of nodes being associated with a shared entity value that satisfies a threshold,
the threshold being based on a quantity of shared entities that have performed one or more transactions with any node of the geographical network;

generate, based on the input information and the overlap information, a predictive model to predict an effect of deactivating a particular node of the plurality of nodes,
the particular node, when deactivated, being unavailable to perform transactions;

select a node, of the plurality of nodes, to potentially deactivate,
the selected node being selected based on the selected node being associated with one or more of:
a greater quantity of shared entities than other nodes of the at least two nodes; or
a greater ratio of shared entities to all entities associated with the selected node, as compared to ratios of shared entities to all entities corresponding to the other nodes of the at least two nodes;

determine a predicted effect of deactivating the selected node based on the predictive model and based on a particular quantity of shared entities associated with the selected node; and
store or provide information describing the predicted effect.

8. The non-transitory computer-readable medium of claim 7 , where the geographical network is a first geographical network associated with a first plurality of shared entities; and
where the set of nodes is a first set of nodes; and
where the one or more instructions, that cause the one or more processors to generate the first geographical network, cause the one or more processors to:
generate a second geographical network including a second set of nodes of the plurality of nodes,
the second set of nodes being associated with a second plurality of shared entities that is different than the first plurality of shared entities.

9. The non-transitory computer-readable medium of claim 7 , where the selected node is associated with a first quantity of new entities,
the first quantity of new entities having performed a transaction with the selected node without having previously performed a transaction with any node of the plurality of nodes; and
where the predictive model outputs information identifying a second quantity of new entities that are predicted to perform a transaction with one or more other nodes of the plurality of nodes,
the second quantity of new entities not having previously performed a transaction with any node of the plurality of nodes.

10. The non-transitory computer-readable medium of claim 9 , where the overlap information identifies respective sets of shared entities that are associated with the selected node and each other node of the plurality of nodes; and
where the one or more instruc

Assignees

• Accenture Global Solutions Ltd
• Accenture Global Soltuions Ltd

Inventors

• Nahata Charu
• Merl Milton Jay
• Naik Amit C
• Pawar Yogesh P
• Tamboli Harsiddhi
• Bottom Joseph S

Classifications

• H04L41/147 Primary

  for predicting network behaviour · CPC title

• H04L43/16

  Threshold monitoring · CPC title