Enhanced management systems and apparatuses

Patent metadata

Field	Value
Publication number	US-11227269-B2
Application number	US-201816181807-A
Country	US
Kind code	B2
Filing date	Nov 6, 2018
Priority date	Nov 6, 2018
Publication date	Jan 18, 2022
Grant date	Jan 18, 2022

Abstract

An artificial intelligence system for managing a consumer relationship is provided. The artificial intelligence system includes: one or more client entities; a storage device configured to store data related to actions and characteristics of the one or more client entities, the actions and characteristics relating to payment of accounts receivable; one or more machine learning server devices configured to generate and update a machine learning model based on previous actions and characteristics of said one or more client entities; and predict future actions of the one or more client entities with respect to the payment of accounts receivable, based on the machine learning model.

First claim

We claim:

1. An artificial intelligence system, comprising:
one or more client entities;
a storage device configured to store data related to actions and characteristics of said one or more client entities, the actions and characteristics relating to payment of accounts receivable;
a first server level including at least two SQL servers, the at least two SQL servers transmitting files amongst each other via a file transfer protocol and processing first data; and
a second server level including at least one server, the at least one server, implemented at least partly in one or more of configurable logic or fixed-functionality logic hardware, configured to:
receive the first data;
automatically generate and update a machine learning model based on the actions and characteristics of said one or more client entities;
predict future actions of said one or more client entities with respect to the payment of accounts receivable, based on results of the machine learning model;
automatically cluster a subset of said one or more entities based on characteristics common to each of said one or more entities in the subset, the characteristics being based on the machine learning model; and
automatically generate an interactive graphic user interface related to the subset, the interactive graphic user interface including a selectable view of data of each of said one or more entities in the subset.

2. The artificial intelligence system of claim 1 , wherein an updated machine learning model replaces a previous machine learning model.

3. The artificial intelligence system of claim 1 , wherein predictive modeling using segmentation is applied to cluster the subset of said one or more entities.

4. The artificial intelligence system of claim 1 , wherein the machine learning model uses predictive modeling techniques to calculate a probability of an occurrence of a business-related event.

5. The artificial intelligence system of claim 1 , wherein the machine learning model uses neural networks to calculate a probability of non-payment of invoices.

6. An apparatus comprising:
a first interface configured to receive input on identities of one or more entities;
a second interface configured to receive data related to actions and characteristics of said one or more entities, the actions and characteristics being related to payment of accounts receivables; and
a first server level and a second server level, each communicatively coupled to a storage device, the first interface and the second interface, wherein the storage device is configured to store the data related to actions and characteristics of said one or more entities,
wherein the first server level includes at least two SQL servers, the at least two SQL servers transmitting files amongst each other via a file transfer protocol and processing first data,
wherein the second server level includes at least one server, the at least one server, implemented at least partly in one or more of configurable logic or fixed-functionality logic hardware,
wherein the at least one server is configured to:
receive the first data;
group said one or more entities based on the actions and characteristics of said one or more entities;
automatically generate a machine learning model based on the data related to previous actions and characteristics of said one or more entities;
apply one or more algorithms of the machine learning model to predict probability of payment or non-payment on the accounts receivable;
automatically cluster a subset of said one or more entities based on characteristics common to each of the said one or more entities in the subset, the characteristics being based on the machine learning model; and
automatically instruct the second interface to generate an interactive graphic user interface related to the subset, the interactive graphic user interface including a selectable view of data of each of said one or more entities in the subset.

7. The apparatus of claim 6 , wherein the at least one server is configured to replace the machine learning model with an updated machine learning model.

8. The apparatus of claim 6 , wherein predictive modeling using segmentation is applied to cluster the subset of said one or more entities.

9. The apparatus of claim 6 , wherein the machine learning model employs predictive modeling techniques to calculate a probability of an occurrence of a business-related event.

10. The apparatus of claim 6 , wherein the machine learning model employs neural networks to calculate a probability of non-payment of invoices.

11. A method of an artificial intelligence system, the method comprising:
identifying one or more entities;
receiving first data related to actions and characteristics of said one or more entities, the actions and characteristics being related to payment of accounts receivable, the first data being received via at least one server of a second server level, the at least one server being implemented at least partly in one or more of configurable logic or fixed-functionality logic hardware, and the first data being received from a first server level including at least two SQL servers, the at least two SQL servers transmitting files amongst each other via a file transfer protocol and processing the first data;
grouping, via the at least one server, said one or more entities based on the actions and characteristics of said one or more entities;
automatically generating, via the at least one server, a machine learning model based on the data related to previous actions and characteristics of said one or more entities;
applying one or more algorithms of the machine learning model to predict probability of a business-related event related to the accounts receivable; and
automatically clustering, via the at least one server, a subset of said one or more entities based on characteristics common to each of the said one or more entities in the subset, the characteristics being based on the machine learning model; and
automatically generating, via the at least one server, an interactive graphic user interface related to the subset, the interactive graphic user interface including a selectable view of each of data of said one or more entities in the subset.

12. The method of claim 11 , further comprising updating the generated machine learning model with an updated machine learning model.

13. The method of claim 11 , wherein the machine learning model employs predictive modeling techniques to calculate a probability of an occurrence of a business-related event.

14. The method of claim 11 , further comprising applying predictive modeling using segmentation to cluster the subset of said one or more entities.

15. The method of claim 11 , wherein the machine learning model employs neural networks to calculate a probability of non-payment of invoices.

16. A non-transitory computer readable medium comprising a set of instructions, which, when executed by at least one server of a second server level and implemented at least partly in one or more of configurable logic or fixed-functionality logic hardware, and when first data is received from a first server level including at least two SQL servers, the at least two SQL servers transmitting files amongst each other via a file transfer protocol and processing the first data, cause the at least one server to:
identify one or more entities;
receive the first data related to actions and characteristics of said one or more entities, the actions and characteristics being related to payment of accounts receivable;
group said one or more entities based on the actions and cha

Assignees

• Accenture Global Solutions Ltd

Inventors

• Collares Leonardo
• Souza Andre

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N20/20 Primary

  Ensemble learning · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title