Data security and protection system using distributed ledgers to store validated data in a knowledge graph

Patent metadata

Field	Value
Publication number	US-10938817-B2
Application number	US-201815946528-A
Country	US
Kind code	B2
Filing date	Apr 5, 2018
Priority date	Apr 5, 2018
Publication date	Mar 2, 2021
Grant date	Mar 2, 2021

Abstract

A system for providing data security and protection using distributed ledgers to store validated data in a global knowledge graph for fraud detection is disclosed. The system may comprise a data access interface, a processor, and an output interface. The data access interface may receive data associated with an individual from a data source. The processor may convert the data into knowledge graph data by: extracting entities and relations from the data; and translating the data into knowledge graph triples to generate the knowledge graph data. The processor may validate the knowledge graph data using a cryptographic validation, to provide secured contents to update a global knowledge graph to determine a fraudulent activity level associated with the individual based on the updated global knowledge graph. The output interface may transmit a report associated with the fraudulent activity level to a report requestor at a computing device.

First claim

The invention claimed is:

1. A system for providing data security and protection, comprising:
one or more data stores to store and manage data within a network;
one or more servers to facilitate operations using information from the one or more data stores;
an analytics system that communicates with the one or more servers and the one or more data stores to provide data and security in the network, the analytics system comprising:
a data access interface to:
receive data associated with an individual from a data source, wherein the individual is associated with at least one of a plurality of entities; and

a processor to:
convert the data into a knowledge graph data by using a core schema that allows for user extensions of an ontology wherein the core schema provides an arrangement of the ontology that defines initial data types and relationships included in the knowledge graph, wherein the conversion of the data into the knowledge graph includes:
 performing an entity extraction on the data to identify one or more entities,
 performing a relation extraction on the data to identify one or more relations between the one or more entities, and
 translating the data into knowledge graph triples based on the one or more entities and the one or more relations to generate the knowledge graph data, wherein the knowledge graph data comprises an update to a knowledge graph;

validate the knowledge graph data by:
 using a cryptographic validation on the knowledge graph data to provide data security and protection for contents of the knowledge graph, wherein the cryptographic validation includes providing permissioned access to the knowledge graph at different levels that include read and write access level and only read access level;
update the knowledge graph based on the validated knowledge graph data, wherein the knowledge graph provides analytics-based information associated with at least the individual and the update to the knowledge graph is made by a user at the read and write access level and the update to the knowledge graph includes one of the extensions of the ontology allowed by the core schema associated with the knowledge graph, wherein the extension to the ontology includes sub-typing a new entity underneath an entity of one of the initial data types; and
determine a fraudulent activity level associated with the individual based on the updated knowledge graph; and

an output interface configured to transmit a report associated with the fraudulent activity level to a report requestor at a computing device, wherein the report is transmitted in a predetermined format.

2. The system of claim 1 , wherein the data is unstructured data comprising at least one of private information and public information, wherein the private information comprises at least one of financial information, account information, and personal information.

3. The system of claim 1 , wherein the data comprises at least one of a text format, an image format, an audio format, and a multimedia format, wherein the data is converted to a text format if it is received in a non-text format.

4. The system of claim 1 , wherein the data source comprises at least one of an enterprise resource planning (ERP) system, a document, a web feed, a sensor, a geolocation data source, an enterprise database, a public database, a server, an analytics tool, a mobile device, a reporting system, and a user input.

5. The system of claim 1 , wherein converting the data into knowledge graph data comprises natural language processing (NLP).

6. The system of claim 1 , wherein one or more of the entity extraction and the relation extraction is performed using a recurrent neural network.

7. The system of claim 1 , wherein the knowledge graph is a global knowledge graph having a plurality of decentralized contributors.

8. The system of claim 1 , wherein the update to the knowledge graph comprises at least one of an addition, a subtraction, and a modification to the one or more entities or one or more relations.

9. The system of claim 1 , wherein the cryptographic validation comprises storing a digital signature on a distributed ledger to provide immutability of the knowledge graph data to update the knowledge graph.

10. The system of claim 9 , wherein the cryptographic validation further comprises at least one of NLP functionality, file-access controls, and document-linking outside of the distribute ledger.

11. A system for providing data security and protection in fraud detection, comprising:
a data access interface to:
receive data associated with an individual from a data source, wherein the individual is associated with at least one of a plurality of entities;

a processor to:
convert the data into knowledge graph data using natural language processing (NLP) by using a core schema that allows for user extensions of an ontology and the core schema provides an arrangement of the ontology that defines initial data types and relationships included in the knowledge graph, wherein the conversion of the data into the knowledge graph includes:
extracting entities from the data associated with the individual,
extracting relations from the data associated with the individual, and
translating the data into knowledge graph triples based on the entities and the relations to generate the knowledge graph data, wherein the knowledge graph data comprises an update to a global knowledge graph, wherein the update to the global knowledge graph comprises at least one of an addition, a subtraction, or a modification to the entities or relations;

validate the knowledge graph data by:
using a cryptographic validation on the knowledge graph data to provide data security and protection for contents of the global knowledge graph, wherein the cryptographic validation includes providing permissioned access to the knowledge graph at different levels that include read and write access level and only read access level and the cryptographic validation comprises:
storing a digital signature on a distributed ledger to provide immutability of the knowledge graph data;

update the global knowledge graph based on the validated knowledge graph data, wherein the global knowledge graph provides analytics-based information associated with at least the individual and the update to the knowledge graph is made by a user at the read and write access level and the update to the knowledge graph includes one of the extensions of the ontology allowed by the core schema associated with the knowledge graph, wherein the extension to the ontology includes sub-typing a new entity underneath an entity of an one of the initial data types; and
determine a fraudulent activity level associated with the individual based on the updated global knowledge graph; and

an output interface to transmit to a report associated with the fraudulent activity level to a report requestor at a computing device, wherein the report is transmitted in a predetermined format.

12. The system of claim 11 , wherein the data is unstructured data comprising at least one of private information and public information, wherein the private information comprises at least one of financial information, account information, and personal information.

13. The system of claim 11 , wherein the data comprises at least one of a text format, an image format, an audio format, and a multimedia format, wherein the data is converted to a text format if it is received in a non-text format.

14. The system of claim 11 , wherein the data source comprises at least one of an enterprise resource planning (ERP) system, a document, a web feed, a sensor, a geolocation data sourc

Assignees

• Accenture Global Solutions Ltd

Inventors

• Han Jingguang
• Guéret Christophe Dominique Marie
• Mccarthy Nicholas Patrick
• Wan Dadong

Classifications

• G06F16/9024

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F21/64 Primary

  Protecting data integrity, e.g. using checksums, certificates or signatures · CPC title

• H04L63/0428

  wherein the data content is protected, e.g. by encrypting or encapsulating the payload · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N3/02

  Neural networks · CPC title