Early pattern detection in data for improved enterprise operations

Patent metadata

Field	Value
Publication number	US-11823019-B2
Application number	US-202117370434-A
Country	US
Kind code	B2
Filing date	Jul 8, 2021
Priority date	Mar 22, 2021
Publication date	Nov 21, 2023
Grant date	Nov 21, 2023

Abstract

Implementations of the present disclosure include receiving a goal, providing a problem-specific knowledge graph that is responsive to at least a portion of the goal, determining a set of events from the problem-specific knowledge graph, processing data representative of events in the set of events through a first machine learning (ML) model to provide a set of event scores, each event score in the set of event scores being associated with a respective event in the set of events, determining a sub-set of events based on the set of event scores, for each event in the sub-set of events, determining at least one action by processing a sequence of actions through a second ML model, and outputting the sub-set of events and a set of actions for execution of at least one action in the set of actions.

First claim

What is claimed is:

1. A computer-implemented method for generating events and actions based on pattern recognition in data of connected networks, the method comprising:
receiving a goal;
providing a problem-specific knowledge graph that is responsive to at least a portion of the goal;
determining a set of events from the problem-specific knowledge graph, wherein determining the set of events comprises:
mapping at least a portion of entities identified from the goal to corresponding nodes in the problem-specific knowledge graph, and
identifying a path within the problem-specific knowledge graph that includes the corresponding nodes, wherein the identified path is a minimal path with shortest distances connecting the corresponding nodes;

processing data representative of events in the set of events through a first machine learning (ML) model to provide a set of event scores, wherein:
each event score in the set of event scores being associated with a respective event in the set of events, and
the first ML model i) processes at least a portion of a sparse feature set of a respective event through an embedding layer to botain a first set of values, ii) processes a dense feature set of the respective event through a hidden layer to obtain a second set of value, and iii) processes the first set of values and the second set of values to provide an event score for the respective event;

determing a sub-set of events based on the set of event scores;
for each event in the sub-set of events, determining at least one action by processing a sequence of actions through a second ML model; and
outputting the sub-set of events and a set of actions for execution of at least one action in the set of actions.

2. The computer-implemented method of claim 1 , wherein events are determined as respective instances of at least one node in the problem-specific knowledge graph.

3. The computer-implemented method of claim 1 , wherein the second ML model receives a sequence of actions associated with a respective event and predicts a next action in the sequence of actions for the respective event.

4. The computer-implemented method of claim 1 , wherein the second ML model comprises a set of transformers that process the sequence of actions.

5. The computer-implemented method of claim 1 , further comprising, for each event in the set of events, extracting data representative of the event through web sensing.

6. A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for generating events and actions based on pattern recognition in data of connected networks, the operations comprising:
receiving a goal;
providing a problem-specific knowledge graph that is responsive to at least a portion of the goal;
determining a set of events from the problem-specific knowledge graph, wherein determining the set of events comprises:
mapping at least a portion of entities identified from the goal to corresponding nodes in the problem-specific knowledge graph, and
identifying a path within the problem-specific knowledge graph that includes the corresponding nodes, wherein the identified path is a minimal path with shortest distances connecting the corresponding nodes;

processing data representative of events in the set of events through a first machine learning (ML) model to provide a set of event scores, wherein:
each event score in the set of event scores being associated with a respective event in the set of events; and
the first ML and i) processes at least a portion of a sparse feature set of a respective event through an embedding layer to obtain a first set of values, ii) processes a dense feature set of the respective event through a hidden layer to obtain a second set of value, and iii) processes the first set of values and the second set of values to provide an event score for the respective event;

determining a sub-set of events based on the set of event scores;
for each event in the sub-set of events, determining at least one action by processing a sequence of actions through a second ML model; and
outputting the sub-set of events and a set of actions for execution of at least one action in the set of actions.

7. The non-transitory computer-readable storage medium of claim 6 , wherein events are determined as respective instances of at least one node in the problem-specific knowledge graph.

8. The non-transitory computer-readable storage medium of claim 6 , wherein the second ML model receives a sequence of actions associated with a respective event and predicts a next action in the sequence of actions for the respective event.

9. The non-transitory computer-readable storage medium of claim 6 , wherein the second ML model comprises a set of transformers that process the sequence of actions.

10. The non-transitory computer-readable storage medium of claim 6 , wherein operations further comprise, for each event in the set of events, extracting data representative of the event through web sensing.

11. A system, comprising:
a computing device; and
a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for generating events and actions based on pattern recognition in data of connected networks, the operations comprising:
receiving a goal;
providing a problem-specific knowledge graph that is responsive to at least a portion of the goal;

determining a set of events from the problem-specific knowledge graph, wherein determining the set of events comprises:
mapping at least a portion of entities identified from the goal to corresponding nodes in the problem-specific knowledge graph, and
identifying a path within the problem-specific knowledge graph that includes the corresponding nodes, wherein the identified path is a minimal path with shortest distances connecting the corresponding nodes;
processing data representative of events in the set of events through a first machine learning (ML) model to provide a set of event scores, wherein:
each event score in the set of event scores being associated with a respective event in the set of events; and
the first ML model i) processes at least a portion of a sparse feature set of a respective event through an embedding layer to obtain a first set of values, ii) processing a dense feature set of the respective event through a hidden layer to obtain a second set of value, and iii) processes the first set of values and the second set of values to provide an event score for the respective event;
determining a sub-set of events based on the set of event scores;
for each event in the sub-set of events, determining at least one action by processing a sequence of actions through a second ML model; and
outputting the sub-set of events and a set of actions for execution of at least one action in the set of actions.

12. The system of claim 11 , wherein events are determined as respective instances of at least one node in the problem-specific knowledge graph.

13. The system of claim 11 , wherein the second ML model receives a sequence of actions associated with a respective event and predicts a next action in the sequence of actions for the respective event.

14. The system of claim 11 , wherein the second ML model comprises a set of transformers that process the sequence of actions.

Assignees

• Accenture Global Solutions Ltd

Inventors

• Guan Lan
• Xiong Guanglei
• Zhang Wenxian
• Kang Sukryool
• Paruchuri Anwitha
• Brewer Jing Su
• Wong Ivan A
• Chan Christopher Yen-Chu
• Moffat Danielle
• Subrahmonia Jayashree
• Barrere Louise Noreen

Classifications

• G06N20/00 Primary

  Machine learning · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G06Q10/0633 Primary

  Workflow analysis · CPC title

• G06Q30/0201 Primary

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q30/0601

  Electronic shopping [e-shopping] · CPC title