SYSTEM AND METHOD FOR ANALYSIS AND DETERMINATION OF RELATIONSHIPS FROM A VARIETY OF DATA SOURCES

• US 20200133964A1
• Filed: 12/30/2019
• Published: 04/30/2020
• Est. Priority Date: 10/13/2017
• Status: Active Grant

• Current Assignee: KPMG LLP (KPMG International Cooperative)
• Original Assignee: KPMG LLP (KPMG International Cooperative)
• Inventors: LEE, John Hyung, GARDNER, James Johnson, EDWARDS, Justin, VORSANGER, Gregory Alexander, SCRIPKA, David Anthony, WAGNER-KAISER, Rachel A.
• Granted Patent: US 11,321,364 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/258 Data format conversion from or to a database
• CPC Class Codes: G06F 16/288 Entity relationship models
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/041 Abduction
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

The invention relates to computer-implemented systems and methods for analyzing data from a variety of data sources. Embodiments of the systems and the methods further provide for generating responses to specific questions based on the analyzed data, wherein the generating includes: retrieving related documents associated with the analyzed data; determining which information should be reported from which of the retrieved related documents; and providing a response based on the determination and a graph schema associated with the related documents.

Claims

1. A computer-implemented method for analyzing data from a variety of data sources, the method comprising:

receiving, as inputs, data from the variety of data sources;

converting the received data from each of the variety of data sources into a common data structure;

identifying keywords in the received data;

generating sentence or word embeddings based on the identified keywords;

receiving a selection of one or more labels based on the generated sentence or word embeddings;

adding the selected one or more labels to a model;

training the model over the common data structure based on a configuration file; and

generating a result in response to a user question based on the model, wherein the generating includes;

retrieving related documents from the received data;

determining which information should be reported from which of the retrieved related documents; and

providing the result based on the determination and a graph schema associated with the related documents.

2. The method of claim 1, wherein the variety of data sources includes at least one of a machine-readable document, non-machine readable document, spreadsheet, image, a Hypertext Markup Language file.

3. The method of claim 1, further comprising:

splitting the received data into component documents, wherein the received data is split based on one of a heuristic model and a trained model.

4. The method of claim 1, further comprising:

tokenizing at least one of word elements and sentence elements in the received data; and

adding default word embeddings to at least one of the tokenized word elements and sentence elements.

5. The method of claim 1, wherein the configuration file includes instructions regarding at least one of a task type, algorithm type, and features.

6. The method of claim 5, wherein (i) the task type is one of:

train, validate, and predict, (ii) the algorithm type is one of a regression algorithm and a recursive algorithm, and (iii) the features include word embeddings.

7. The method of claim 1, further comprising:

performing at least one quality assessment check.

8. The method of claim 1, further comprising:

receiving, via a user interface, at least one expression;

providing the at least one expression to the model;

selecting, with an application programming interface, annotation candidates associated with the at least one expression; and

training the model based on the selected annotation candidates.

9. The method of claim 1, wherein, during training, target truth labels and features are extracted from a training dataset, and then provided to the model

10. A computer-implemented system for analyzing data from a variety of data sources, the system comprising:

a processor, wherein the processor is configured to;

receive, as inputs, data from the variety of data sources;

convert the received data from each of the variety of data sources into a common data structure;

identify keywords in the received data;

generate word or sentence embeddings based on the identified keywords;

receive a selection of one or more labels based on the generated word or sentence embeddings;

add the selected one or more labels to a model;

train the model over the common data structure based on a configuration file; and

generate a result in response to a user question based on the model, wherein the generating includes;

retrieving related documents from the received data;

determining which information should be reported from which of the retrieved related documents; and

providing the result based on the determination and a graph schema associated with the related documents.

11. The system of claim 10, wherein the variety of data sources includes at least one of a machine-readable document, non-machine readable document, spreadsheet, image, a Hypertext Markup Language file.

12. The system of claim 10, wherein the processor is further configured to:

split the received data into component documents, wherein the received data is split based on one of a heuristic model and a trained model.

13. The system of claim 10, wherein the processor is further configured to:

tokenize at least one of word elements and sentence elements in the received data; and

add default word embeddings to at least one of the tokenized word elements and sentence elements.

14. The system of claim 10, wherein the configuration file includes instructions regarding at least one of a task type, algorithm type, and features.

15. The system of claim 14, wherein (i) the task type is one of:

train, validate, and predict, (ii) the algorithm type is one of a regression algorithm and a recursive algorithm, and (iii) the features include word embeddings.

16. The system of claim 10, wherein the processor is further configured to:

perform at least one quality assessment check.

17. The system of claim 10, wherein the processor is further configured to:

receive, via a user interface, at least one expression;

provide the at least one expression to the model;

select, with an application programming interface, annotation candidates associated with the at least one expression; and

train the model based on the selected annotation candidates.

18. The system of claim 10, wherein, during training, target truth labels and features are extracted from a training dataset, and then provided to the model.

19. A computer-implemented system for analyzing data from a variety of data sources, the system comprising:

an application programming interface; and

a processor, wherein the processor is configured to;

generate a result in response to a user question based on a machine learning model, wherein the generating includes;

retrieving related documents from the received data;

determining which information should be reported from which of the retrieved related documents; and

providing the result based on the determination and a graph schema associated with the related documents;

wherein the machine learning model is trained on annotation candidates provided by the application programming interface.