METHODS FOR AUTOMATICALLY GENERATING STRUCTURED PRICING MODELS FROM UNSTRUCTURED MULTI-CHANNEL COMMUNICATIONS AND DEVICES THEREOF

• US 20190057450A1
• Filed: 07/10/2018
• Published: 02/21/2019
• Est. Priority Date: 07/24/2017
• Status: Active Grant

• Current Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Original Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Inventors: Mark, Jimmy C., Upadhyay, Sudhir, Voell, David
• Granted Patent: US 10,885,586 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/117 Tagging; Marking up details of markup languages G06F40/143; Designating a block; Setting of attributes style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

Methods, non-transitory computer readable media, and natural language understanding (NLU) service device are disclosed that receive raw requests for price quotes for financial instruments from two or more different types of communication channels and via one or more communication networks. The raw requests are in two or more different formats and comprise unstructured data. The unstructured data of the raw requests is analyzed to identify key value(s) associated with the raw requests. The raw requests are then automatically transformed based on the identified key value(s) into price quote request(s) comprising structured data in particular format(s) required by pricing application(s) hosted by pricing server device(s). The price quote request(s) are output to one or more of the pricing application(s) via another one or more communication networks in order to facilitate automated pricing of the financial instruments.

Claims

1. A method for automatically generating structured pricing models from unstructured multi-channel communications implemented by one or more natural language understanding (NLU) service devices, the method comprising:

receiving a plurality of raw pricing requests for price quotes for financial instruments from two or more different types of communication channels and via one or more communication networks, wherein the raw pricing requests are in two or more different formats and comprise unstructured data;

analyzing the unstructured data of the raw pricing requests to identify one or more key values associated with the raw pricing requests;

automatically transforming the raw pricing requests based on the identified key values into price quote requests comprising structured data in one or more particular formats required by one or more pricing applications hosted by one or more pricing server devices; and

outputting the price quote requests to one or more of the pricing applications via another one or more communication networks in order to facilitate automated pricing of the financial instruments.

2. The method as set forth in claim 1, further comprising receiving the raw pricing requests from one or more client devices, obtaining one or more quote responses to the price quote requests from the one or more of the pricing applications, and returning the quote responses to the client devices in response to the raw pricing requests.

3. The method as set forth in claim 1, wherein the one or more key values are analyzed based on the application of a model to the unstructured data and the method further comprises training the model.

4. The method as set forth in claim 3, further comprising updating the model based on received feedback data regarding a result of the transformation.

5. The method as set forth in claim 1, wherein the unstructured data of each of the raw pricing requests is analyzed based one or more of a set of words included therein, a sequence of the words, a proximity in time to one or more of the of the raw pricing requests, or a pattern matching technique in order to identify the key values.

6. A natural language understanding (NLU) service device, comprising memory comprising programmed instructions stored thereon and one or more processors configured to be capable of executing the stored programmed instructions to:

receive a plurality of raw pricing requests for price quotes for financial instruments from two or more different types of communication channels and via one or more communication networks, wherein the raw pricing requests are in two or more different formats and comprise unstructured data;

analyze the unstructured data of the raw pricing requests to identify one or more key values associated with the raw pricing requests;

automatically transform the raw pricing requests based on the identified key values into price quote requests comprising structured data in one or more particular formats required by one or more pricing applications hosted by one or more pricing server devices; and

output the price quote requests to one or more of the pricing applications via another one or more communication networks in order to facilitate automated pricing of the financial instruments.

7. The NLU service device as set forth in claim 6, wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to receive the raw pricing requests from one or more client devices, obtain one or more quote responses to the price quote requests from the one or more of the pricing applications, and return the quote responses to the client devices in response to the raw pricing requests.

8. The NLU service device as set forth in claim 6, wherein the one or more key values are analyzed based on the application of a model to the unstructured data and the one or more processors are further configured to be capable of executing the stored programmed instructions to train the model.

9. The NLU service device as set forth in claim 8, wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to update the model based on received feedback data regarding a result of the transformation.

10. The NLU service device as set forth in claim 6, wherein the unstructured data of each of the raw pricing requests is analyzed based one or more of a set of words included therein, a sequence of the words, a proximity in time to one or more of the of the raw pricing requests, or a pattern matching technique in order to identify the key values.

11. A non-transitory machine readable medium having stored thereon instructions for automatically generating structured pricing models from unstructured multi-channel communications comprising executable code which when executed by one or more processors, causes the one or more processors to:

receive a plurality of raw pricing requests for price quotes for financial instruments from two or more different types of communication channels and via one or more communication networks, wherein the raw pricing requests are in two or more different formats and comprise unstructured data;

analyze the unstructured data of the raw pricing requests to identify one or more key values associated with the raw pricing requests;

automatically transform the raw pricing requests based on the identified key values into price quote requests comprising structured data in one or more particular formats required by one or more pricing applications hosted by one or more pricing server devices; and

output the price quote requests to one or more of the pricing applications via another one or more communication networks in order to facilitate automated pricing of the financial instruments.

12. The non-transitory machine readable medium as set forth in claim 11, wherein the executable code when executed by the processors further causes the one or more processors to receive the raw pricing requests from one or more client devices, obtain one or more quote responses to the price quote requests from the one or more of the pricing applications, and return the quote responses to the client devices in response to the raw pricing requests.

13. The non-transitory machine readable medium as set forth in claim 11, wherein the one or more key values are analyzed based on the application of a model to the unstructured data and the executable code when executed by the processors further causes the one or more processors to train the model.

14. The non-transitory machine readable medium as set forth in claim 13, wherein the executable code when executed by the processors further causes the one or more processors to update the model based on received feedback data regarding a result of the transformation.

15. The non-transitory machine readable medium as set forth in claim 11, wherein the unstructured data of each of the raw pricing requests is analyzed based one or more of a set of words included therein, a sequence of the words, a proximity in time to one or more of the of the raw pricing requests, or a pattern matching technique in order to identify the key values.