Method for converting speech to text, performing natural language processing on the text output, extracting data values and matching to an electronic ticket form

• US 8,898,063 B1
• Filed: 03/17/2014
• Issued: 11/25/2014
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Mark Sykes
• Original Assignee: Mark Sykes
• Inventors: Sykes, Mark, Baldock, George Ronald
• Primary Examiner(s): He, Jialong
• Application Number:
  US14/215,532
• Time in Patent Office: 253 Days
• Field of Search: 704/270, 704/275
• US Class Current: 704/270
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

A system and method for extracting data values from a conversation to complete an electronic trade ticket over a communications network. The system comprises a plurality of client devices and a processor based server. A digital switchboard routes an incoming call from a first user to a second user to the server over the communications network. The telephone numbers of the users are verified against the stored telephone numbers in a database. A sample representing a predetermined period of the recorded conversation are utilized to identify the users. The conversation between the users are transcribed onto an electronic text file and processed to extract terms to populate data fields of an electronic trade ticket.

Claims

1. A computer based method for extracting data values from a conversation to complete an electronic trade ticket over a communications network, comprising the steps of:

routing an incoming call from a first user to a second user by a digital switchboard to a processor based server over the communications network;

verifying telephone numbers of the first and second users against the stored telephone numbers in a database by a server processor;

recording a conversation between the first and second users by a recorder of the server and storing the conversation in the database;

obtaining a sample representing a predetermined period of the conversation by a speaker engine of the server to identify and verify the first and second users;

transcribing the conversation to an electronic text file by a speech recognition engine of the server and storing the electronic text file in the database;

performing natural language processing on the electronic text file by a natural language processing engine of the server to correct typographical, syntax and form errors, and to obtain trade information through relational co-reference and entity tracking; and

generating an electronic trade ticket by extracting terms from the electronic text file to populate data fields of the electronic trade ticket by a ticket generator of the server.

2. The method of claim 1, further comprising the step of converting the electronic ticket to financial information exchange (FIX) format by a FIX engine of the server.

3. The method of claim 1, wherein the step of performing natural language processing further comprises the step of splitting the electronic text file by tokens representing letters, numbers, punctuations and symbols.

4. The method of claim 1, further comprising the step of accessing the server over the communications network by a client device associated with each user.

5. The method of claim 4, further comprising the step recording the conversation at a request of each client device such that two recordings of the conversation and two transcribed electronic text files of the conversation are stored in the database.

6. The method of claim 5, further comprising the step of comparing the two transcribed electronic text files of the conversation by an annotation differential tool of the server to determine inconsistencies between the two transcribed text files.

7. The method of claim 1, further comprising the step of determining whether all the terms for the electronic trade ticket are extracted from the electronic text file by the ticket generator;

and transmitting an alert message to a client device associated with at least one of the first and second users of any missing terms by the server processor.

8. A system for extracting data values from a conversation to complete an electronic trade ticket over a communications network, comprising:

a plurality of client devices, each associated with a user and connected to the communications network;

a processor based server comprising;

a digital switchboard for routing an incoming call from a first user to a second user to the server over the communications network;

a server processor for verifying telephone numbers of the first and second users against the stored telephone numbers in a database;

a recorder for recording a conversation between the first and second users in a database;

a speaker engine for obtaining a sample representing a predetermined period of the conversation to identify and verify the first and second users;

a speech recognition engine for transcribing the conversation to an electronic text file and storing the electronic text file in the database;

a natural language processing engine for performing natural language processing on the electronic text file to correct typographical, syntax and form errors, and to obtain trade information through relational co-reference and entity tracking; and

a ticket generator for generating an electronic trade ticket by extracting terms from the electronic text file to populate data fields of the electronic trade ticket.

9. The system of claim 8, further comprising a FIX engine for converting the electronic ticket to financial information exchange (FIX) format.

10. The system of claim 8, wherein the natural language processing engine splits the electronic text file by tokens representing letters, numbers, punctuations and symbols.

11. The system of claim 8, wherein a client device associated with each of the first and second users accesses the server over the communications network.

12. The system of claim 11, wherein at least two recorders record the conversation at a request of each client device such that two recordings of the conversation and two transcribed electronic text files of the conversation are stored in the database.

13. The system of claim 12, wherein the server further comprises an annotation differential tool for comparing the two transcribed electronic text files of the conversation to determine inconsistencies between the two transcribed text files.

14. The system of claim 8, wherein the ticket generator determines whether all the terms for the electronic trade ticket are extracted from the electronic text file;

and wherein the server processor transmits an alert message to a client device associated with at least one of the first and second users of any missing terms.

15. A non-transitory computer readable medium comprising computer executable code for extracting data values from a conversation to complete an electronic trade ticket over a communications network, said computer executable comprising instructions for:

routing an incoming call from a first user to a second user by a digital switchboard to a processor based server over the communications network;

verifying telephone numbers of the first and second users against the stored telephone numbers in a database by a server processor;

recording a conversation between the first and second users by a recorder of the server and storing the conversation in the database;

obtaining a sample representing a predetermined period of the conversation by a speaker engine of the server to identify and verify the first and second users;

transcribing the conversation to an electronic text file by a speech recognition engine of the server and storing the electronic text file in the database;

performing natural language processing on the electronic text file by a natural language processing engine of the server to correct typographical, syntax and form errors, and to obtain trade information through relational co-reference and entity tracking; and

generating an electronic trade ticket by extracting terms from the electronic text file to populate data fields of the electronic trade ticket by a ticket generator of the server.

16. The computer readable medium of claim 15, wherein said computer executable code further comprises instructions for converting the electronic ticket to financial information exchange (FIX) format by a FIX engine of the server.

17. The computer readable medium of claim 15, wherein said computer executable code further comprises instructions for splitting the electronic text file by tokens representing letters, numbers, punctuations and symbols.

18. The computer readable medium of claim 15, wherein said computer executable code further comprises instructions for recording the conversation at a request of each client device such that two recordings of the conversation and two transcribed electronic text files of the conversation are stored in the database.

19. The computer readable medium of claim 18, wherein said computer executable code further comprises instructions for comparing the two transcribed electronic text files of the conversation by an annotation differential tool of the server to determine inconsistencies between the two transcribed text files.

20. The computer readable medium of claim 15, wherein said computer executable code further comprises instructions for:

determining whether all the terms for the electronic trade ticket are extracted from the electronic text file by the ticket generator; and

transmitting an alert message to a client device associated with at least one of the first and second users of any missing terms by the server processor.