Automated extraction of performance segments and metadata values associated with the performance segments from contract documents

1. A data processing system for processing a contract document having at least one performance segment, the data processing system comprising:

an input unit configured to receive the contract document from a user device;

a memory unit configured to store a plurality of extraction machine learning models; and

a processor communicably coupled to the input unit and the memory unit, the processor being configured to:

extract the at least one performance segment from the contract document;

execute one or more machine learning models that output a type of performance segment associated with the extracted at least one performance segment based on input of the extracted at least one performance segment, wherein the one or more machine learning models are trained with a training set comprising a plurality of predefined standard performance segments and corresponding types of each of the plurality of predefined standard performance segments, and the one or more machine learning models identify the type of performance segment;

identify at least one metadata associated with the identified type of performance segment, the at least one metadata being selected from a predefined list of metadata associated with a plurality of types of performance segments;

based on the identified type of performance segment associated with the at least one performance segment and the identified at least one metadata associated with the identified type of performance segment, select at least one extraction machine learning model from the plurality of extraction machine learning models; and

extract at least one metadata value, associated with the identified at least one metadata, from the at least one performance segment with the at least one extraction machine learning model selected from the plurality of extraction machine learning models.

2. The data processing system as claimed in claim 1 , wherein the processor is further configured to validate the identified type of the at least one performance segment using a machine learning engine based on a list of key terms associated with the plurality of types of performance segments.

3. The data processing system as claimed in claim 1 , wherein the processor is further configured to:

parse the contract document into a plurality of performance segments prior to the extraction of the at least one performance segment from the contract document.

4. The data processing system as claimed in claim 1 , wherein the memory unit is configured to store a table including reference to a plurality of predefined metadata, a plurality of extraction machine learning models associated with each of the predefined metadata, an accuracy associated with each of the plurality of extraction machine learning models, and a corresponding type of performance segment.

5. The data processing system as claimed in claim 1 , wherein the processor is configured to transmit the extracted at least one performance segment and the at least one metadata value associated with the extracted at least one performance segment to the user device for display.

6. The data processing system as claimed in claim 4 , wherein the processor is further configured to select the at least one extraction machine learning model based on the table stored in the memory unit.

7. A method for processing a contract document having at least one performance segment, the method comprising:

extracting, by a processor, at least one performance segment from the contract document;

executing, by the processor, one or more machine learning models that output a type of performance segment associated with the extracted at least one performance segment based on an input of the extracted at least one performance segment, wherein the one or more machine learning models are trained with a training set comprising a plurality of predefined standard performance segments and corresponding types of each of the plurality of predefined standard performance segments, and the one or more machine learning models identify the type of performance segment;

identifying, by the processor, at least one metadata associated with the identified type of performance segment, the at least one metadata being selected from a predefined list of metadata associated with a plurality of types of performance segments;

based on the identified type of performance segment associated with the at least one performance segment and the identified at least one metadata associated with the identified type of performance segment, selecting at least one extraction machine learning model from a plurality of extraction machine learning models; and

extracting, by the processor, at least one metadata value, associated with the identified at least one metadata, from the at least one performance segment with the at least one extraction machine learning model selected from the plurality of extraction machine learning models.

8. The method as claimed in claim 7 , further comprising:

validating, by the processor, the identified type of the at least one performance segment using a rule-based engine based on a list of key terms associated with the plurality of types of performance segments.

9. The method as claimed in claim 7 , further comprising:

parsing, by the processor, the contract document into a plurality of performance segments prior to the extraction of the at least one performance segment from the contract document.

10. The method as claimed in claim 7 , further comprising:

storing, in a memory unit, a table including reference to a plurality of predefined metadata, a plurality of extraction machine learning models associated with each of the predefined metadata, an accuracy associated with each of the plurality of extraction machine learning models, and a corresponding type of performance segment.

11. The method as claimed in claim 10 , further comprising:

selecting, by the processor, the at least one extraction machine learning model based on the table stored in the memory unit.

12. The method as claimed in claim 7 , further comprising:

transmitting, by the processor, the extracted at least one performance segment and the at least one metadata value associated with the extracted at least one performance segment to a user device for display.

13. One or more non-transitory computer-readable media having stored therein computer-executable instructions causing one or more processors, when programmed thereby, to perform operations processing a contract document having at least one performance segment, wherein the operations comprise:

extracting, by a processor, at least one performance segment from the contract document;

executing, by the processor, one or more machine learning models that output a type of performance segment associated with the extracted at least one performance segment based on input of the extracted at least one performance segment, wherein the one or more machine learning models are trained with a training set comprising a plurality of predefined standard performance segments and corresponding types of each of the plurality of predefined standard performance segments, and the one or more machine learning models identify the type of performance segment;

identifying, by the processor, at least one metadata associated with the identified type of performance segment, the at least one metadata being selected from a predefined list of metadata associated with a plurality of types of performance segments;

based on the identified type of performance segment associated with the at least one performance segment and the identified at least one metadata associated with the identified type of performance segment, selecting at least one extraction machine learning model from a plurality of extraction machine learning models; and

extracting, by the processor, at least one metadata value, associated with the identified at least one metadata, from the at least one performance segment with the at least one extraction machine learning model selected from the plurality of extraction machine learning models.