WE CLAIM:
1. A computer implemented method for classification of data in a machine learning system comprising:
generating a data classifier using a first dataset;
determining an accuracy value of the data classifier to achieve a predefined model accuracy threshold;
iterating calibration of the first dataset based on a set of parameters till the accuracy value matches or exceeds the predefined model accuracy threshold value; wherein the calibration comprises at least a user input to indicate a correctness of a presented subset of data from a second dataset;
generating, using the calibration, an enhanced data classifier for the classification of data.
2. The method of claim 1, wherein the data classifier is generated based on a training data available for the first dataset.
3. The method of claim 1, wherein the calibration is performed based on the set of parameters comprising one or more of a certainty score, a click utilization value, a certainty threshold value, a model accuracy value, an average machine learning time and an average annotation time or a combination thereof.
4. The method of the claim 4, wherein the certainty threshold based on set of parameters is dynamically adjusted until the predefined model accuracy threshold is achieved
5. The method of claim 1 wherein the user input received over the presented subset of data is used to generate the click utilization and the average annotation time
23

6. The method of claim 1, wherein the presented subset of data is generated from the second dataset based on the certainty threshold value and a computed candidate vector distance.
7. The method of claim 1, wherein the iterating of calibration further comprises;
coupling the presented subset of data with the user input and the training data till the predefined model accuracy threshold is achieved.
8. A data classification system comprising:
a processor; and
a memory coupled to the processor configured to be capable of executing programmed instructions comprising and stored in the memory to;
generate a data classifier using a first dataset;
determine an accuracy value of the data classifier to achieve a predefined model accuracy threshold;
iterate a calibration of the first dataset based on a set of parameters till the accuracy value matches or exceeds the predefined model accuracy threshold value; wherein the calibration comprises at least a user input to indicate an /correctness of a presented subset of data from a second dataset;
generate, using the calibration, an enhanced data classifier for the classification of data.
9. The system of claim 9, wherein the wherein the processor is further
configured to be capable of executing the stored programmed instructions to
generated the data classifier based on a training data available for the first dataset.
24

10. The system of claim 9, wherein the processor is further configured to be capable of executing the stored programmed instructions to perform the calibration is performed based on the set of parameters comprising one or more of a certainty score, a click utilization value, a certainty threshold value, a model accuracy value, an average machine learning time and an average annotation time or a combination thereof.
11. The system of the claim 12, wherein the processor is further configured to be capable of executing the stored programmed instructions to dynamically adjust the certainty threshold based on set of parameters until the predefined model accuracy threshold is achieved
12. The system of claim 9, wherein the processor is further configured to be capable of executing the stored programmed instructions to generate the click utilization and the average annotation time, based on the user input received over the presented subset of data.
13. The system of claim 9 wherein the processor is further configured to be capable of executing the stored programmed instructions to generate the presented subset of data from the second dataset based on the certainty threshold value and a computed candidate vector distance.
14. The system of claim 9, wherein the processor is further configured to be capable of executing the stored programmed instructions to iterate of calibration, further comprising;
coupling the presented subset of data with the user input and the training data till the predefined model accuracy threshold is achieved.
Dated this on April 02,2019 ^_^
Swetha S N
Of K& S Partners
25 Agent for the Ap,
IN/PA-2123