Update README.md
Browse files
README.md
CHANGED
|
@@ -79,10 +79,17 @@ This model is meant to generate "Intent" for a given customer query on bank's ne
|
|
| 79 |
|
| 80 |
How to use :
|
| 81 |
|
| 82 |
-
1. Type a query such as
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
|
| 87 |
|
| 88 |
## Training and evaluation data
|
|
|
|
| 79 |
|
| 80 |
How to use :
|
| 81 |
|
| 82 |
+
1. Type a query such as
|
| 83 |
+
a) "Tell me my last 10 transactions" or
|
| 84 |
+
b) "I am senior citizen. What is FD rates" or
|
| 85 |
+
c) "I want to send money to my brother" or
|
| 86 |
+
d) "I want Fixed Deposit rate for 2 Crore INR"
|
| 87 |
+
e) "What is the outstanding EMI or my loan"
|
| 88 |
+
f) "How many active loans do I have ?"
|
| 89 |
+
e) "I want to add a new beneficiary"
|
| 90 |
+
3. This engine will understand the "intent" behind the query and return the value of LABEL_0 to LABEL_50.
|
| 91 |
+
4. The LABEL having maximum value (which will be at the top in the result) will be the identified "intent"
|
| 92 |
+
5. Use above mapping table and convert LABEL to Code. So, for example, LABEL_34 means "Senior Citizen Fixed Deposit Rate" and so on.
|
| 93 |
|
| 94 |
|
| 95 |
## Training and evaluation data
|