NIN-CallLabels-v1
Turn bank-support conversations into reviewable labels.
Explore Models in NINXL for available workflows. Supported capabilities and model availability vary.
- Payment method
- UPI
- Issue
- Failed payment · debited
- Customer request
- Refund
- Agent promise
- Raise complaint
- Resolution
- Not confirmed
From source to something useful.
Illustrative example, authored by NIN. This is not a live model prediction.
- 01 / SOURCE
English UPI support excerpt
Customer: My UPI payment failed but the amount was debited. Please refund it. Agent: I will raise a complaint. The refund is not confirmed yet.
- 02 / FOCUSED MODEL
NIN-CallLabels-v1
Classify banking intent, customer requests and agent promises in English bank-support transcripts.
Planned capability - 03 / REVIEW
Conversation labels
A label describes the transcript, not verified account activity. Bank and support reviewers should validate labels before operational use.
Inspect the example input and output
English UPI support excerpt
Customer: My UPI payment failed but the amount was debited. Please refund it. Agent: I will raise a complaint. The refund is not confirmed yet.
Conversation labels
Payment method: UPI Issue: Failed payment, amount debited Request: Refund Agent promise: Raise complaint Resolution: Pending
Turn bank-support conversations into reviewable labels.
Label English bank-support transcripts for banking intent, UPI payment issues, refund requests, agent promises and resolution status. Designed for bank operations and complaint review.
Classify banking intent, customer requests and agent promises in English bank-support transcripts.
Identify whether the transcript records a resolved or pending outcome.
Identify UPI payment complaints, refund requests and other bank-service issues.
On-device / private-hosted
Built around your workflow.
On-device execution in NIN products and private hosting for organisational workflows are intended deployment options.
Details after evaluation.
Model size, hardware requirements, supported formats, licensing and measured performance will be documented when available. No release date is announced.
Where could NIN-CallLabels-v1 help?
Tell us about your workflow, the data it uses and what a useful result would look like. Discuss an evaluation partnership with NIN.
Discuss this model ↗
