Normalized claim
F1-score accuracy: 95.1% increase
"achieved 95.085 percent F1-Score accuracy"
IBS Software builds bilingual NER for cargo logistics emails using Amazon Bedrock managed distillation
Use case typeDocument processing automationUpdated Jun 30, 2026
IBS Software's cargo system processes thousands of bilingual cargo logistics email messages daily, extracting critical information such as air waybill numbers, flight details, weights, and delivery instructions in English and Japanese. The team built a production-ready bilingual named entity recognition solution to identify 23 entity types across the two languages while keeping inference cost low and supporting real-time processing.
- Organization
- IBS Software
- Industry
- Logistics
- Location
- United States
- Published
- June 2026
Reported outcomes
Operational inference cost: 14× lower
Cost savings
Processing latency: Less than 2 seconds
Catalog median for cost savings deployments: −40% across 171 reported metrics. Compare benchmarks →
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Operational inference cost: 14 x decrease
"reducing operational costs by 14x"
Normalized claim
Processing latency: 2 seconds decrease
"processes email messages in under 2 seconds"
Normalized claim
Teacher performance retained: 98%
"retained 98 percent of the teacher’s performance"
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- IBS Software
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Machine Learning Blog
They deployed a pipeline where Amazon S3 receives
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 2 of 2
- 1Document processing automation
- 2AI model training
- IBS Software annotated 500 bilingual email messages, with 350 English and 150 Japanese examples, for 23 entity types.
- The team used Amazon Bedrock managed distillation to transfer knowledge from Amazon Nova Pro to Amazon Nova Lite with token-level distillation.
- They deployed a pipeline where Amazon S3 receives .eml files, AWS Lambda extracts content, Amazon Bedrock runs the distilled model, and structured JSON results are stored in Amazon DynamoDB with confidence filtering and validation rules.
- The solution achieved 95.085% F1-score accuracy.
- It processed messages in under 2 seconds.
- It reduced operational inference costs by 14x while retaining about 98% of the teacher model performance.
Architecture
Cargo email messages arrive as .eml files in Amazon S3. AWS Lambda extracts email body and metadata. Amazon Bedrock processes text with a distilled Nova Lite model trained via managed distillation from Nova Pro. The model returns 23 entity types with confidence scores, then validation rules and confidence filtering are applied before structured JSON is stored in Amazon DynamoDB.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Quantified outcome available
- Technical implementation details available
Type: Blog PostPublished: Jun 30, 2026Publisher: AWSEvidence: VendorConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Was this useful?
Community
Comments
No published comments yet.