Elevance Health was granted a patent for improving conversational AI accuracy

{
  "signal_id": "772c3acb-ab2e-592d-b82f-041681be390c",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-09-15T00:56:36+00:00",
  "company": {
    "name": "Elevance Health",
    "domain": "elevancehealth.com"
  },
  "data": {
    "cpc": [
      {
        "code": "H04L 51/02",
        "label": "Transmission of digital information"
      },
      {
        "code": "G06F 40/30",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning",
      "Healthcare Technology"
    ],
    "detail": "In August 2026 Elevance Health patented chatbot testing technology for healthcare customer-service and support interactions.",
    "summary": "Elevance Health was granted a patent for improving conversational AI accuracy",
    "event_at": "2026-08-18",
    "inventors": [
      {
        "name": "Channabasava R",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Prasad Halkur Shankar Rao",
        "status": "unresolved",
        "is_primary": false
      }
    ],
    "tech_area": "networking / data transmission",
    "event_kind": "grant_date",
    "grant_date": "2026-08-18",
    "source_url": "https://patents.google.com/patent/US12712830",
    "cpc_primary": {
      "code": "H04L 51/02",
      "label": "Transmission of digital information"
    },
    "patent_title": "Conversational artificial intelligence regression ensemble",
    "patent_number": "US12712830",
    "uspto_assignee": "Elevance Health, Inc.",
    "patent_abstract": "A method of improving chatbot accuracy includes receiving an input test file containing chatbot interactions data including utterances, expected intents, and expected responses. For each interaction, the method may generate predicted intents and responses using an AI-based chatbot trained on previous interaction data. The method may determine similarity between predicted and expected responses/intents by calculating Levenshtein distances and comparing to predetermined thresholds. Failed interaction keywords may be extracted using natural language processing to identify failing topics. Machine learning decision tree classification may analyze patterns in failed interactions to generate resolution suggestions. The method may generate an interactive dashboard displaying historical performance trends, domain-specific accuracy metrics, visualizations of frequently keywords, and confidence distributions for failed interactions. This automated regression testing approach enables efficient identification and resolution of chatbot performance issues while maintaining response quality.",
    "precision_class": "structural",
    "invention_explanation": "A quality-checking method that compares a chatbot’s predicted intent and answer with the expected result, using multiple evaluation models to identify failures.",
    "technologies_mentioned": [
      "conversational AI",
      "chatbots",
      "natural language processing",
      "automated testing"
    ]
  }
}

curl https://signals.autobound.ai/v1/signals/772c3acb-ab2e-592d-b82f-041681be390c \
  -H "X-API-KEY: $AUTOBOUND_API_KEY"

curl -X POST https://signals.autobound.ai/v1/companies/enrich \
  -H "X-API-KEY: $AUTOBOUND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"domain":"elevancehealth.com","limit":20}'