Skip to main content
OraclePatent grant

Oracle was granted a patent for distance-based chatbot intent classification.

Source: Autobound Signal API · 147 signals tracked for Oracle · updated

Get Oracle's live signals in Claude or ChatGPT, or by API

AskWhat changed at Oracle this week? Use Autobound signals for oracle.com.

What happened

In November 2026 Oracle patented a natural-language processing technique for classifying user messages in chatbot systems.

Source

patents.google.comNov 17, 2026

US patent US12801861

Distance-based logit values for natural language processing

Abstract

Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.

patents.google.com/patent/US12801861Read the full source

Extracted by Autobound

From the Signal API record
Signal
Patent grant

What this signalsA new patent often shows where a company is putting its R&D budget.

Grant date
Nov 17, 2026
Inventors
4
Tech area
software / computing
Patent number
US12801861

The full record

From the Signal API record

People

  • Ying XuInventor
  • Poorya ZaremoodiInventor
  • Thanh Tien VuInventor
  • Cong Duy Vu HoangInventor
  • Vladislav BlinovInventor
  • Yu-Heng HongInventor

Details

Primary CPC class
G06F 40/35 (Electric digital data processing)
USPTO assignee
Oracle International Corporation
What the invention does
A chatbot uses several machine-learning classifiers with adjusted confidence scores based on how far an input is from known message categories.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Machine Learning
  • Language Technology

Technologies named

  • natural language processing
  • chatbots
  • machine learning
  • text classification

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Oracle and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Oracle this week?”

  2. Send it to your own tools

    The Signal API returns patent signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full patents-company record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/083bdfd0-6b93-5e42-8bd5-ffec2943f68a returns this record as JSON. POST /v1/companies/enrich returns every signal for oracle.com.

{
  "signal_id": "083bdfd0-6b93-5e42-8bd5-ffec2943f68a",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:33:49+00:00",
  "company": {
    "name": "Oracle",
    "domain": "oracle.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06F 40/35",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06N 20/00",
        "label": "Computing arrangements based on specific computational models"
      },
      {
        "code": "H04L 51/02",
        "label": "Transmission of digital information"
      },
      {
        "code": "G06F 40/205",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 40/253",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning",
      "Language Technology"
    ],
    "detail": "In November 2026 Oracle patented a natural-language processing technique for classifying user messages in chatbot systems.",
    "summary": "Oracle was granted a patent for distance-based chatbot intent classification.",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Ying Xu",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Poorya Zaremoodi",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/pooryazare"
      },
      {
        "name": "Thanh Tien Vu",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/thanh-vu-5592aa31"
      },
      {
        "name": "Cong Duy Vu Hoang",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/cdvhoang"
      },
      {
        "name": "Vladislav Blinov",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Yu-Heng Hong",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Yakupitiyage Don Thanuja Samodhye Dharmasiri",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Vishal Vishnoi",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/vishalvishnoi"
      }
    ],
    "tech_area": "software / computing",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12801861",
    "cpc_primary": {
      "code": "G06F 40/35",
      "label": "Electric digital data processing"
    },
    "patent_title": "Distance-based logit values for natural language processing",
    "patent_number": "US12801861",
    "uspto_assignee": "Oracle International Corporation",
    "patent_abstract": "Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.",
    "precision_class": "structural",
    "invention_explanation": "A chatbot uses several machine-learning classifiers with adjusted confidence scores based on how far an input is from known message categories.",
    "technologies_mentioned": [
      "natural language processing",
      "chatbots",
      "machine learning",
      "text classification"
    ]
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.