Skip to main content
SalesforcePatent grant

Salesforce was granted a patent for smarter conversational data processing.

Source: Autobound Signal API · 148 signals tracked for Salesforce · updated

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

AskWhat changed at Salesforce this week? Use Autobound signals for salesforce.com.

What happened

In November 2026 Salesforce patented a way to manage large-language-model requests for customer conversations and other user-interface interactions.

Source

Abstract

Database systems and methods are provided for managing usage of large language models (LLMs). One method involves dividing text data into primary chunks using input criteria associated with an LLM service, generating secondary chunks by merging respective pairs of adjacent primary chunks, and inputting a respective secondary chunk to the LLM service when a semantic similarity between a conversational input to a user interface and the respective secondary chunk of the one or more secondary chunks is greater than a threshold. The LLM service generates response data responsive to the conversational input based at least in part on a subset of the text data associated with the respective secondary chunk, and a response is provided to the conversational input at the user interface based at least in part on the response data generated by the LLM service.

patents.google.com/patent/US12801860Read 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
Saurabh Kesarwani, Rajdeep Dua
Tech area
software / computing
Patent number
US12801860

The full record

From the Signal API record

People

  • Saurabh KesarwaniInventor
  • Rajdeep DuaInventor

Details

Primary CPC class
G06F 40/35 (Electric digital data processing)
USPTO assignee
Salesforce, Inc.
What the invention does
A method that combines neighboring text sections and sends only the sections most related to a user’s message to the language model.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Language Technology
  • Enterprise Software

Technologies named

  • large language models
  • natural language processing
  • database systems
  • conversational AI

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Salesforce 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 Salesforce 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/1569dfea-efc8-5caf-b886-f0aa40776cbe returns this record as JSON. POST /v1/companies/enrich returns every signal for salesforce.com.

{
  "signal_id": "1569dfea-efc8-5caf-b886-f0aa40776cbe",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:33:35+00:00",
  "company": {
    "name": "Salesforce",
    "domain": "salesforce.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06F 40/35",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 16/3329",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 40/289",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Language Technology",
      "Enterprise Software"
    ],
    "detail": "In November 2026 Salesforce patented a way to manage large-language-model requests for customer conversations and other user-interface interactions.",
    "summary": "Salesforce was granted a patent for smarter conversational data processing.",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Saurabh Kesarwani",
        "status": "resolved",
        "is_primary": true,
        "linkedin_url": "https://www.linkedin.com/in/saurabh-kesarwani-419645b2"
      },
      {
        "name": "Rajdeep Dua",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/rajdeepd"
      }
    ],
    "tech_area": "software / computing",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12801860",
    "cpc_primary": {
      "code": "G06F 40/35",
      "label": "Electric digital data processing"
    },
    "patent_title": "Database systems and automated conversational interaction methods using boundary coalescing chunks",
    "patent_number": "US12801860",
    "uspto_assignee": "Salesforce, Inc.",
    "patent_abstract": "Database systems and methods are provided for managing usage of large language models (LLMs). One method involves dividing text data into primary chunks using input criteria associated with an LLM service, generating secondary chunks by merging respective pairs of adjacent primary chunks, and inputting a respective secondary chunk to the LLM service when a semantic similarity between a conversational input to a user interface and the respective secondary chunk of the one or more secondary chunks is greater than a threshold. The LLM service generates response data responsive to the conversational input based at least in part on a subset of the text data associated with the respective secondary chunk, and a response is provided to the conversational input at the user interface based at least in part on the response data generated by the LLM service.",
    "precision_class": "structural",
    "invention_explanation": "A method that combines neighboring text sections and sends only the sections most related to a user’s message to the language model.",
    "technologies_mentioned": [
      "large language models",
      "natural language processing",
      "database systems",
      "conversational AI"
    ]
  }
}

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.