Skip to main content
Home DepotPatent grant

Home Depot was granted a patent for joint-learning search classification.

What happened

In August 2026 Home Depot patented search technology for understanding customer queries and organizing results across its online shopping experience.

Source

patents.google.comAug 25, 2026

US patent US12717856

Search engine using joint learning for multi-label classification

Abstract

A method of configuring a search engine to classify a search query includes receiving a search query data set, the search query data set comprising a plurality of search queries, defining a first set of candidate labels and a second set of candidate labels according to the search queries in the search query data set, concatenating the first set of candidate labels with the second set of candidate labels to generate a concatenated candidate label set, generating a compatibility matrix comprising a similarity between the concatenated candidate label set and the search query data set, and training a classification network according to the compatibility matrix.

patents.google.com/patent/US12717856Read 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
Aug 25, 2026
Inventors
3
Tech area
software / computing
Patent number
US12717856

The full record

From the Signal API record

People

  • Ali AhmadvandInventor
  • Surya KallumadiInventor
  • Faizan JavedInventor

Details

Primary CPC class
G06F 16/9535 (Electric digital data processing)
USPTO assignee
Home Depot Product Authority, LLC
What the invention does
A search method that learns several label types together, compares how well they fit each query, and uses those matches to classify searches.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Machine Learning
  • eCommerce

Technologies named

  • search engines
  • machine learning
  • query classification
  • eCommerce

Extraction

Detected
Sep 15, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Home Depot 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 Home Depot 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/1a76669a-87b2-5439-af34-0e4056b461ba returns this record as JSON. POST /v1/companies/enrich returns every signal for homedepot.com.

{
  "signal_id": "1a76669a-87b2-5439-af34-0e4056b461ba",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-09-15T19:45:42+00:00",
  "company": {
    "name": "Home Depot",
    "domain": "homedepot.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06F 16/9535",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 18/2148",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 18/2431",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06N 3/045",
        "label": "Computing arrangements based on specific computational models"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning",
      "eCommerce"
    ],
    "detail": "In August 2026 Home Depot patented search technology for understanding customer queries and organizing results across its online shopping experience.",
    "summary": "Home Depot was granted a patent for joint-learning search classification.",
    "event_at": "2026-08-25",
    "inventors": [
      {
        "name": "Ali Ahmadvand",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Surya Kallumadi",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/surya-kallumadi-a0778a13"
      },
      {
        "name": "Faizan Javed",
        "status": "unresolved",
        "is_primary": false
      }
    ],
    "tech_area": "software / computing",
    "event_kind": "grant_date",
    "grant_date": "2026-08-25",
    "source_url": "https://patents.google.com/patent/US12717856",
    "cpc_primary": {
      "code": "G06F 16/9535",
      "label": "Electric digital data processing"
    },
    "patent_title": "Search engine using joint learning for multi-label classification",
    "patent_number": "US12717856",
    "uspto_assignee": "Home Depot Product Authority, LLC",
    "patent_abstract": "A method of configuring a search engine to classify a search query includes receiving a search query data set, the search query data set comprising a plurality of search queries, defining a first set of candidate labels and a second set of candidate labels according to the search queries in the search query data set, concatenating the first set of candidate labels with the second set of candidate labels to generate a concatenated candidate label set, generating a compatibility matrix comprising a similarity between the concatenated candidate label set and the search query data set, and training a classification network according to the compatibility matrix.",
    "precision_class": "structural",
    "invention_explanation": "A search method that learns several label types together, compares how well they fit each query, and uses those matches to classify searches.",
    "technologies_mentioned": [
      "search engines",
      "machine learning",
      "query classification",
      "eCommerce"
    ]
  }
}

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.