Patent 16 / Customer-Business Pairing
01 / 11 US11810005B2
↑↓ navigate  ·  all patents →
Siten Sanghvi  ·  Granted Nov 7, 2023

Customer-Business Pairing

An ML platform that predicts each customer's upcoming purchases from behavioral history, runs a vendor matching optimization to find relevant discounts, filters the match against preference rules (including distance), and triggers delivery via internet or SMS fallback.

US11810005B2Patent
Jul 29, 2020Filed
40 monthsTime to grant
19 Claims / 3 independentScope
2 CitationsForward citations
SCROLL TO EXPLORE
Visual patent explainer
02 / The Problem

Customer offers are broadcast. Purchase intent is predictable. These two facts aren't connected.

Businesses send the same promotional offers to every customer, regardless of purchase timing or expressed preferences. Meanwhile, financial institutions have rich transactional histories that signal exactly what a customer is likely to buy next — and when. That signal has never been systematically used to route relevant vendor offers.

No Purchase Prediction LayerVendors have no reliable way to know who is about to buy what — they blast broad promotions and hope for relevance
Preference Rules UncapturedEven targeted offers ignore customer-level constraints like distance willing to travel, preferred payment source, or timing windows
Connectivity DependencyDigital-only offer delivery fails entirely for customers without reliable internet access at the moment of relevance
03 / The Invention

Predict the purchase. Match the vendor. Apply the rules. Deliver.

A computing platform learns each user's purchase activity pattern from historical data, identifies upcoming anticipated purchases, then determines — via an ML optimization algorithm — a vendor whose sales offering includes a discount matching that anticipated purchase.

Before triggering the action, the platform retrieves the user's pre-stored preference rules (including distance willing to travel) and confirms they apply to the purchase attributes. Only then does it route the offer — using internet or SMS fallback depending on connectivity.

04 / Architecture

Behavioral history drives prediction. ML optimization drives the match.

The platform operates in two simultaneous tracks: a user behavioral track (learning purchase patterns from historical activity) and a vendor track (receiving and cataloguing current sales offerings). The ML optimization algorithm runs at the intersection — producing a match that satisfies both sides.

Preference rules act as a gate: a valid match that violates a user constraint (e.g., the vendor is too far) is not triggered. A time-based expiration rule can also block offers that are no longer within the user's defined window.

Architecture — US11810005B2
User behavioral
history
Vendor sales
offerings + discounts
Anticipated purchase
identified
ML optimization
matching
Preference rules
check (distance, etc.)
Trigger offer
(internet or SMS)
05 / Preference Rules

The chatbot collects the rules. The platform enforces them.

An intelligent chatbot initiates an interactive session with the user to collect preference rules via NLP. These rules are stored in a repository and retrieved at matching time — ensuring the system never surfaces an offer the user wouldn't accept.

The patent explicitly names distance as a preference rule attribute — a geographic constraint that eliminates irrelevant local offers before they reach the customer.

User-Defined Preference Rules — US11810005B2
Distance
Maximum distance the user is willing to travel for a product — eliminates vendor matches outside this radius.
Payment Source
Designates which payment instrument the user wants applied to anticipated purchases — eliminates offers requiring an unsupported payment method.
Time Window
A user-defined time period after which the offer is no longer triggered — preventing stale matches from firing when the purchase window has passed.
Comm Channel
Preferred communication mode — internet-first with optional SMS fallback when connectivity is unavailable.
06 / Matching Process

Five steps from user pattern to triggered offer.

The matching pipeline is explicit in the patent claims — it's not just a recommendation engine. The ML optimization algorithm identifies optimized resources; the preference rule gate confirms the match is valid for this specific user; and the time expiration check confirms it's still timely.

Matching Pipeline — US11810005B2
1
Determine Pattern
Platform analyzes historical user activity to establish a personal purchase activity pattern.
2
Identify Anticipated Purchase
Based on pattern, the platform identifies one or more upcoming purchase activities the user is likely to make.
3
ML Optimization Match
Algorithm searches vendor offering database for a sales offering — including a discount — that matches the anticipated purchase, optimizing for configured resources.
4
Preference Rule Gate
Platform retrieves user preference rules and confirms they apply to the matched purchase attributes — distance, payment source, timing window.
5
Trigger Offer Delivery
Action triggered via first (internet) or second (SMS) communication mode based on connectivity check. IVA initiates a session to present the matched offer.
07 / Match Simulator

Select a purchase pattern. See the match outcome.

The platform doesn't treat all anticipated purchases the same way. Preference rules, vendor proximity, and the user's interaction history modulate what gets matched and how it's delivered. Select a scenario below to see the full outcome.

Purchase Pattern → Match Outcome
08 / Dual-Mode Delivery

Internet check baked into the trigger logic.

Like the companion patent (P15 — ML Account Management), the connectivity check is not a fallback workaround — it's a structural element of the core claim. The platform must determine connectivity before triggering, and must use one of the two communication modes to deliver.

This dual-mode design ensures that customers without internet access at the moment of purchase-pattern relevance still receive the matched offer — via SMS — without any manual intervention.

Delivery Logic — US11810005B2
Preference rules
check passes
Connectivity
check
Internet available
→ First mode
No internet
→ Second mode (SMS)
IVA presents matched
offer to user
09 / Applications

Predictive, preference-gated commerce pairing at scale.

The combination of behavioral prediction, vendor matching, and preference-rule gating enables a new category of commerce infrastructure — one where offers arrive at the right moment, for the right product, from the right vendor, filtered by what the customer already said they want.

Use Cases — US11810005B2
Express
Local Business Offer Routing Platform predicts a grocery purchase and matches it to a nearby vendor offering a discount — filtered by the user's max distance preference — then delivers the offer via their preferred channel.
Express
Pre-Purchase Discount Surfacing Before a user makes a purchase they were already planning, the platform surfaces a matching vendor discount — converting an organic purchase into a loyalty-building interaction.
Inferred
Offline Customer Commerce Access Customer without active internet access receives an SMS-delivered matched offer for an anticipated purchase — enabling commerce relevance even in low-connectivity environments.
Inferred
Small Business Demand Signal Vendors (especially small businesses) gain advance visibility into imminent purchase demand from matched customers — allowing them to prepare inventory and staffing accordingly.
10 / Citations

2 Forward Citations

This patent has been cited by Intuit and a Chinese industrial supply platform — indicating that the customer-vendor purchase-matching framework is being applied both to individual consumer applications (Intuit's recipient attribute prediction) and supply-chain procurement optimization.

Forward citations confirmed via Google Patents · Jun 22, 2026
Forward Citations (2 of 2)
Intuit, Inc. US11900365B1  ·  Feb 13, 2024 Predicting attributes for recipients
Ouye Industrial Products Co., Ltd. CN115129764B  ·  Mar 25, 2025 Procurement data analysis method and system based on intelligent matching of supply and demand
11 / Timeline

Patent Lifecycle

Jul 29, 2020
Filed
Application filed
18 months
Feb 3, 2022
Published
Pre-grant publication US20220036210A1
21 months
Nov 7, 2023
Granted
US11810005B2 granted
~17 years
Mar 19, 2041
Expires
Est. expiration (adjusted — subject to maintenance fees)
End / Patent 16