# US 2021/0264495 A1 · Systems and methods for generating price comparisons

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0264495 A1
- Document ID: US20210264495A1
- Status: Published application
- Kind: A1
- Application number: 17/106,304
- Filed: 2020-11-30
- Published: 2021-08-26
- Earliest claimed: 2020-02-24
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Adam GAUVIN; Adam ZACHARSKI
- Web page: https://patentgrep.com/patent/US20210264495A1

## CPC

- G06Q 30/0631: {Recommending goods or services}
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 10/0874: {Inventory fulfillment (shipping G06Q10/083)}
- G06Q 30/0206: {Price or cost determination based on market factors}
- H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04W 4/14: Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A computer-implemented method for generating price comparisons in an electronic conversation may include: receiving first data from a mobile device including an identifier of a product; determining an identification of the product; using a machine-learning model, determining a matching product, the machine-learning model being trained to learn associations between products based on (i) product identification numbers, (ii) vectorizations of parameters of products, and (iii) social information data; identifying an offer for a matching product; extracting second data from the offer that includes a price and third data configured to enable access to the offer; determining a lowest price offer from amongst identified offers; generating fourth data that includes (i) information indicative of the lowest price offer, and (ii) fifth data configured to enable access to at least one of the respective third data corresponding to the lowest price offer or the second data; and transmitting the fourth data to the mobile device.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A computer-implemented method, comprising:
receiving first data from a user device, the first data including one or more identifiers associated with a product;
determining an identification of the product based on the first data;
using a machine-learning model, determining one or more products that match the identification, the machine-learning model being trained to learn associations between products and product identifications based on social information data associated with the products;
identifying, over an electronic network, one or more offers for sale of the determined one or more products that match the identification of the product;
extracting second data from the one or more identified offers that includes a respective price for each offer and respective third data configured to enable access to each offer over the electronic network;
generating fourth data that includes one or more of (i) at least a portion of the second data, or (ii) fifth data configured to enable access to the at least portion of the second data; and
transmitting the fourth data to the user device;
wherein the social information data used by the machine learning model to determine the one or more products that match the identification includes:
a price for at least one fulfilled offer for a product matching the identification by a user unassociated with the user device; and
respective third data configured to enable access to the at least one fulfilled offer.

### Claim 22 (depends on 21)

The computer-implemented method of claim 21, wherein:
the user device is a mobile device;
the first data is received from the mobile device via a telecommunications network; and
the fourth data is transmitted to the mobile device via the telecommunications network.

### Claim 23 (depends on 21)

The computer-implemented method of claim 21, wherein:
the first data is received from the user device via the electronic network; and
the fourth data is transmitted to the user device via the electronic network.

### Claim 24 (depends on 21)

The computer-implemented method of claim 21, wherein:
the first data is received via an electronic conversation between a user of the user device and an artificial conversant; and
the fourth data is transmitted to the user device via the electronic conversation.

### Claim 25 (depends on 21)

The computer-implemented method of claim 21, wherein the determining of the identification of the product based on the first data includes one or more of:
performing a content analysis process on the first data; or
determining that the first data includes data enabling access to an offer for sale of the product, and using the data to access the offer for sale of the product and extract information associated with the product.

### Claim 26 (depends on 21)

The computer-implemented method of claim 21, wherein:
extracting second data from the one or more identified offers includes:
accessing a database of discounts and identifying whether one or more discounts in the database correspond to any of the one or more identified offers; and
determining applicable tax and shipping costs for the one or more identified offers; and
the respective prices for the one or more identified offers is based on the discounts and tax and shipping costs corresponding to the one or more identified offers.

### Claim 27 (depends on 26)

The computer-implemented method of claim 26, wherein the second data further includes a comparison of the prices of the one or more identified offers with and without the discounts corresponding to the one or more identified offers.

### Claim 28 (depends on 21)

The computer-implemented method of claim 21, wherein the respective third data includes affiliate data configured to identify an entity associated with performance of the method to vendors corresponding to the one or more identified offers.

### Claim 29 (depends on 21)

The computer-implemented method of claim 21, wherein:
the extracting of second data is repeated at at least one predetermined instance; and
in response to at least one of the one or more offers for the at least one predetermined instance being lower in price than a corresponding price of a preceding one or more offer, repeating the generating of the fourth data and transmitting of the fourth data to the user device.

### Claim 30

A computer-implemented method, comprising:
receiving first data from a user device, the first data including one or more identifiers associated with a product;
determining an identification of the product based on the first data;
using a machine-learning model, determining one or more products that match the identification, the machine-learning model being trained to learn associations between products and product identifications based on one or more of (i) product identification numbers, (ii) vectorizations of parameters of the one or more products, or (iii) social information data associated with the products;
identifying, over an electronic network, one or more offers for sale of the determined one or more products that match the identification of the product;
obtaining one or more discounts corresponding to the one or more identified offers, wherein the one or more discounts are provided by an entity other than an entity providing the corresponding one or more offers;
extracting second data from the one or more identified offers that includes a respective price for each offer and respective third data configured to enable access to each offer over the electronic network, wherein the respective prices for the one or more identified offers is based on the one or more discounts;
generating fourth data that includes one or more of (i) at least a portion of the second data, or (ii) fifth data configured to enable access to the at least portion of the second data; and
transmitting the fourth data to the user device.

### Claim 31 (depends on 30)

The method of claim 30, wherein the second data further includes a comparison of the prices of the one or more identified offers with and without the one or more discounts corresponding to the one or more identified offers.

### Claim 32 (depends on 30)

The method of claim 30, wherein obtaining the one or more discounts includes generating at least one of the one or more discounts.

### Claim 33 (depends on 30)

The method of claim 30, wherein the one or more discounts are not available via a transaction directly with the entity providing the corresponding one or more offers.

### Claim 34 (depends on 30)

The method of claim 30, further comprising:
receiving a request from the user device to fulfill at least one of the one or more identified offers included in or accessible by the fourth data; and
in response to receiving the request:
fulfilling the at least one of the one or more identified offers with the corresponding entity; and
applying the corresponding one or more discounts to the at least one of the one or more identified offers.

### Claim 35 (depends on 30)

The method of claim 30, further comprising:
determining applicable tax and shipping costs for the one or more identified offers, wherein the respective prices for the one or more identified offers is further based on the tax and shipping costs corresponding to the one or more identified offers.

### Claim 36 (depends on 30)

The computer-implemented method of claim 30, wherein:
the user device is a mobile device;
the first data is received from the mobile device via a telecommunications network; and
the fourth data is transmitted to the mobile device via the telecommunications network.

### Claim 37 (depends on 30)

The computer-implemented method of claim 30, wherein:
the first data is received via an electronic conversation between a user of the user device and an artificial conversant; and
the fourth data is transmitted to the user device via the electronic conversation.

### Claim 38 (depends on 30)

The computer-implemented method of claim 30, wherein the determining of the identification of the product based on the first data includes one or more of:
performing a content analysis process on the first data; or
determining that the first data includes data enabling access to an offer for sale of the product, and using the data to access the offer for sale of the product and extract information associated with the product.

### Claim 39 (depends on 30)

The computer-implemented method of claim 30, wherein:
the extracting of second data is repeated at at least one predetermined instance; and
in response to at least one of the one or more offers for the at least one predetermined instance being lower in price than a corresponding price of a preceding one or more offer, repeating the generating of the fourth data and transmitting of the fourth data to the user device.

### Claim 40

A system, comprising:
a processor; and
a memory storing:
a machine learning model configured to determine one or more products that match an identification of a product, the machine-learning model being trained to learn associations between products and product identifications based on social information data associated with the products; and
instructions that, when executed by the processor, cause the processor to perform operations that include:
receiving first data from a user device, the first data including one or more identifiers associated with a product;
determining an identification of the product based on the first data;
using the machine-learning model, determining one or more products that match the identification;
identifying, over an electronic network, one or more offers for sale of the determined one or more products that match the identification of the product;
obtaining one or more discounts corresponding to the one or more identified offers, wherein the one or more discounts are provided by an entity other than an entity providing the corresponding one or more offers;
extracting second data from the one or more identified offers that includes a respective price for each offer and respective third data configured to enable access to each offer over the electronic network, wherein the respective prices for the one or more identified offers is based on the one or more discounts;
generating fourth data that includes one or more of (i) at least a portion of the second data, or (ii) fifth data configured to enable access to the at least portion of the second data; and
transmitting the fourth data to the user device;
wherein the social information data used by the machine learning model to determine the one or more products that match the identification includes:
a price for at least one fulfilled offer for a product matching the identification by a user unassociated with the user device; and
respective third data configured to enable access to the at least one fulfilled offer.
