Application program interfaces for order and delivery service recommendations

Patent metadata

Field	Value
Publication number	US-11295322-B1
Application number	US-201916248471-A
Country	US
Kind code	B1
Filing date	Jan 15, 2019
Priority date	Jan 15, 2019
Publication date	Apr 5, 2022
Grant date	Apr 5, 2022

Abstract

An online order management service is configured to interface between merchants and order/delivery services so that a merchant can provide a catalog to multiple order/delivery services without having to communicate directly with the order/delivery services. A recommendation service is also provided to provide recommendations to merchants regarding which of multiple order/delivery services to use. The recommendation service bases its recommendations on historical order data that has been archived by the online order management service, as well as on known or derived merchant properties. The recommendation service may also recommend product items to be included in a catalog in order to improve sales results achieved when listing the catalog with any particular order/delivery service.

First claim

What is claimed is:

1. A method, comprising:
receiving, via a vendor service interface, orders placed by customers with network-accessible third-party services;
sending the orders to merchants via a data communication network;
training one or more machine learning models utilizing, as a training dataset, order data corresponding to the orders sent to the merchants and contextual data associated with a specific merchant such that one or more trained machine learning models are generated, the one or more machine learning models trained based at least in part on similarity metrics associated with the merchants such that the trained machine learning models are configured to identify third-party services that are most likely to be utilized by the specific merchant that has characteristics and associated data similar to the merchants;
determining, utilizing the one or more trained machine learning models with historical order data as input to the one or more trained machine learning models, a recommended network-accessible third-party service to be used for publishing a product catalog of the specific merchant, wherein the historical order data identifies one or more of:
items of the orders;
third-party services with which the customers placed the orders; or
the merchants that fulfilled the orders;

selecting the specific merchant from the merchants to receive data including a recommendation to utilize the recommended network-accessible third-party service for publishing the product catalog; and,
sending, to the specific merchant, the data representing the recommendation.

2. The method of claim 1 , further comprising sending the product catalog to the recommended network-accessible third-party service for publishing.

3. The method of claim 1 , wherein:
the historical order data indicates times at which the orders were placed; and
determining the recommended network-accessible third-party service is based at least in part on a current time and the times at which the orders were placed.

4. The method of claim 1 , further comprising analyzing the historical order data to determine one or more recommended items of the merchant to be included in the product catalog.

5. The method of claim 1 , further comprising instructing the recommended network-accessible third-party service to publish the product catalog.

6. The method of claim 1 , further comprising:
identifying a group of the orders that were fulfilled by merchants having one or more common properties; and
wherein the historical order data corresponds to the group of the orders.

7. The method of claim 6 , wherein one or more common properties comprise one or more of:
geographic locations;
business types;
product offerings;
product inventories;
sales rates; or
cash flows.

8. The method of claim 6 , further comprising analyzing the historical order data to determine the one or more common properties.

9. The method of claim 6 , further comprising determining the one or more common properties based at least in part on merchant information received from one or more online services, wherein the merchant information comprises one or more of:
operations data;
inventory data; or
transaction data.

10. A system, comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions executable by the one or more processors, wherein the instructions program the one or more processors to perform actions comprising:
receiving, via a vendor service interface, historical order data regarding orders placed by customers with network-accessible third-party order services, wherein the historical order data identifies one or more of:
items of the orders;
for individual ones of the orders, one of the network-accessible third-party order services with which the order was placed; or
for the individual ones of the orders, a merchant that fulfilled the order;

training one or more machine learning models utilizing, as a training dataset, the historical order data and contextual data associated with a specific merchant such that one or more trained machine learning models are generated, the one or more machine learning models trained based at least in part on similarity metrics associated with merchants such that the trained machine learning models are configured to identify third-party services that are most likely to be utilized by the specific merchant with characteristics and associated data similar to the merchants;
determining, utilizing the one or more trained machine learning models, a recommendation of a network-accessible order and delivery service to be used by the specific merchant for publishing a product catalog;
selecting the specific merchant from the merchants to receive data including the recommendation; and
sending, to the specific merchant, the data representing the recommendation.

11. The system of claim 10 , the actions further comprising sending the product catalog to the network-accessible third-party service for publishing.

12. The system of claim 10 , the actions further comprising:
analyzing the historical order data to determine one or more recommended items of the merchant to be included in the catalog.

13. The system of claim 10 , the actions further comprising:
analyzing the historical order data to determine one or more items ordered by customers that are in a geographic region associated with the specific merchant; and
recommending that the one or more items be included in the product catalog.

14. The system of claim 10 , the actions further comprising:
identifying a group of the orders that were fulfilled by merchants having one or more common properties; and
wherein the historical order data corresponds to the group of the orders.

15. A system comprising:
one or more processors; and
non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving, via a vendor service interface, orders placed by customers with network-accessible third-party services;
training one or more machine learning models utilizing, as a training dataset, order data corresponding to the orders sent to the merchants and contextual data associated with a specific merchant such that one or more trained machine learning models are generated, the one or more machine learning models trained based at least in part on similarity metrics associated with the merchants such that the trained machine learning models are configured to identify third-party services that are most likely to be utilized by the specific merchant with characteristics and associated data similar to the merchants;
determining, utilizing the one or more trained machine learning models with historical order data as input to the one or more trained machine learning models, a recommended network-accessible third-party service to be used for publishing a product catalog of the specific merchant;
selecting the specific merchant from the merchants to receive data including a recommendation to utilize the recommended network-accessible third-party service for publishing the product catalog; and
sending, to the specific merchant, the data representing the recommendation.

16. The system of claim 15 , the operations further comprising:
identifying a group of the orders that were fulfilled by merchants having one or more common properties; and
wherein the historical order data is from the group of the orders.

17. The system of claim 16 , the operations further comprisin

Assignees

• Square Inc
• Block Inc

Inventors

• Yien Kevin
• Johnson Logan

Classifications

• G06Q50/12

  Hotels or restaurants · CPC title

• G06Q30/0631

  Recommending goods or services · CPC title

• G06Q10/083

  Shipping · CPC title

• G06Q30/0603

  Catalogue creation or management · CPC title

• G06Q30/0201 Primary

  Market modelling; Market analysis; Collecting market data · CPC title