System and method to recommend a service provider

Patent metadata

Field	Value
Publication number	US-11847682-B2
Application number	US-202016876774-A
Country	US
Kind code	B2
Filing date	May 18, 2020
Priority date	May 18, 2020
Publication date	Dec 19, 2023
Grant date	Dec 19, 2023

Abstract

Disclosed herein are system, method, and computer program product embodiments for recommending a service provider. An embodiment operates by receiving a search request specifying a service request by a user and location for the requested service, retrieving prior financial transactions of the user to purchase the service from a database, and determining a preference of the user based on the retrieved prior financial transactions. The embodiment further operates by applying the preference to a model trained to output a recommended service provider and selecting the recommended service provider for display on a user's device. The model more likely recommends service providers in the location having a higher ratio of tip-to-price relative to other providers for the service in the location based on a history of prior financial transactions of a plurality of users.

First claim

What is claimed is:

1. A computer-implemented method for recommending a service provider, comprising:
obtaining in real time transaction data of a service from payment terminals of a plurality of service providers to store the transaction data in at least one database as a history of prior financial transactions of the service, wherein the transaction data includes an initial charge and an updated charge of the service;
determining a typical tip and a typical price for the service based on the initial charge and the updated charge of the service;
training a machine-learning model based on the determined typical tip and typical price for the service to generate a service level for each of the plurality of service providers, wherein the service level is determined by a ratio of the typical tip to the typical price of the service;
receiving, via a user interface of a user's device, a search request including a service requested by a user and a location specified by the user for the requested service;
retrieving, from the at least one database, prior financial transactions of the user purchasing the service in the location;
training the machine-learning model using the prior financial transactions of the user purchasing the service to generate a preference of the user related to the service;
outputting a recommended service provider based on the service level for each service provider, the preference of the user, and a spending limit of the user, such that the service level of the recommended service provider is higher than the service levels of other service providers in the location, as specified in the history of prior financial transactions of the service;
providing a visual display of the recommended service provider to the user's device;
collecting feedback data of the recommended service provider from the user;
collecting, in real time from payment terminals of the recommended service provider, metadata of financial transactions of the user purchasing the service from the recommended service provider;
collecting review data of the recommended service provider scraped from third-party websites;
collecting additional financial transactions of the recommended service provider from external data sources through at least one application programming interface (API); and
adjusting the service level of the recommended service provider in the machine-learning model using the feedback data from the user, the metadata of financial transactions of the user purchasing the service from the recommended service provider, the review data, and the additional financial transactions.

2. The computer-implemented method of claim 1 , wherein the spending limit of the user comprises an available account balance of the user; and wherein the recommended service provider is selected based on the available account balance of the user.

3. The computer-implemented method of claim 1 , further comprising, for each of the prior financial transactions of the service:
calculating a tip for the service in the history of prior financial transactions as a difference between the initial and updated charges.

4. The computer-implemented method of claim 3 , further comprising determining the typical price and the typical tip based on a frequency of the initial charge and a frequency of the tip for the service respectively in the history of prior financial transactions of the service.

5. The computer-implemented method of claim 4 , further comprising providing for display on the user's device the typical price and a recommended tip for the recommended service provider, wherein the recommended tip is determined based on the preference of the user and the typical tip.

6. The computer-implemented method of claim 1 , further comprising:
determining a price range of the service based on the history of prior financial transactions of the service; and
providing for display on the user's device the price range.

7. The computer-implemented method of claim 1 , wherein receiving the location comprises receiving the location in the search request from the user.

8. The computer-implemented method of claim 1 , wherein receiving the location comprises receiving the location generated by a positioning sensor of the user's device.

9. The computer-implemented method of claim 1 , further comprising providing for display on the user's device a map of the service providers in the location with respective typical price of the service in the location.

10. The computer-implemented method of claim 1 , further comprising providing for display an alert related to the service in the location.

11. A system, comprising:
a memory; and
at least one processor coupled to the memory and configured to:
obtain in real time transaction data of a service from payment terminals of a plurality of service providers to store the transaction data in at least one database as a history of prior financial transactions of the service, wherein the transaction data includes an initial charge and an updated charge of the service;
determine a typical tip and a typical price for the service based on the initial charge and the updated charge of the service;
train a machine-learning model based on the determined typical tip and typical price for the service to generate a service level for each of the plurality of service providers, wherein the service level is determined by a ratio of the typical tip to the typical price of the service;
receive, via a user interface of a user's device, a search request including a service requested by a user and a location specified by the user for the requested service;
retrieve, from the at least one database, prior financial transactions of the user purchasing the service;
train the machine-learning model using the prior financial transactions of the user purchasing the service to generate a preference of the user related to the service;
output a recommended service provider based on the service level for each service provider, the preference of the user, and a spending limit of the user, such that the service level of the recommended service provider is higher than the service levels of other service providers in the location, as specified in the history of prior financial transactions of the service;
provide a visual display of the recommended service provider to the user's device;
collect feedback data of the recommended service provider from the user;
collect, in real time from payment terminals of the recommended service provider, metadata of financial transactions of the user purchasing the service from the recommended service provider;
collect review data of the recommended service provider scraped from third-party websites;
collect additional financial transactions of the recommended service provider from external data sources through at least one application programming interface (API); and
adjust the service level of the recommended service provider in the machine-learning model using the feedback data from the user, the metadata of financial transactions of the user purchasing the service, the review data, and the additional financial transactions.

12. The system of claim 11 , wherein the spending limit of the user comprises an available account balance of the user; and wherein the recommended service provider is selected based on the available account balance of the user.

13. The system of claim 11 , wherein the at least one processor is further configured to, for each of the prior financial transactions of the service:
calculate a tip for the service in the history of prior financial transaction as a difference between the initial and updated charges.

Assignees

• Capital One Services Llc

Inventors

• Tessler Leeyat Bracha
• Johnson Kyle
• Guo Rocky
• Rodriguez Elisa-Michelle
• Wu Angelina
• Saia Michael
• Cheng Lin Ni Lisa

Classifications

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q30/0206

  Price or cost determination based on market factors · CPC title

• G06Q30/0625 Primary

  by formulating product or service queries, e.g. using keywords or predefined options · CPC title