Methods and systems for the sale of consumer services

• US 10,402,760 B2
• Filed: 11/15/2013
• Issued: 09/03/2019
• Est. Priority Date: 11/15/2012
• Status: Active Grant

• Current Assignee: Impel IT! Incorporated
• Original Assignee: Impel IT! Incorporated
• Inventors: Kinsey, II, Edward Phillip
• Primary Examiner(s): Yesildag, Mehmet
• Application Number:
  US14/081,692
• Publication Number:
  US 20140136264A1
• Time in Patent Office: 2,118 Days
• Field of Search: None
• CPC Class Codes: G06Q 10/063116 Schedule adjustment for a person or group
• CPC Class Codes: G06Q 10/1095 Meeting or appointment
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0627 using item specifications
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: Y02P 90/80 Management or planning

Abstract

Computer-implemented systems and methods for the sale of consumer services. Predictions are made based on the behaviors, preferences, assets, identifying characteristics, and other attributes associated with customers and merchants. In one implementation, a prediction is made as to whether a customer is likely to request a service and whether a merchant is likely to be selected by the customer to provide the service. In another implementation, the calendars of a merchant and customer are automatically updated to account for the customer'"'"'s late arrival to an appointment at the merchants location. In yet another implementation, a customer purchases an appointment for a service from another customer that has the appointment scheduled with a merchant providing the service.

Claims

1. A computer-implemented method comprising:

(a) predicting, by at least one computer utilizing at least one processor, that a customer of a plurality of customers is likely to request a service, wherein the predicting in (a) is based on first historical data comprising attributes of different customers that have previously requested the service;

(b) predicting, by the at least one computer utilizing the at least one processor, that one or more merchants of a plurality of merchants has a respective probability of being selected by the customer to provide the service that meets a threshold, wherein the predicting in (b) is based on second historical data comprising attributes of different merchants that have previously provided the service, the predicting in (b) comprising;

training a machine learning classifier over a period of time, using the second historical data, to predict whether a particular customer would be likely to select a given merchant for scheduling an appointment for the service; and

providing current attributes of the plurality of merchants and current attributes of the customer as inputs to the machine learning classifier and obtaining the predicted merchants as output of the classifier;

(c) selecting, by the at least one computer utilizing the at least one processor, one of the predicted merchants based on one or more criteria;

(d) scheduling the appointment for the service on a calendar of the customer and on a calendar of the selected merchant;

(e) providing notification of the appointment to a customer device of the customer and a merchant device of the selected merchant;

(f) determining a time of the scheduled service and a geographical location of the scheduled service;

(g) identifying a plurality of previous appointments of the customer for one or more other services, the previous appointments having a pattern of being scheduled at times proximate to the time of the scheduled service, the previous appointments having a pattern of taking place at a geographical location same as or proximate to the geographical location of the scheduled service;

(h) automatically scheduling on a calendar of the customer one or more appointments for one or more of the other services at one or more times proximate to the scheduled service;

(i) predicting that the one or more appointments for the one or more other services are likely to require one or more electronic forms, wherein the predicting in (i) is based on third historical data comprising attributes of different merchants that have previously provided the other services and attributes of different users that have previously requested the other services;

(j) automatically populating the one or more electronic forms with information associated with the customer based on a permission of the customer specified in a customer profile;

(k) assigning a machine-readable unique barcode to the customer and storing a representation of the unique barcode in the customer profile;

(l) tracking a location of the customer via a location tracking sensor of the customer device;

(m) determining that the customer has arrived, based on information received via the location tracking sensor of the customer device, at a location of a merchant providing one of the other services;

(n) in response to the determination of the arrival of the customer, causing the unique barcode of the customer to be presented on a display screen of the customer device; and

(o) upon scanning the unique barcode by a scanning device at the location of the merchant providing one of the other services, registering the arrival of the customer and electronically issuing one or more of the electronic forms to the merchant providing one of the other services.

2. The method of claim 1 wherein scheduling the appointment comprises:

sending information to the customer device to cause the customer device to notify the customer of the appointment; and

after sending the information to the customer device, receiving from the customer device an indication of acceptance of the appointment.

3. The method of claim 1 wherein scheduling the appointment comprises:

sending information to the merchant device to cause the merchant device to notify the merchant of the appointment; and

after sending the information to the merchant device, receiving from the merchant device an indication of acceptance of the appointment.

4. The method of claim 1 wherein the notification is one or more of:

audio, visual, and haptic.

5. The method of claim 1 wherein predicting that the customer of the plurality of customers is likely to request the service comprises:

training a second classifier to predict whether a given customer would request the service using the first historical data comprising the attributes of different customers that have requested the service; and

providing attributes of the customer as input to the second classifier and obtaining a prediction as output of the second classifier.

6. The method of claim 1 wherein attributes of a particular customer comprises a plurality of the following:

an identification attribute, a preference attribute, an asset attribute, and a task attribute.

7. The method of claim 6 wherein:

a particular identification attribute is one of;

name, gender, driver'"'"'s license number, social security number, no-show performance, and home address;

wherein a particular preference attribute is one of;

level of feedback expected from merchants, type of service, whether to automatically schedule appointments for services, whether to allow another user to purchase an appointment, physical exercise preference, whether to follow scheduled maintenance, a preference of merchant for a given service, and merchant location preference;

wherein a particular asset attribute is one of;

primary care doctor, spouse/partner, home address, and vehicle identification number; and

wherein a particular task attribute is one of;

car repair, car maintenance, doctor visit, exercise class, training, haircut, and spa appointment.

8. The method of claim 1 wherein attributes of a particular merchant comprises a plurality of the following:

an identification attribute, a preference attribute, a resource attribute, and a task attribute.

9. The method of claim 8 wherein:

a particular identification attribute is one of;

business name, service sector, business address, gender, business license, on-time performance, operating hours, type of personal care provider, type of automotive service provider, type of building maintenance provider, type of training provider, type of transportation services provider, and type of healthcare provider;

wherein a particular preference attribute is one of;

resource utilization, accept weekend appointments, automatic appointment triage, accept emergency requests, accept insurance, and type of insurance accepted;

wherein a particular resource attribute is one of;

employee name, employee specialty, and current location; and

wherein a particular task attribute is one of;

car repair, car maintenance, doctor visit, exercise class, haircut, and spa appointment.

10. The method of claim 1 wherein the service is one of:

car repair, car maintenance, doctor visit, exercise class, training, haircut, and spa appointment.

11. The method of claim 1 wherein a particular criterion is:

a distance between a current location of the customer device and the merchant, a customer approval rating of the merchant, a preference of the customer, customer feedback regarding the merchant, or a specialty of the merchant.

12. The method of claim 1 wherein the customer device is one of:

a smart phone, a smart watch, smart glasses, a portable computer, and a tablet computer.

13. A system comprising:

one or more computers programmed to perform operations comprising;

(a) predicting that a customer of a plurality of customers is likely to request a service. wherein the predicting in (a) is based on first historical data comprising attributes of different customers that have previously requested the service;

(b) predicting that one or more merchants of a plurality of merchants has a respective probability of being selected by the customer to provide the service that meets a threshold, wherein the predicting in (b) is based on second historical data comprising attributes of different merchants that have previously provided the service, the predicting in (b) comprising;

training a machine learning classifier over a period of time, using the second historical data, to predict whether a particular customer would be likely to select a given merchant for scheduling an appointment for the service; and

providing current attributes of the plurality of merchants and current attributes of the customer as inputs to the machine learning classifier and obtaining the predicted merchant as output of the classifier;

(c) selecting one of the predicted merchants based on one or more criteria;

(d) scheduling the appointment for the service on a calendar of the customer and on a calendar of the selected merchant;

(e) providing notification of the appointment to a customer device of the customer and a merchant device of the selected merchant;

(f) determining a time of the scheduled service and a geographical location of the scheduled service;

(g) identifying a plurality of previous appointments of the customer for one or more other services, the previous appointments having a pattern of being scheduled at times proximate to the time of the scheduled service, the previous appointments having a pattern of taking place at a geographical location same as or proximate to the geographical location of the scheduled service;

(h) automatically scheduling on a calendar of the customer one or more appointments for one or more of the other services at one or more times proximate to the scheduled service;

(i) predicting that the one or more appointments for the one or more other services are likely to require one or more electronic forms, wherein the predicting in (i) is based on third historical data comprising attributes of different merchants that have previously provided the other services and attributes of different users that have previously requested the other services;

(j) automatically populating the one or more electronic forms with information associated with the customer based on a permission of the customer specified in a customer profile;

(k) assigning a machine-readable unique barcode to the customer and storing a representation of the unique barcode in the customer profile;

(l) tracking a location of the customer via a location tracking sensor of the customer device;

(m) determining that the customer has arrived, based on information received via the location tracking sensor of the customer device, at a location of a merchant providing one of the other services;

(n) in response to the determination of the arrival of the customer, causing the unique barcode of the customer to be presented on a display screen of the customer device; and

(o) upon scanning the unique barcode by a scanning device at the location of the merchant providing one of the other services, registering the arrival of the customer and electronically issuing one or more of the electronic forms to the merchant providing one of the other services.

14. The system of claim 13 wherein scheduling the appointment comprises:

sending information to the customer device to cause the customer device to notify the customer of the appointment; and

after sending the information to the customer device, receiving from the customer device an indication of acceptance of the appointment.

15. The system of claim 13 wherein scheduling the appointment comprises:

sending information to the merchant device to cause the merchant device to notify the merchant of the appointment; and

after sending the information to the merchant device, receiving from the merchant device an indication of acceptance of the appointment.

16. The system of claim 13 wherein the notification is one or more of:

audio, visual, and haptic.

17. The system of claim 13 wherein predicting that the customer of the plurality of customers is likely to request the service comprises:

training a second classifier to predict whether a given customer would request the service using the first historical data comprising the attributes of different customers that have requested the service; and

providing attributes of the customer as input to the second classifier and obtaining a prediction as output of the second classifier.

18. The system of claim 13 wherein attributes of a particular customer comprises a plurality of the following:

an identification attribute, a preference attribute, an asset attribute, and a task attribute.

19. The system of claim 18 wherein:

a particular identification attribute is one of;

name, gender, driver'"'"'s license number, social security number, no-show performance, and home address;

wherein a particular preference attribute is one of;

level of feedback expected from merchants, type of service, whether to automatically schedule appointments for services, whether to allow another user to purchase an appointment, physical exercise preference, whether to follow scheduled maintenance, a preference of merchant for a given service, and merchant location preference;

wherein a particular asset attribute is one of;

primary care doctor, spouse/partner, home address, and vehicle identification number; and

wherein a particular task attribute is one of;

car repair, car maintenance, doctor visit, exercise class, training, haircut, and spa appointment.

20. The system of claim 13 wherein attributes of a particular merchant comprises a plurality of the following:

an identification attribute, a preference attribute, a resource attribute, and a task attribute.

21. The system of claim 20 wherein:

a particular identification attribute is one of;

business name, service sector, business address, gender, business license, on-time performance, operating hours, type of personal care provider, type of automotive service provider, type of building maintenance provider, type of training provider, type of transportation services provider, and type of healthcare provider;

wherein a particular preference attribute is one of;

resource utilization, accept weekend appointments, automatic appointment triage, accept emergency requests, accept insurance, and type of insurance accepted;

wherein a particular resource attribute is one of;

employee name, employee specialty, and current location; and

wherein a particular task attribute is one of;

car repair, car maintenance, doctor visit, exercise class, haircut, and spa appointment.

22. The system of claim 13 wherein the service is one of:

car repair, car maintenance, doctor visit, exercise class, training, haircut, and spa appointment.

23. The system of claim 13 wherein a particular criterion is:

a distance between a current location of the customer device and the merchant, a customer approval rating of the merchant, a preference of the customer, customer feedback regarding the merchant, or a specialty of the merchant.

24. The system of claim 13 wherein the customer device is one of:

a smart phone, a smart watch, smart glasses, a portable computer, and a tablet computer.

25. An article of manufacture, comprising a non-transitory machine-readable medium storing instructions that, when executed, configure one or more computers to perform operations comprising:

(a) predicting that a customer of a plurality of customers is likely to request a service, wherein the predicting in (a) is based on first historical data comprising attributes of different customers that have previously requested the service;

(b) predicting that one or more merchants of a plurality of merchants has a respective probability of being selected by the customer to provide the service that meets a threshold, wherein the predicting in (b) is based on second historical data comprising attributes of different merchants that have previously provided the service, the predicting in (b) comprising;

training a machine learning classifier over a period of time, using the second historical data, to predict whether a particular customer would be likely to select a given merchant for scheduling an appointment for the service; and

providing current attributes of the plurality of merchants and current attributes of the customer as inputs to the machine learning classifier and obtaining the predicted merchant as output of the classifier;

(c) selecting one of the predicted merchants based on one or more criteria;

(d) scheduling the appointment for the service on a calendar of the customer and on a calendar of the selected merchant;

(e) providing notification of the appointment to a customer device of the customer and a merchant device of the selected merchant;

(f) determining a time of the scheduled service and a geographical location of the scheduled service;

(g) identifying a plurality of previous appointments of the customer for one or more other services, the previous appointments having a pattern of being scheduled at times proximate to the time of the scheduled service, the previous appointments having a pattern of taking place at a geographical location same as or proximate to the geographical location of the scheduled service;

(h) automatically scheduling on a calendar of the customer one or more appointments for one or more of the other services at one or more times proximate to the scheduled service;

(i) predicting that the one or more appointments for the one or more other services are likely to require one or more electronic forms, wherein the predicting in (i) is based on third historical data comprising attributes of different merchants that have previously provided the other services and attributes of different users that have previously requested the other services;

(j) automatically populating the one or more electronic forms with information associated with the customer based on a permission of the customer specified in a customer profile;

(k) assigning a machine-readable unique barcode to the customer and storing a representation of the unique barcode in the customer profile;

(l) tracking a location of the customer via a location tracking sensor of the customer device;

(m) determining that the customer has arrived, based on information received via the location tracking sensor of the customer device, at a location of a merchant providing one of the other services;

(n) in response to the determination of the arrival of the customer, causing the unique barcode of the customer to be presented on a display screen of the customer device; and

(o) upon scanning the unique barcode by a scanning device at the location of the merchant providing one of the other services, registering the arrival of the customer and electronically issuing one or more of the electronic forms to the merchant providing one of the other services.

26. The article of manufacture of claim 25, wherein predicting that the customer of the plurality of customers is likely to request the service comprises:

training a second classifier to predict whether a given customer would request the service using the first historical data comprising the attributes of different customers that have requested the service; and

providing attributes of the customer as input to the second classifier and obtaining a prediction as output of the second classifier.