Computing techniques to predict locations to obtain products utilizing machine-learning
Various embodiments are generally directed to techniques utilizing computers to determine one or more locations for a customer to pickup a product based on a trained models. Embodiments may also include generating a code that may be utilized to obtain the product and perform a verification operation.
1. An apparatus, comprising:
a communication interface coupled with a computing network;
a processor circuit coupled with the communication interface; and
a memory coupled with the processor circuit and the communication interface, the memory storing instructions which when executed by the processor circuit, cause the processor circuit to:
receive, via the communication interface coupled with the computing network, a request from a device associated with a customer, the request comprising information for a product and the customer;
receive, periodically or semi-periodically, location information associated with the customer prior to training a trained model, the location information for use in training a model to produce the trained model;
apply the trained model to the information associated with the product and the customer of the request to determine one or more physical locations of a product provider that are near the customer at various times of the day and a convenience probability for each of the one or more physical locations of a product provider to provide the product;
generate a code associated with the request;
apply a hashing algorithm to the code to generate a hash value to send to the device associated with the customer and to a system associated with the product provider;
send, via the communication interface, first information to the device associated with the customer, the first information to include an indication of at least one of the one or more physical locations and the hash value of the code, wherein the indication is based on the convenience probability;
perform a lookup in a data structure, the lookup being based on the indication of the at least one physical location, to determine the system associated with the product provider to pick up the product; and
send second information to the system associated with the product provider, the second information to identify the product and the hash value of the code, wherein the system is to use the second information to enable access to the product when an instance of the hash value of the code is provided to the system.
2. The apparatus of claim 1 , wherein the information of the request comprises:
product information to identify the product to purchase,
customer information to identify the customer associated with the request, and
location information associated with the customer.
3. The apparatus of claim 2 , comprising:
storage,
wherein the instructions further cause the processor circuit to:
determine the trained model to apply to the information of the request based on the customer information to identify the customer associated with the request; and
retrieve the trained model from the storage.
4. The apparatus of claim 1 , wherein the instructions further cause the processor circuit to:
predict a location area of the customer when applying the trained model to the information of the request;
determine the one or more physical locations of the product provider within the location area.
5. The apparatus of claim 4 , wherein the instructions further cause the processor circuit to:
determine a physical location of the one or more physical locations of the product provider predicted to be closest to the customer based on the information in the request, wherein the first information to include the physical location of the product provider; and
send the second information to the system of the product provider at the physical location.
6. The apparatus of claim 4 , wherein the instructions further cause the processor circuit to:
send an indication of each of the one or more physical locations to the device associated with the customer;
receive an indication of a selection a physical location of the one or more physical locations; and
send the second information to the system of the product provider at the physical location.
7. The apparatus of claim 1 , wherein the instructions further cause the processor circuit to:
generate the trained model for the customer based on the location information.
8. The apparatus of claim 1 , wherein the instructions further the processor circuit to:
receive, periodically or semi-periodically, location information associated with the customer subsequent to training the trained model; and
retrain the trained model for the customer based on the location information associated with the customer.
9. The apparatus of claim 1 , wherein the code is one of an alphanumeric code, barcode image, or digital audio code; and
wherein the indication of the first information includes a digital link which when interacted with by a user of the device, causes a map application to open on the device with directions to the at least one of the one or more physical locations.
10. A computer-implemented method, comprising:
receiving, via a communication interface coupled with a computing network, a request from a device associated with a customer, the request comprising information for a product and the customer;
receiving, periodically or semi-periodically, location information associated with the customer prior to training a trained model, the location information for use in training a model to produce the trained model;
applying the trained model to the information associated with the product and the customer of the request to determine one or more physical locations of a product provider that are near the customer at various times of a day and a convenience probability for each of the one or more physical locations of a product provider to provide the product;
generating a code associated with the request, the code including a digital audio code;
encrypting the code for sending to the device associated with the customer and to a system associated with the product provider;
sending first information to the device associated with the customer, the first information to include an indication of at least one of the one or more physical locations and the code, wherein the indication is based on the convenience probability, wherein the digital audio code is configured to be played back via a speaker of the device associated with the customer to the system for verification;
performing a lookup in a data structure, the lookup being based on the indication of the at least one physical location, to determine the system associated with the product provider to pick up the product; and
sending second information to the system associated with the product provider, wherein the second information is to identify the product and to be compared with the digital audio code, wherein the system is to use the second information to enable access to the product in response to an instance of the digital audio code being provided to the system and corresponding to the digital audio code received by the system in the second information.
11. The computer-implemented method of claim 10 , wherein the information of the request comprises:
product information to identify the product to purchase,
customer information to identify the customer associated with the request, and
location information associated with the customer.
12. The computer-implemented method of claim 11 , comprising:
determining the trained model to apply to the information of the request based on the customer information to identify the customer associated with the request; and
retrieving the trained model from a storage device.
13. The computer-implemented method of claim 10 , comprising:
predicting a location area of the customer when applying the trained model to the information of the request;
determining the one or more physical locations of the product provider within the location area.
14. The computer-implemented method of claim 13 , comprising:
determining a physical location of the one or more physical locations of the product provider predicted to have a highest convenience probability, wherein the first information to include the physical location of the product provider; and
sending the second information to the system of the product provider at the physical location.
15. The computer-implemented method of claim 13 , comprising:
sending an indication of each of the one or more physical locations to the device associated with the customer;
receiving an indication of a selection a physical location of the one or more physical locations; and
sending the second information to the system of the product provider at the physical location.
16. The computer-implemented method of claim 10 , comprising:
generating the trained model for the customer based on the location information.
17. The computer-implemented method of claim 10 , comprising:
receiving, periodically or semi-periodically, location information associated with the customer subsequent to training the trained model; and
retraining the trained model for the customer based on the location information associated with the customer.
18. The computer-implemented method of claim 10 , wherein the indication of the first information includes a digital link which when interacted with by a user of the device, causes a map application to open on the device with directions to the at least one of the one or more physical locations.
19. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to:
receive, via a communication interface coupled with a computing network, a request from a device associated with a customer, the request comprising information for a product and the customer;
receive, periodically or semi-periodically, location information associated with the customer prior to training a trained model, the location information for use in training a model to produce the trained model;
apply the trained model to the information associated with the product and the customer of the request to determine one or more physical locations of a product provider that are near the customer at various times of a day and a convenience probability for each of the one or more physical locations of a product provider to provide the product;
generate a code associated with the request;
apply a hashing algorithm to the code to generate a hash value of the code to send to the device associated with the customer and to a system associated with the product provider;
send first information to the device associated with the customer, the first information to include an indication of at least one of the one or more physical locations and the hash value of the code, wherein the indication is based on the convenience probability;
perform a lookup in a data structure, the lookup being based on the indication of the at least one physical location, to determine the system associated with the product provider to pick up the product; and
send second information to the system associated with the product provider, the second information to identify the product and the hash value of the code, wherein the system is to use the second information to enable access to the product when an instance of the hash value of the code is provided to the system.
20. The computer-readable storage medium of claim 19 , comprising:
predict a location area of the customer when applying the trained model to the information of the request;
determine the one or more physical locations of the product provider within the location area.