Systems and methods for providing product image recommendations

Patent metadata

Field	Value
Publication number	US-2021125251-A1
Application number	US-201916662211-A
Country	US
Kind code	A1
Filing date	Oct 24, 2019
Priority date	Oct 24, 2019
Publication date	Apr 29, 2021
Grant date	—

Abstract

For products that are sold online, the manner in which a product is displayed in an image can affect sales of the product. Embodiments of the present disclosure relate to computer-implemented systems and methods to provide a user with recommendations when generating an image of a product. A method includes obtaining a product image and determining parameters of the product image. A recommendation for modifying the product image is then generated using a model to relate these parameters to market success of the product image. The recommendation is displayed on the user device, and a user can potentially improve subsequent product images by following the recommendation.

First claim

1 . A computer-implemented method comprising:
storing, in memory, a model to relate parameters of a product image to market success of the product image; obtaining a particular product image, the particular product image having been generated by a user device; determining particular parameters of the particular product image; generating, using the model and the particular parameters, a recommendation for modifying the particular product image; and instructing the user device to display the recommendation on the user device.

2 . The computer-implemented method of claim 1 , wherein:
the model comprises a look-up table comprising desired parameters, and generating the recommendation comprises comparing the particular parameters to the desired parameters.

3 . The computer-implemented method of claim 1 , wherein:
the model is implemented using a machine learning algorithm, and generating the recommendation comprises:
inputting the particular parameters into the machine learning algorithm; and
calculating, using the machine learning algorithm, a prediction of market success of the particular product image, wherein the recommendation is associated with an improvement to the prediction of the market success of the particular product image.

4 . The computer-implemented method of claim 3 , wherein:
the machine learning algorithm comprises a neural network, and generating the recommendation further comprises:
determining a modification to the neural network that produces the improvement to the prediction of the market success of the particular product image; and
generating the recommendation based on the modification to the neural network.

5 . The computer-implemented method of claim 1 , wherein obtaining the particular product image comprises receiving the particular product image from the user device.

6 . The computer-implemented method of claim 1 , wherein instructing the user device to display the recommendation comprises transmitting the recommendation to the user device.

7 . The computer-implemented method of claim 1 , wherein determining the particular parameters of the particular product image comprises performing image analysis on the particular product image.

8 . The computer-implemented method of claim 1 , further comprising:
obtaining a description of a product displayed in the particular product image, wherein determining the particular parameters of the particular product image comprises determining a parameter of the particular product image based on the description of the product.

9 . The computer-implemented method of claim 1 , further comprising:
obtaining data indicating a capability of the user device, wherein determining the particular parameters of the particular product image comprises determining a parameter of the particular product image based on the capability of the user device.

10 . The computer-implemented method of claim 1 , wherein generating the recommendation comprises generating the recommendation to improve market success of the particular product image.

11 . The computer-implemented method of claim 1 , wherein generating the recommendation comprises generating an instruction for a user of the user device.

12 . The computer-implemented method of claim 1 , further comprising:
instructing, based on the recommendation, the user device to adjust a setting on the user device.

13 . The computer-implemented method of claim 1 , wherein instructing the user device to display the recommendation comprises instructing the user device to display the recommendation while the particular product image is displayed on the user device.

14 . The computer-implemented method of claim 1 , wherein:
the particular product image is a first product image, and instructing the user device to display the recommendation comprises instructing the user device to display the recommendation while a second product image is displayed on the user device, the second product image having been captured by the user device.

15 . The computer-implemented method of claim 1 , wherein the particular product image is a first product image and the particular parameters are a first plurality of parameters, the method further comprising:
obtaining a second product image for a same product as the first product image, the second product image having been captured by the user device; determining a second plurality of parameters of the second product image; determining, using the model and the second plurality of parameters, that the second product image is suitable; and instructing the user device to display, on the user device, an indication that the second product image is suitable.

16 . A system comprising:
a memory to store a model relating parameters of a product image to market success of the product image; and a processor to:
obtain a particular product image, the particular product image having been generated by a user device,
determine particular parameters of the particular product image,
generate, using the model and the particular parameters, a recommendation for modifying the particular product image, and
instruct the user device to display the recommendation on the user device.

17 . The system of claim 16 , wherein:
the model comprises a look-up table comprising desired parameters, and the recommendation is based on a comparison of the particular parameters and the desired parameters.

18 . The system of claim 16 , wherein:
the model is implemented using a machine learning algorithm, and the processor is further to:
input the particular parameters into the machine learning algorithm; and
calculate, using the machine learning algorithm, a prediction of market success of the particular product image, wherein the recommendation is associated with an improvement to the prediction of the market success of the particular product image.

19 . The system of claim 18 , wherein:
the machine learning algorithm comprises a neural network, and the processor is further to:
determine a modification to the neural network that produces the improvement to the prediction of the market success of the particular product image; and
generate the recommendation based on the modification to the neural network.

20 . The system of claim 16 , wherein the processor is further to receive the particular product image from the user device.

21 . The system of claim 16 , wherein the processor is further to transmit the recommendation to the user device.

22 . The system of claim 16 , wherein the processor is further to perform image analysis on the particular product image to determine the particular parameters.

23 . The system of claim 16 , wherein the processor is further to:
obtain a description of a product displayed in the particular product image, and determine a parameter of the particular product image based on the description of the product.

24 . The system of claim 16 , wherein the processor is further to:
obtain data indicating a capability of the user device, and determine a parameter of the particular product image based on the capability of the user device.

25 . The system of claim 16 , wherein the recommendation is to improve market success of the particular product image.

26 . The system of claim 16 , wherein the recommendation comprises an instruction for a user of the user device.

27 .

Assignees

• Shopify Inc

Inventors

• D'Souza Franklyn
• Wade Jonathan
• Haapoja Juho Mikko

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/084

  Backpropagation, e.g. using gradient descent · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/08

  Learning methods · CPC title