Method, device, and computer program product for searching and displaying product images

• US 10,521,855 B2
• Filed: 01/07/2015
• Issued: 12/31/2019
• Est. Priority Date: 01/09/2014
• Status: Active Grant

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Cao, Yang
• Primary Examiner(s): Smith, Jeffrey A.
• Assistant Examiner(s): Wood, Allison G
• Application Number:
  US14/591,360
• Publication Number:
  US 20150193863A1
• Time in Patent Office: 1,819 Days
• Field of Search: 705 261- 272
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06Q 30/0623 Item investigation
• CPC Class Codes: G06Q 30/0629 for generating comparisons
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers

Abstract

Embodiments of the present application relate to a method and system searching for and displaying product images to a user. The method includes acquiring an initial product image set for a user, wherein the initial product image set includes a product image corresponding to a product purchased by the user, a product image characterized as interesting by the user, a product image bookmarked by the user, or a combination thereof; searching for product images that are similar in one or more characteristics to initial product images in the initial product image set; and sending found product images to be displayed to the user.

Claims

1. A method for searching for and displaying product images, the method comprising:

obtaining, by one or more processors, a product search query;

acquiring, by one or more processors, an initial product image set for a user based at least in part on the product search query and historical information pertaining to the user wherein the initial product image set includes a product image corresponding to a product purchased by the user, a product image characterized as interesting by the user, a product image bookmarked by the user, or a combination thereof;

searching, by one or more processors, for a second product image set for the user, wherein the searching for the second product image set is based at least in part on the initial product image set, and the second product image set comprises one or more product images that are similar in one or more characteristics to the initial product images in the initial product image set;

sending, by one or more processors, the second product image set to be displayed to the user;

receiving, by one or more processors, user input with respect to a selection of an image indicated as interesting by the user in the second product image set;

searching, by one or more processors, for a third product image set for the user, wherein the searching for the third product image set is based at least in part on a set of images comprised in the second product image set and the selection of the image indicated as interesting by the user in the second product image set, and the third product image set comprises one or more images that are similar in one or more characteristics to the set of images comprised in the second product image set, wherein the initial product image set is not directly used in connection with searching for the third product image set; and

sending, by one or more processors, the third product image set to be displayed to the user.

2. The method as described in claim 1, wherein the one or more characteristics corresponds to a color, a style, a shape, a texture, or a combination thereof.

3. The method as described in claim 1, wherein the searching for product images that are similar in one or more characteristics to the initial product images in the initial product image set comprises:

specifying the initial product images in the initial product image set as current initial product images;

searching for product images that are similar to the current initial product images in one or more characteristics, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to a preset similarity threshold value;

obtaining a search product image set, wherein the search product image set comprises found product images and similarities of the found product images to the current initial product images;

selecting product images for a next round of search from the search product image set, wherein product images for the next round of search include product images that are not characterized as uninteresting to the user and that have not been regarded as current initial product images;

adding the selected next round search product images to a display product image set;

specifying the selected next round search product images as the current initial product images; and

searching for product images that are similar in one or more characteristics to the current initial product images, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value;

wherein the sending of the found product images to the user comprises sending one or more of the product images in the display product image set to the user.

4. The method as described in claim 3, wherein searching for product images that are similar in one or more characteristics to the current initial product images, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value and the obtaining of the search product image set comprises:

searching for product images that are similar in color, style, or texture to the current initial product images wherein a product image that is similar in color, style, or texture to the current initial product images has a similarity value that is greater than or equal to the preset similarity threshold value and obtaining the search product image set.

5. The method of claim 3, wherein searching for product images that are similar in one or more characteristics to the current initial product images, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value and the obtaining of the search product image set comprises:

using identifying numbers of the current initial product images as a basis for searching a similar product image cache library for product images that are similar in one or more characteristics to the current initial product images, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value and obtaining the search product image set, wherein the similar product image cache library stores previously searched and found information on product images that are similar in one or more characteristics.

6. The method as described in claim 3, further comprising:

determining one or more of whether a search layer number of the current initial product images is less than a preset layer quantity threshold value and whether a number of product images included in the display product image set is less than a preset image quantity threshold value; and

in response to determining that the search layer number of the current initial product images is less than the preset layer quantity threshold value or the number of product images included in the display product image set is less than the preset image quantity threshold value, searching for product images that are similar to the current initial product images in one or more characteristics, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value.

7. The method as described in claim 3, wherein the sending the one or more product images in the display product image set to the user comprises:

selecting a preset number of product images sequentially in turn from among product images corresponding to each the initial product image in the display product image set;

generating a product image list, wherein the product images corresponding to each of the initial product images refer to a series of product images obtained by searching each of the initial product images as a direct search ontological object or an indirect search ontological object; and

sending the product images in the product image list to the user.

8. The method of claim 1, wherein the searching for the third product image set comprises:

iteratively searching for a set of product images based on an immediately previous set of product images obtained in connection with the search for the third product image set.

9. The method of claim 8, wherein the iteratively searching is performed until a number of iterative searches is greater than a preset search threshold or a number of searched images is greater than a preset image quantity threshold.

10. The method of claim 1, wherein the second product image set is further searched based at least in part on whether the user has previously identified an image as uninteresting.

11. The method of claim 1, wherein the third product image set excludes a subset of images of the second product image set that are determined to be deemed as uninteresting by the user.

12. The method of claim 11, wherein the user input with respect to the second product image set is indicative of the subset of images of the second product image set that are determined to be deemed as uninteresting by the user.

13. The method of claim 1, wherein the initial product image set comprises direct search ontological objects with respect to the product search query, and the second product image set and the third product image set comprise indirect search ontological objects with respect to the initial product image set.

14. A device for searching for and displaying product images, the device comprising:

one or more processors configured to;

obtain a product search query;

acquire an initial product image set for a user based at least in part on the product search query and historical information pertaining to the user wherein the initial product image set includes a product image corresponding to a product purchased by the user, a product image characterized as interesting by the user, a product image bookmarked by the user, or a combination thereof search for a second product image set for the user, wherein the searching for the second product image set is based at least in part on the initial product image set, wherein the second product image set comprises one or more product images that are similar in one or more characteristics to the initial product images in the initial product image set;

send the second product image set to be displayed to the user;

receive user input with respect to a selection of an image indicated as interesting by the user in the second product image set;

search for a third product image set for the user, wherein the searching for the third product image set is based at least in part on a set of images comprised in the second product image set and the selection the image indicated as interesting by the user in the second product image set, and the third product image set comprises one or more images that are similar in one or more characteristics to the set of images comprised in the second product image set, wherein the initial product image set is not directly used in connection with searching for the third product image set; and

send the third product image set to be displayed to the user

one or more memories coupled to the one or more processors, configured to provide the one or more processors with instructions.

15. The device as described in claim 14, wherein the one or more characteristics corresponds to a color, a style, a shape, a texture, or a combination thereof.

16. The device as described in claim 14, wherein the one or more processors are further configured to:

specify the initial product images in the initial product image set as current initial product images;

search for product images that are similar to the current initial product images in one or more characteristics, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to a preset similarity threshold value;

obtain a search product image set, wherein the search product image set comprises found product images and similarities of the found product images to the current initial product images;

select product images for a next of search from the search product image set, wherein product images for the next of search include product images that are not characterized as uninteresting to the user and that have not been regarded as current initial product images;

add the selected next round search product images to a display product image set;

specify the selected next round search product images as the current initial product images; and

search for product images that are similar in one or more characteristics to the current initial product images, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value,

wherein the device comprises a display unit that is configured to send the product images in the display product image set to be displayed to the user.

17. The device as described in claim 16,

wherein to search for product images that are similar in one or more characteristics to the current initial product images, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value and the obtaining of the search product image set comprises:

searching for product images that are similar in color, style, or texture to the current initial product images wherein a product image that is similar in color, style, or texture to the current initial product images has a similarity value that is greater than or equal to the preset similarity threshold value and obtaining the search product image set.

18. The device as described in claim 16, wherein to search for product images that are similar in one or more characteristics to the current initial product images, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value and the obtaining of the search product image set comprises:

use identifying numbers of the current initial product images as a basis for searching a similar product image cache library for product images that are similar in color, style, or texture to the current initial product images, wherein a product image that is similar in color, style, or texture to the current initial product images has a similarity value is greater than or equal to the preset similarity threshold value and obtaining the search product image set, wherein the similar product image cache library stores previously searched and found information on product images that are similar in color, style, texture, or a combination thereof.

19. The device as described in claim 16, wherein one or more processors are further configured to:

determine one or more of whether a search layer number of the current initial product images is less than a preset layer quantity threshold value and whether a number of product images included in the display product image set is less than a preset image quantity threshold value; and

in response to determining that the search layer number of the current initial product images is less than the preset layer quantity threshold value or the number of product images included in the display product image set is less than the preset image quantity threshold value, search for product images that are similar in one or more characteristics to the current initial product images, wherein a product image that is similar to the current initial product images in one or more characteristics has a similarity value that is greater than or equal to the preset similarity threshold value.

20. The device as described in claim 16, wherein the one or more processors are further configured to:

select a preset number of product images sequentially in turn from among product images corresponding to each of the initial product images in the display product image set; and

generate a product image list, wherein the product images corresponding to each of the initial product images refer to a series of product images obtained by searching each of the initial product images as a direct search ontological object or an indirect search ontological object; and

send the product images in the product image list to be displayed to the user.

21. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

obtaining, by one or more processors, a product search query;

acquiring, by one or more processors, an initial product image set for a user based at least in part on the product search query and historical information pertaining to the user wherein the initial product image set includes a product image corresponding to a product purchased by the user, a product image characterized as interesting by the user, a product image bookmarked by the user, or a combination thereof;

searching, by one or more processors, for a second product image set for the user, wherein the searching for the second product image set is based at least in part on the initial product image set, wherein the second product image set comprises one or more product images that are similar in one or more characteristics to the initial product images in the initial product image set, wherein the initial product image set is not directly used in connection with searching for the third product image set;

sending, by one or more processors, the second product image set to be displayed to the user;

receiving, by one or more processors, user input with respect to a selection of an image indicated as interesting by the user in the second product image set;

searching, by one or more processors, for a third product image set for the user, wherein the searching for the third product image set is based at least in part on a set of images comprised in the second product image set and the selection of the image indicated as interesting by the user in the second product image set, and the third product image set comprises one or more images that are similar in one or more characteristics to the set of images comprised in the second product image set; and

sending, by one or more processors, the third product image set to be displayed to the user.