Image-based search and recommendation techniques implemented via artificial intelligence
View Patent ↗Methods, apparatus, and processor-readable storage media for image-based search and recommendation techniques implemented via artificial intelligence are provided herein. An example computer-implemented method includes detecting, in response to a user search query comprising an image, an object in the image by applying one or more artificial intelligence algorithms to the image; determining one or more features of the object by applying the one or more artificial intelligence algorithms to one or more portions of the image containing at least a portion of the object; identifying the detected object as a particular enterprise offering based at least in part on the one or more determined features of the object; determining one or more additional enterprise offerings based at least in part on the identified enterprise offering; outputting, to the user, information pertaining to the identified enterprise offering and information pertaining to the one or more additional enterprise offerings.
1. A computer-implemented method comprising:
detecting, in response to a user search query comprising an image, an object in the image by applying one or more artificial intelligence algorithms to the image;
determining one or more features of the object by applying the one or more artificial intelligence algorithms to one or more portions of the image containing at least a portion of the object, wherein applying the one or more artificial intelligence algorithms to one or more portions of the image containing at least a portion of the object comprises:
extracting the one or more features of the object from the one or more portions of the image by processing the one or more portions of the image using at least one convolutional neural network function, wherein using the at least one convolutional neural network function comprises converting the one or more portions of the image from at least one block of multiple pixels to at least one single pixel using at least one rectified linear activation function;
identifying the detected object as a particular enterprise offering based at least in part on the one or more determined features of the object;
determining one or more additional enterprise offerings based at least in part on the identified enterprise offering; and
outputting, to the user, information pertaining to the identified enterprise offering and information pertaining to the one or more additional enterprise offerings;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The computer-implemented method of claim 1 , wherein the one or more artificial intelligence algorithms compare the image to one or more images of known enterprise offerings stored in a database.
3. The computer-implemented method of claim 2 , wherein comparing comprises comparing one or more colors of the image to one or more colors of the one or more images of known enterprise offerings stored in the database.
4. The computer-implemented method of claim 2 , wherein comparing comprises comparing one or more shapes detected in the image to one or more shapes detected in the one or more images of known enterprise offerings stored in the database.
5. The computer-implemented method of claim 2 , wherein comparing comprises comparing one or more one or more visual patterns of the image to one or more visual patterns of the one or more images of known enterprise offerings stored in the database.
6. The computer-implemented method of claim 5 , wherein the one or more visual patterns comprises a distance between two or more components within the image.
7. The computer-implemented method of claim 1 , wherein the image is a two-dimensional image, and wherein the one or more artificial intelligence algorithms compare the two-dimensional image to one or more three-dimensional images of known enterprise offerings stored in a database.
8. The computer-implemented method of claim 1 , further comprising:
determining a confidence score for the identifying of the detected object as a particular enterprise offering.
9. The computer-implemented method of claim 1 , further comprising:
training the one or more artificial intelligence algorithms based at least in part on the image and the identified enterprise offering.
10. The computer-implemented method of claim 1 , wherein determining the one or more additional enterprise offerings is further based at least in part on one or more similarities between the identified enterprise offering and the one or more additional enterprise offerings.
11. The computer-implemented method of claim 1 , wherein determining the one or more additional enterprise offerings is further based at least in part on one or more historical purchase patterns of the user.
12. The computer-implemented method of claim 1 , wherein determining the one or more additional enterprise offerings is further based at least in part on one or more historical purchase patterns of one or more additional users.
13. The computer-implemented method of claim 1 , wherein the information pertaining to the identified enterprise offering comprises a hyperlink to an electronic commerce website of the enterprise wherein the identified enterprise offering is offered for purchase.
14. The computer-implemented method of claim 1 , wherein the information pertaining to the one or more additional enterprise offerings comprises one or more hyperlinks to one or more electronic commerce websites of the enterprise wherein the one or more additional enterprise offerings are offered for purchase.
15. A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device:
to detect, in response to a user search query comprising an image, an object in the image by applying one or more artificial intelligence algorithms to the image;
to determine one or more features of the object by applying the one or more artificial intelligence algorithms to one or more portions of the image containing at least a portion of the object, wherein applying the one or more artificial intelligence algorithms to one or more portions of the image containing at least a portion of the object comprises:
extracting the one or more features of the object from the one or more portions of the image by processing the one or more portions of the image using at least one convolutional neural network function, wherein using the at least one convolutional neural network function comprises converting the one or more portions of the image from at least one block of multiple pixels to at least one single pixel using at least one rectified linear activation function;
to identify the detected object as a particular enterprise offering based at least in part on the one or more determined features of the object;
to determine one or more additional enterprise offerings based at least in part on the identified enterprise offering; and
to output, to the user, information pertaining to the identified enterprise offering and information pertaining to the one or more additional enterprise offerings.
16. The non-transitory processor-readable storage medium of claim 15 , wherein the one or more artificial intelligence algorithms compare the image to one or more images of known enterprise offerings stored in a database.
17. The non-transitory processor-readable storage medium of claim 15 , wherein the image is a two-dimensional image, and wherein the one or more artificial intelligence algorithms compare the two-dimensional image to one or more three-dimensional images of known enterprise offerings stored in a database.
18. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to detect, in response to a user search query comprising an image, an object in the image by applying one or more artificial intelligence algorithms to the image;
to determine one or more features of the object by applying the one or more artificial intelligence algorithms to one or more portions of the image containing at least a portion of the object, wherein applying the one or more artificial intelligence algorithms to one or more portions of the image containing at least a portion of the object comprises:
extracting the one or more features of the object from the one or more portions of the image by processing the one or more portions of the image using at least one convolutional neural network function, wherein using the at least one convolutional neural network function comprises converting the one or more portions of the image from at least one block of multiple pixels to at least one single pixel using at least one rectified linear activation function;
to identify the detected object as a particular enterprise offering based at least in part on the one or more determined features of the object;
to determine one or more additional enterprise offerings based at least in part on the identified enterprise offering; and
to output, to the user, information pertaining to the identified enterprise offering and information pertaining to the one or more additional enterprise offerings.
19. The apparatus of claim 18 , wherein the one or more artificial intelligence algorithms compare the image to one or more images of known enterprise offerings stored in a database.
20. The apparatus of claim 18 , wherein the image is a two-dimensional image, and wherein the one or more artificial intelligence algorithms compare the two-dimensional image to one or more three-dimensional images of known enterprise offerings stored in a database.