System and method for content creation tool for use with shoppable content data
In accordance with an embodiment, described herein is a system and method for providing a content creation tool for use with shoppable content data. A content management system, such as, for example, an Oracle Content and Experience Cloud (OCE) environment, enables the creation of shoppable content that provides a purchasing opportunity directly from the content itself. The system can include, support, or operate in accordance with a content creation tool, that can incorporate aspects of artificial intelligence, for use with shoppable content data, including, for example, performing automatic detection of objects in an image; and automatic discovery of products to be mapped with the shoppable objects or shoppable content; for use in publishing the shoppable content in mobile application, web, or other document formats.
1. A system for providing a content creation tool, including object detection within digital content or images, for use with shoppable content, comprising:
a content management system running on a computer comprising a processor and memory;
a content creation tool running within the content management system, wherein the content creation tool operates to:
automatically detect shoppable objects within a digital content based upon an object detection model trained on data associated with a user, the data associated with the user comprising images of products associated with the user,
determine, via an application programming interface provided at the content management system that enables communication and data exchange between the content management system and a commerce provider repository, products at the commerce provider repository of the user to be mapped to the automatically detected shoppable objects, the commerce provider repository being provided at another computer comprising another processor and another memory, and
create objects for use in publishing shoppable content in websites or other documents;
wherein the content creation tool, based upon automatically detecting a plurality of shoppable objects mapped to a plurality of products in a digital image, said automatically detecting the plurality of shoppable objects being based upon the object detection model trained on data associated with the user, determines a confidence score for each detected shoppable object and, upon each confidence score surpassing a threshold value, generates and displays a cropped bounding box around each of the automatically detected shoppable objects in the digital image, wherein the cropped bounding boxes are utilized in distinguishing the automatically detected shoppable objects from other portions of the digital image that are not automatically detected as shoppable objects based upon the object detection model trained on data associated with the user, and linking, via the application programming interface and to determine the availability for purchase thereof, products from the commerce provider repository with the plurality of shoppable objects detected in the digital image.
2. The system of claim 1 , wherein the system automatically identifies products within each of one or more digital images using an object detection model trained on customer domain data associated with the commerce provider.
3. The system of claim 1 wherein the system generates feature vectors stored within a vector space data structure, corresponding to the shoppable objects detected in the digital image, based on image features identified within the cropped bounding box of the detected products.
4. The system of claim 1 , wherein the system associates shoppable objects detected within digital images into vectors within a multi-dimensional vector space, and compares subsequently-received input digital content with product images, to find relevant product options within the products associated with the commerce provider.
5. The system of claim 4 , wherein the content management system generates one or more image metadata attributes or tags based on products described within the content management system for each of the digital images.
6. The system of claim 5 , wherein metadata information captured in the content management system is used to enrich original content, which metadata information is made available for search and discovery, including smart searching and sorting.
7. The system of claim 1 , wherein the system includes a shoppable content JavaScript container or widget that generates image hyperlinks to image maps, including one or more clickable areas within the image, wherein each image map can link a shoppable object in the image that allows a user to add associated products directly to a user's shopping cart from a web page.
8. The system of claim 1 ,
wherein the content management system, via the server API, operates to request the commerce provider system to send data describing or defining a set of products offered for sale by the commerce provider; and wherein the content management system receives a list of the products, along with the data describing or defining the list of products.
9. The system of claim 1 , wherein the system is provided as part of a cloud computing environment or is accessed through one or more cloud services.
10. A method for providing a content creation tool, including object detection within digital content or images, for use with shoppable content, comprising:
providing, at a computer comprising a microprocessor and a memory, a content management system; and
running a content creation tool within the content management system, wherein the content creation tool operates to:
automatically detect shoppable objects within a digital content based upon an object detection model trained on data associated with a user, the data associated with the user comprising images of products associated with the user,
determine, via an application programming interface provided at the content management system that enables communication and data exchange between the content management system and a commerce provider repository, products at the commerce provider repository of the user to be mapped to the automatically detected shoppable objects, the commerce provider repository being provided at another computer comprising another processor and another memory, and
create objects for use in publishing shoppable content in websites or other documents;
wherein the content creation tool, based upon automatically detecting the plurality of shoppable objects mapped to a plurality of products in a digital image, said automatically detecting a plurality of products being based upon the object detection model trained on data associated with the user, determines a confidence score for each detected shoppable object and, upon each confidence score surpassing a threshold value, generates and displays a cropped bounding box around each of the automatically detected shoppable objects in the digital image, wherein the cropped bounding boxes are utilized in distinguishing the automatically detected shoppable objects from other portions of the digital image that are not automatically detected as shoppable objects based upon the object detection model trained on data associated with the user, the data comprising images of products associated with the user, and linking, via the application programming interface and to determine the availability for purchase thereof, products from the commerce provider repository with the shoppable objects detected in the digital image.
11. The method of claim 10 , further comprising automatically identifying products within each of one or more digital images using an object detection model trained on customer domain data associated with the commerce provider.
12. The method of claim 10 , further comprising generating feature vectors stored within a vector space data structure, corresponding to the shoppable objects detected in the digital image, based on image features identified within the cropped bounding box of the detected products.
13. The method of claim 10 , further comprising associating shoppable objects detected within digital images into vectors within a multi-dimensional vector space, and compares subsequently-received input digital content with product images, to find relevant product options within the products associated with the commerce provider.
14. The method of claim 10 , wherein the content management system generates one or more image metadata attributes or tags based on products described within the content management system for each of the digital images.
15. The method of claim 10 wherein metadata information captured in the content management system is used to enrich original content, which metadata information is made available for search and discovery, including smart searching and sorting.
16. The method of claim 10 , wherein the system includes a shoppable content JavaScript container or widget that generates image hyperlinks to image maps, including one or more clickable areas within the image, wherein each image map can link a shoppable object in the image that allows a user to add associated products directly to a user's shopping cart from a web page.
17. The method of claim 10 , wherein a server API operates to provide access by the content management system to data stored at a commerce provider system;
wherein the content management system, via the server API, operates to request the commerce provider system to send data describing or defining a set of products offered for sale by the commerce provider; and wherein the content management system receives a list of the products, along with the data describing or defining the list of products.
18. A non-transitory computer readable storage medium having instructions thereon, which when read and executed by a computer cause the computer to perform steps comprising:
providing, at a computer comprising a microprocessor and a memory, a content management system; and
running a content creation tool within the content management system, wherein the content creation tool operates to:
automatically detect shoppable objects within a digital content based upon an object detection model trained on data associated with a user, the data associated with the user comprising images of products associated with the user,
determine, via an application programming interface provided at the content management system that enables communication and data exchange between the content management system and a commerce provider repository, products at the commerce provider repository of the user to be mapped to the automatically detected shoppable objects, the commerce provider repository being provided at another computer comprising another processor and another memory, and
create objects for use in publishing shoppable content in websites or other documents;
wherein the content creation tool, based upon automatically detecting the plurality of shoppable objects mapped to a plurality of products in a digital image, said automatically detecting a plurality of products being based upon the object detection model trained on data associated with the user, determines a confidence score for each detected shoppable object and, upon each confidence score surpassing a threshold value, generates and displays a cropped bounding box around each of the automatically detected shoppable objects in the digital image, wherein the cropped bounding boxes are utilized in distinguishing the automatically detected shoppable objects from other portions of the digital image that are not automatically detected as shoppable objects based upon the object detection model trained on data associated with the user, the data comprising images of products associated with the user, and linking, via the application programming interface and to determine the availability for purchase thereof, products from the commerce provider repository with the shoppable objects detected in the digital image.