Generation of product videos using machine learning
A computer-implemented method, a computer system and a computer program product automatically generate product videos based on requested feature sets in stored data. the method includes acquiring a plurality of product features from a server, where each product feature in the plurality of product features is associated with data selected from a group consisting of: text data, audio data, and image data. The method also includes receiving a request for a product video, where a product in the product video comprises a set of product features in the plurality of product features. The method further includes identifying the data associated with each product feature in the set of product features for the request. Lastly, the method includes generating the product video based on identified data for the product.
1 . A computer-implemented method for automated generation of adaptive instructional product videos to indicate how a product is used based on requested feature sets in stored data, the method comprising:
acquiring a plurality of product features from a server, wherein each product feature in the plurality of product features is associated with data selected from a group consisting of: text data, audio data, and image data;
receiving a request for an instructional product video, wherein a product in the instructional product video comprises a set of current product features in the plurality of product features, the request for the product video including a request to view instructions to utilize a specific version of a manufacturer's product or to view a specific product feature;
identifying the data associated with each current product feature in the set of product features for the request for the instructional product video;
generating the instructional product video using a generative adversarial neural network (GAN) based on identified data for the product, the instructional product video including frames showing the requested version of the manufacturer's product or the specific product feature;
acquiring a plurality of updated or revised product features from the server, the updated or revised product features associated with an update to the specific version of the manufacturer's product or the specific product feature; and
generating an updated instructional product video, the updated instructional product video including frames showing the updated or revised product feature associated with the update to the specific version of the manufacturer's product or the specific product feature and instructions how to use the updated specific version of the manufacturer's product or the updated specific product feature.
2 . The computer-implemented method of claim 1 , further comprising:
identifying a product version for each product feature in the plurality of product features; and
generating a template video for the product version from the data associated with each product feature having the identified product version.
3 . The computer-implemented method of claim 2 , further comprising:
determining that a product feature in the set of product features for the request does not include the product version for the template video;
identifying a change to the template video based on the product feature; and
modifying the template video based on an identified change to the template video.
4 . The computer-implemented method of claim 3 , wherein the modifying the template video includes removing a video frame associated with the product feature from the template video, wherein the product feature is determined to be an obsolete product feature.
5 . The computer-implemented method of claim 3 , wherein a machine learning model that predicts video context based on content in a video is used to identify the change to the template video.
6 . The computer-implemented method of claim 2 , further comprising storing the plurality of product features in a product feature database, wherein the product feature database associates each product feature in the plurality of product features with the data of a respective product feature and the product version for the respective product feature.
7 . A computer system for automated generation of adaptive instructional product videos to indicate how a product is used based on requested feature sets in stored data, the computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
acquiring a plurality of product features from a server, wherein each product feature in the plurality of product features is associated with data selected from a group consisting of: text data, audio data, and image data;
receiving a request for an instructional product video, wherein a product in the instructional product video comprises a set of current product features in the plurality of product features, the request for the product video including a request to view instructions to utilize a specific version of a manufacturer's product or to view a specific product feature;
identifying the data associated with each current product feature in the set of product features for the request for the instructional product video;
generating the instructional product video using a generative adversarial neural network (GAN) based on identified data for the product, the instructional product video including frames showing the requested version of the manufacturer's product or the specific product feature;
acquiring a plurality of updated or revised product features from the server, the updated or revised product features associated with an update to the specific version of the manufacturer's product or the specific product feature; and
generating an updated instructional product video, the updated instructional product video including frames showing the updated or revised product feature associated with the update to the specific version of the manufacturer's product or the specific product feature and instructions how to use the updated specific version of the manufacturer's product or the updated specific product feature.
8 . The computer system of claim 7 , further comprising:
identifying a product version for each product feature in the plurality of product features; and
generating a template video for the product version from the data associated with each product feature having the identified product version.
9 . The computer system of claim 8 , further comprising:
determining that a product feature in the set of product features for the request does not include the product version for the template video;
identifying a change to the template video based on the product feature; and
modifying the template video based on an identified change to the template video.
10 . The computer system of claim 9 , wherein the modifying the template video includes removing a video frame associated with the product feature from the template video, wherein the product feature is determined to be an obsolete product feature.
11 . The computer system of claim 9 , wherein a machine learning model that predicts video context based on content in a video is used to identify the change to the template video.
12 . The computer system of claim 8 , further comprising storing the plurality of product features in a product feature database, wherein the product feature database associates each product feature in the plurality of product features with the data of a respective product feature and the product version for the respective product feature.
13 . A computer program product for automated generation of adaptive instructional product videos to indicate how a product is used based on requested feature sets in stored data, the computer program product comprising:
a computer-readable storage device having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
acquiring a plurality of product features from a server, wherein each product feature in the plurality of product features is associated with data selected from a group consisting of: text data, audio data, and image data;
receiving a request for an instructional product video, wherein a product in the instructional product video comprises a set of product features in the plurality of product features, the request for the product video including a request to view instructions to utilize a specific version of a manufacturer's product or to view a specific product feature;
identifying the data associated with each product feature in the set of product features for the request for the instructional product video;
generating the instructional product video using a generative adversarial neural network (GAN) based on identified data for the product, the instructional product video including frames showing the requested version of the manufacturer's product or the specific product feature;
acquiring a plurality of updated or revised product features from the server, the updated or revised product features associated with an update to the specific version of the manufacturer's product or the specific product feature; and
generating an updated instructional product video, the updated instructional product video including frames showing the updated or revised product feature associated with the update to the specific version of the manufacturer's product or the specific product feature and instructions how to use the updated specific version of the manufacturer's product or the updated specific product feature.
14 . The computer program product of claim 13 , further comprising:
identifying a product version for each product feature in the plurality of product features; and
generating a template video for the product version from the data associated with each product feature having the identified product version.
15 . The computer program product of claim 14 , further comprising:
determining that a product feature in the set of product features for the request does not include the product version for the template video;
identifying a change to the template video based on the product feature; and
modifying the template video based on an identified change to the template video.
16 . The computer program product of claim 15 , wherein the modifying the template video includes removing a video frame associated with the product feature from the template video, wherein the product feature is determined to be an obsolete product feature.
17 . The computer program product of claim 15 , wherein a machine learning model that predicts video context based on content in a video is used to identify the change to the template video.