IP Library Granted Patent US 12699535
Granted Patent B2
US 12699535 · App. 18/205,935 · Granted Aug 4, 2026

Social media content creator

Inventor: Shiva Chintaluru (Hyderabad, IN)
Assignee: Microsoft Technology Licensing, LLC
G06Q10/40G06F3/04842G06F3/14G10L13/02
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12699535
App. No.
18/205,935
Granted
Aug 4, 2026
Kind
B2
Abstract

Systems and methods are directed to generating a social media post. The system receives, via a post generation user interface (UI) implemented by a post generation component executing on a mobile device, an indication to generate a post on a topic for a networking platform. The system obtains, from a generative artificial intelligence system, text for the post based on the topic and the networking platform. A plurality of images are displayed and a selection of one or more images of the plurality of images is received. Using the selected one or more images, the system generates a video by applying transition effects to the selected one or more images. A preview of the post including the video on the post generation UI is presented on the mobile device. In response to an indication to share the post, the system publishes the post to the networking platform.

Claims (76)

1 . A method for machine-generating posts that are formatted differently for different networking platforms based on corresponding posting requirements, the method comprising:

receiving, via a post generation user interface (UI) implemented by a post generation component executing on a mobile device of a user, an indication to generate a post on a topic for a networking platform of the different networking platforms;

obtaining, from a generative artificial intelligence system, text for the post tailored to the networking platform, the obtaining being triggered by an application programming interface (API) call to the generative artificial intelligence system, the API call including an indication of the topic, an indication of the networking platform, and any applicable user preferences, the generative artificial intelligence system customizing the text based on the topic, the user preferences, and posting requirements of the networking platform;

causing display of a plurality of images associated with the topic;

receiving a selection of one or more images of the plurality of images;

using the selected one or more images, generating, by a video component, a video, the generating comprising:

selecting a video template based on the networking platform and a number of the selected one or more images;

retrieving, from a database of video templates, the selected video template associated with the networking platform, the selected video template comprising instructions for generating the video including an amount of time to display each image of the one or more images before an image transition and a transition effect to apply at each image transition between the one or more images; and

applying the amount of time to display each image and the transition effect to each image transition;

generating, by a preview component, a preview of the post by formatting a size and length of the video based on the posting requirements of the networking platform and incorporating the formatted video with the text, the posting requirements including a size requirement, a pixel requirement, and a length requirement specific to the networking platform, the formatting producing a video that complies with the posting requirements without requiring manual post-processing;

causing presentation of the preview of the post on the post generation UI; and

in response to an indication to share the post, causing the post to be published to the networking platform.

2 . The method of claim 1 , further comprising:

receiving an indication of activation of the post generation component;

in response to receiving the indication of the activation of the post generation component, determining custom prompts to display on the post generation UI, the custom prompts providing selectable suggestions for the topic; and

causing display of a first set of the custom prompts on the post generation UI, the first set of the custom prompts displayed prior to any user input being received via the post generation UI.

3 . The method of claim 2 , wherein determining the custom prompts comprises:

accessing a profile of a user using the post generation component;

based on the profile, determining one or more subject matters associated with the user; and

ranking the one or more subject matters, the ranked one or more subject matters being used to generate the custom prompts.

4 . The method of claim 2 , wherein the first set comprises a top ranked number of custom prompts, the method further comprising:

based on a selection of a custom prompt from the first set, causing a next ranked custom prompt not included in the first set to replace the selected custom prompt on the post generation UI.

5 . The method of claim 1 , wherein causing display of the plurality of images comprises:

accessing, via the post generation component executing on the mobile device, images captured and stored on the mobile device; and

identifying stored images on the mobile device that are related to the topic for display.

6 . The method of claim 1 , wherein causing display of the plurality of images comprises:

triggering the post generation component to interact with a camera application on the mobile device to capture a live image and display the captured live image.

7 . The method of claim 1 , wherein causing display of the plurality of images comprises generating, by an image generation application or a generative artificial intelligence system, an image based on the topic.

8 . The method of claim 1 , further comprising:

receiving an indication of a time to share the post; and

scheduling the post to be published to the networking platform at the indicated time.

9 . The method of claim 8 , further comprising:

accessing machine-learned data indicating suggested times to share the post; and

causing display of one or more suggested times to share the post from which the indication of time is selected.

10 . The method of claim 1 , further comprising incorporating a machine-generated voice-over based on the text, the incorporating the machine-generated voice-over comprising:

generating speech based on the text for the post; and

incorporating the speech as the voice-over to the video.

11 . The method of claim 1 , wherein the transition effect is selected from a set including zoom in, zoom out, fade in, fade out, and morph effects to apply at each image transition between the one or more images.

12 . A system comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations for machine-generating posts that are formatted differently for different networking platforms based on corresponding posting requirements, the operations comprising:

receiving, via a post generation user interface (UI) implemented by a post generation component executing on a mobile device of a user, an indication to generate a post on a topic for a networking platform of the different networking platforms;

obtaining, from a generative artificial intelligence system, text for the post tailored to the networking platform, the obtaining being triggered by an application programming interface (API) call to the generative artificial intelligence system, the API call including an indication of the topic, an indication of the networking platform, and any applicable user preferences, the generative artificial intelligence system customizing the text based on the topic, the user preferences, and posting requirements of the networking platform;

causing display of a plurality of images associated with the topic;

receiving a selection of one or more images of the plurality of images;

using the selected one or more images, generating a video the generating comprising:

selecting a video template based on the networking platform and a number of the selected one or more images;

retrieving, from a database of video templates, the selected video template associated with the networking platform, the selected video template comprising instructions for generating the video including an amount of time to display each image of the one or more images before an image transition and a transition effect to apply at each image transition between the one or more images; and

applying the amount of time to display each image and the transition effect to each image transition to generate the video;

generating, by a preview component, a preview of the post by formatting a size and length of the video based on the posting requirements of the networking platform and incorporating the formatted video with the text, the posting requirements including a size requirement, a pixel requirement, and a length requirement specific to the networking platform, the formatting producing the formatted video that complies with the posting requirements without requiring manual post-processing;

causing presentation of the preview of the post on the post generation UI; and

in response to an indication to share the post, causing the post to be published to the networking platform.

13 . The system of claim 12 , wherein the operations further comprise:

receiving an indication of activation of the post generation component;

in response to receiving the indication of the activation of the post generation component, determining custom prompts to display on the post generation UI, the custom prompts providing selectable suggestions for the topic; and

causing display of a first set of the custom prompts on the post generation UI, the first set of the custom prompts displayed prior to any use input being received via the post generation UI.

14 . The system of claim 12 , wherein causing display of the plurality of images comprises:

triggering the post generation component to interact with a camera application on the mobile device to capture a live image and display the captured live image.

15 . The system of claim 12 , wherein the operations further comprise:

receiving an indication of a time to share the post; and

scheduling the post to be published to the networking platform at the indicated time.

16 . The system of claim 15 , wherein the operations further comprise:

accessing machine-learned data indicating suggested times to share the post; and

causing display of one or more suggested times to share the post from which the indication of time is selected.

17 . A machine-storage medium comprising instructions which, when executed by one or more processors of a machine, cause the machine to perform operations for machine-generating posts that are formatted differently for different networking platforms based on corresponding posting requirements, the operations comprising:

receiving, via a post generation user interface (UI) implemented by a post generation component executing on a mobile device of a user, an indication to generate a post on a topic for a networking platform of the different networking platforms;

obtaining, from a generative artificial intelligence system, text for the post tailored to the networking platform, the obtaining being triggered by an application programming interface (API) call to the generative artificial intelligence system, the API call including an indication of the topic, an indication of the networking platform, and any applicable user preferences, the generative artificial intelligence system customizing the text based on the topic, the user preferences, and posting requirements of the networking platform;

causing display of a plurality of images associated with the topic;

receiving a selection of one or more images of the plurality of images;

using the selected one or more images, generating a video, the generating comprising:

selecting a video template based on the networking platform and a number of the selected one or more images;

retrieving, from a database of video templates, the selected video template associated with the networking platform, the selected video template comprising instructions for generating the video including an amount of time to display each image of the one or more images before an image transition and a transition effect to apply at each image transition between the one or more images; and

applying the amount of time to display each image and the transition effect to each image transition to generate the video;

generating, by a preview component, a preview of the post by formatting a size and length of the video based on the posting requirements of the networking platform and incorporating the formatted video with the text, the posting requirements including a size requirement, a pixel requirement, and a length requirement specific to the networking platform, the formatting producing the formatted video that complies with the posting requirements without requiring manual post-processing;

causing presentation of the preview of the post on the post generation UI; and

in response to an indication to share the post, causing the post to be published to the networking platform.