SYSTEMS AND METHODS FOR GENERATING CONTENT ITEMS VIA MACHINE LEARNING - Technological field and brief summary

Aug 4, 2026

Systems and methods generate a content model and recommendations tied to an online presence. The approach receives indications of user inputs, such as interactions with posts, photos, videos, websites, online shops, reels, or stories, then extracts interests from the received content. A machine learning module derives a set of characteristics and learns associations between user interaction with one or more content items and those characteristics. Recommendations may include product or content promotions and can be delivered via advertisements, profiles, or other online presence generated through machine learning.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages37

Reading Time1 h 33 min

AccessFree to download

Technological Field

Background

Brief Summary

Interest Extraction and Characteristics

Recommendation Generation

Technical Disclosure Commons Defensive Publications Series July 2023 SYSTEMS AND METHODS FOR GENERATING CONTENT ITEMS VIA MACHINE LEARNING Follow this and additional works at: [https://www.tdcommons.org/dpubs_series](https://www.tdcommons.org/dpubs_series) Recommended Citation "SYSTEMS AND METHODS FOR GENERATING CONTENT ITEMS VIA MACHINE LEARNING", Technical Disclosure Commons,(July 27, 2023) [https://www.tdcommons.org/dpubs_series/6080](https://www.tdcommons.org/dpubs_series/6080) This work is licensed under a Creative Commons Attribution 4.0 License. This Article is brought to you for free and open access by Technical Disclosure Commons. It has been accepted for inclusion in Defensive Publications Series by an authorized administrator of Technical Disclosure Commons. SYSTEMS AND METHODS FOR GENERATING CONTENT ITEMS VIA MACHINE LEARNING TECHNOLOGICAL FIELD [0001] The present disclosure generally relates to systems and methods for generating content. BACKGROUND [0002] An online presence may include content interacted with or posted by a user on a platform. Such content may include products and items associated with a brand, an activity of interest, and the like. Such information may be useful to advertisers, especially when an advertised product may relate to one or more items featured in content that was posted or interacted with. Further, advertisers are increasingly soliciting platforms with a large number of users to promote their products or content. Knowing the association between the online presence of an advertisers target audience and the product or content may be an important criterion for advertisers. However, current advertising technology may face significant challenges for advertisers with respect to determining such associations, and otherwise using an online presence to identify potential products of interest to specific users. BRIEF SUMMARY [0003] Various systems, methods, and devices are described for generating a content model and recommendations in association with an online presence. In some examples, the content model may be an advertisement model or any other suitable content model for recommending content items. Recommendations may include product recommendations, presented as content (e.g., an advertisement(s) (e.g., product ads, content ads, or the like)) or other promotion to a user, an online profile, or any other suitable type of online presence which may be generated by machine learning. [0004] In various examples, systems and methods may receive an indication of a user’s input associated with the user, such as interactions with a post(s), photo(s), video(s), website(s), online shop(s), reel(s), or one or more stories. An interest extraction module may determine an interest associated with the received input. A machine learning module may develop a set of Published by Technical Disclosure Commons, 2023 2 characteristics associated with the interest (e.g., user frequently interacts with content associated with shoes). The machine learning model may utilize a neural network to develop an association between user interaction with a first content item(s) (e.g., a post, a video, a photo, reel, story, a website, an online marketplace, an online shop, or any suitable content item(s) or combination thereof) and a characteristic. A recommendation may be generated based on an association between the set of characteristics and the content item(s). A machine learning module, which may be the same or different machine learning module may generate the recommendation. The content items may include content associated with a platform (e.g., an interactive platform) . In various examples, a report identifying a user profile, of the online presence may assist in identifying targeted user-generated content (UGC) or content for promotion (e.g., a recommendation) via an interactive platform. [0005] In various examples, the interest extracti

FAQs

What inputs does the system use to generate content item recommendations?

The system receives user-related input indications such as interactions with posts, photos, videos, websites, online shops, reels, stories, and similar online content.

How does the system extract user interests and transform them into usable data?

An interest extraction module determines interests associated with the input, such as clothing items, brands, activities, items, sounds, songs, foods, scenes, individuals, and stores, then derives characteristics related to those interests.

How are recommendations generated and delivered to users or content providers?

A machine learning module learns associations between interaction with content items and the extracted characteristics, then generates recommendations that may be presented as ads, profile-based promotions, or other online presence outputs via device interfaces.

Aug 4, 2026

Upload by Lucas Martin