Predicted popularity of digital entities

Abstract

Presentation of relevant and predicted popular digital entities to users in a content feed is provided. Aspects of predicting popular systems use one or more predictive models, such as neural networks or regression models, to generate digital entities (e.g., documents, people, electronic communications, meetings, locations, digital images, digital videos, digital audio, etc.) for predicting popular scores. By considering trends and context, predictive popularity systems calculate future popularity scores for digital entities and determine which digital entities are relevant to a given user and likely to become popular around the user and people in the user's network in the future. The predictive hotspot system curates digital entities that are determined to be relevant and predicted to be popular around the user and presents the digital entities in the content feed.

Description

technical field [0001] The present invention relates to automated systems and methods for presenting relevant and predicted popular digital entities to users in content feeds. Background technique [0002] Information workers / users have become accustomed to generating, editing, viewing and receiving large volumes of electronic documents and other information (eg, electronic communications, images, data, etc.). In an enterprise situation, such as a company, school, social network, etc., a given user may encounter hundreds (or more) of documents or other information items, each of which has a different meaning to the information worker. degree of relevance, interest, or importance, and is often spread across various workloads and storage systems (e.g., email, social feeds, intranet sites, network file systems, etc.). Therefore, it can be time-consuming and inefficient for users to search for content related to them. In addition, users are likely to be less aware of people an...

AI Technical Summary

Problems solved by technology

Therefore, it can be time-consuming and inefficient for users to search for content related to them

In addition, users are likely to be less aware of people and information items that may be popular around them based on trends, such as people with whom the user's colleagues are likely to collaborate, documents with which the user's colleagues are likely to interact, information items that the user's colleagues may receive Emails, meetings that the user's colleagues may attend, etc.

Images