Hashing-based effective user modeling

Abstract

In one embodiment, a method includes receiving user behavior data and contextual information associated with the user behavior data, the contextual information including a first data portion associated with a first context type. The method includes generating, from the user behavior data and the contextual information using a hashing algorithm, a first heterogeneous hash code including a first portion representing the user behavior data and a second hash code portion representing the first data portion associated with the first context type. The method includes accessing a second heterogeneous hash code including a third hash code portion representing a second data portion associated with the first context type. The method includes comparing the first heterogeneous hash code with the second heterogeneous hash code including determining similarity between the second hash code portion of the first heterogeneous hash code and the third hash code portion of the second heterogenous hash code.

Description

technical field [0001] The present disclosure generally relates to user activity modeling and similarity searching. Background technique [0002] In big data systems for advertising and marketing, finding and ranking similar groups of users (this is called nearest neighbor search) is a key task, especially for tasks such as lookalike search, user segmentation, etc. (user segmentation) and recommendation applications. Many types of modern devices, including TVs and mobile devices, have detailed profiles of users' interaction history with content, such as live TV, video-on-demand, games, apps, and external devices, which can be used to calculate the interaction between users. similarity, and finally calculate their "nearest neighbors". However, such a task is computationally expensive due to the large-scale nature of such data, which may involve tens of millions of users with constantly updated interaction histories, each spanning millions of sessions over time. [0003] On...

AI Technical Summary

Problems solved by technology

However, such a task is computationally expensive due to the large-scale nature of such data (which may involve tens of millions of users with constantly updated interaction histories, each spanning millions of sessions over time).

Images