Semantic And User Embeddings for Tenant-Configurable Hybrid Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines struggle to provide highly personalized and relevant search results due to reliance on term frequency and basic embeddings, failing to account for user preferences and semantic similarity.
Innovation Solution
A predictive feedback and semantic engine (PFSE) that utilizes tenant- and user-specific embeddings, leveraging deep learning and neural networks to merge personalization, semantic sense, and predictive analytics, creating a highly configurable and scalable search system with improved relevancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If term frequency is used to determine search result relevancy, then the search system is simple to implement, but the search relevancy is sub-optimal and cannot provide personalized results
Solution Approach 1:
The patent transforms the search relevancy determination from simple term frequency counting to a complex multi-parameter evaluation system using neural networks. The system changes parameters including user preference vectors, semantic embeddings, and interaction history weights to dynamically calculate relevancy scores, thereby improving measurement precision while accepting increased system complexity
Solution Approach 2:
The patent replaces the mechanical term frequency counting mechanism with a neural network-based semantic analysis system. Instead of mechanically counting term occurrences, the system uses deep learning models to understand semantic meaning, user intent, and contextual relevance, substituting simple mechanical operations with intelligent computational processes
2Measurement precision
If word embeddings are used to provide semantic search results, then the search system understands semantic meaning, but the results are not highly personalized to user preferences
Solution Approach 1:
The patent segments the search system into multiple specialized components: a semantic embedding module for understanding meaning, a user profile module for capturing preferences, an interaction history module for learning behavior patterns, and a predictive feedback engine for synthesizing personalized results. This segmentation allows each component to specialize while working together to achieve high personalization accuracy
Solution Approach 2:
The patent performs preliminary actions by pre-training neural network models on large corpora of user interaction data before deployment. User profiles and preference vectors are constructed in advance through continuous learning from interaction history, so that when search queries are processed, the system already has personalized models ready to generate highly relevant results
Data Source
AI summary
In some implementations, the techniques described herein relate to a method including: loading, by a processor, a predictive model, the predictive model including a first set of hidden layers; loading, by the processor, a semantic model, the semantic model including a second set of hidden layers; generating, by the processor, a tenant model using the first set of hidden layers and a third set of hidden layers, the third set of hidden layers receiving, as input, an output of the first set of hidden layers; loading, by the processor, a tenanted training data set; training, by the processor, the tenant model by biasing the first set of hidden layers with the second set of hidden layers and training weights of at least the third set of hidden layers using the tenanted training data set; and building, by the processor, an embedding index using the tenant model.