Entity Search System with Industry Sector Derivation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search technologies fail to provide a searching experience similar to consulting a human expert, particularly in determining industry sectors from user queries, asking relevant questions, and rewriting queries for effective search results across various industries like online retail, healthcare, and real estate.
Innovation Solution
A search system that derives industry sector information from user queries, solicits additional information through relevant questions, and rewrites queries to facilitate searching, using techniques such as segmentation, normalization, and industry-specific knowledge to guide the search process and present relevant results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a typical search engine is used to search for entities with conversational queries, then the search system is simple and easy to operate, but it cannot return helpful results for complex information needs
Solution Approach 1:
The patent introduces an intermediary processing layer between the user's conversational query and the search engine. This intermediary includes components that segment the query, determine industry sectors, derive additional questions, and rewrite the query into a format suitable for search engines. This mediator transforms the simple conversational input into a structured, multi-component search strategy that maintains ease of use while improving result quality.
Solution Approach 2:
The patent segments the conversational query into multiple components: initial query segmentation, identification of industry sector, derivation of additional questions, and rewriting into formatted search queries. By breaking down the complex information need into manageable segments, the system can process each aspect separately and combine results to provide comprehensive answers.
2Measurement precision
If the search system asks multiple additional questions to derive industry sector information, then the search result accuracy is improved, but the search time and user interaction complexity increase
Solution Approach 1:
The patent performs preliminary actions by pre-defining industry sector categories and pre-establishing relationships between queries and sectors. When a user submits a query, the system quickly matches it against predefined patterns and sectors rather than conducting extensive analysis from scratch. This preliminary preparation reduces the time needed for accurate industry sector identification.
Solution Approach 2:
The system uses feedback mechanisms where the results from initial query processing inform subsequent question generation. The system analyzes the initial query, determines what industry sector information is needed, and selectively asks only the necessary additional questions rather than a fixed set of all possible questions. This feedback-driven approach minimizes interaction time while maintaining accuracy.
3Adaptability or versatility
If the system rewrites queries to facilitate searching across multiple industries, then the search coverage and relevance are improved, but the query processing complexity increases
Solution Approach 1:
The patent creates a universal query rewriting framework that handles multiple industries and search scenarios through a single system. The same core components (segmentation, industry sector determination, question derivation, rewriting) are applied across different industries such as real estate, healthcare, retail, and professional services. This multi-functional approach achieves broad search coverage without requiring separate specialized systems for each industry.
Solution Approach 2:
The system changes parameters of the query based on the determined industry sector. Different industries have different relevant parameters and search strategies - for example, real estate queries may focus on location and property type parameters, while healthcare queries may focus on service type and provider credentials. The system dynamically adjusts query parameters based on the identified industry context, enabling versatile search coverage.
Data Source
AI summary
Methods and apparatus that deliver a searching experience that is substantially akin to consultation with a human expert, and that satisfies a user's information need in fulfilling projects such as purchasing, shopping, procurement, bartering, requesting for quotes, in online retail, traditional retail, wholesale, health care, travel, real estate, restaurant-going, entertainment, logistics, and sourcing are disclosed. Search results often contain entities that provide services and products. Records being searched are associated with industry sectors in a broad sense. Industry sector information is first derived from a user query; and is used in determining relevant and adequate additional questions for a searcher, and in matching, ranking, and presenting search results.