Entity Scoring System for Search Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face inefficiencies in finding suitable entities to obtain items due to lack of awareness of available entities and information, leading to unsatisfactory search results and inefficient relationships management within organizations.
Innovation Solution
A system that uses a machine learning model to generate an entity list by processing identifying markers associated with query items, calculating similarity distances, and ranking entities based on scenario scores, allowing users to find the best-matched entities for their needs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional search techniques comparing terms in search queries to terms in potential results are used, then the search process is simple and fast, but the search accuracy and credibility of results deteriorate when results are from unfamiliar or non-credible sources
Solution Approach 1:
The patent introduces an intermediary entity scoring system that mediates between the search query and potential results. This intermediary layer calculates credibility scores for sources and combines them with term matching scores to produce weighted search results, thereby improving search accuracy while maintaining a manageable process through automated scoring mechanisms.
Solution Approach 2:
The patent changes the evaluation parameters from simple term matching to a multi-parameter scoring system that includes term similarity, source credibility, and entity scores. This transformation allows the system to differentiate between results from credible and non-credible sources, improving search accuracy without excessive complexity through structured parameter weighting.
2Productivity
If users manually search for entities to obtain items, then the search process is straightforward, but the time consumption and efficiency deteriorate due to lack of awareness of available entities
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing entity profiles with identifying markers and scenario scores before search queries are submitted. When a search is performed, the system quickly retrieves and matches these pre-prepared profiles against the query, dramatically reducing search time while improving productivity through advance preparation of entity data.
Solution Approach 2:
The patent creates simplified copies of entity information in the form of entity profiles containing key identifying markers and scenario scores. These copied profiles enable rapid comparison and matching without requiring users to examine complete entity details, thus reducing time loss while maintaining finding efficiency through streamlined information representation.
3Reliability
If organizations manage entity relationships without a systematic approach, then the management process is simple, but the quality of relationships and ability to find suitable entities deteriorates
Solution Approach 1:
The patent segments entity management into distinct components: entity profiles with identifying markers, scenario-specific scoring systems, and relationship matching algorithms. This segmentation improves relationship management quality by allowing targeted optimization of each component while keeping overall system complexity manageable through modular architecture and clear separation of concerns.
Data Source
AI summary
A processor may receive a request for a query item may include a plurality of identifying markers, relating to data associated with the query item. A machine learning model, trained to identify similar items according to the plurality of identifying markers, may then process the plurality of identifying markers and provide a list of one or more similar items and respective similarity distances. The processor may access a respective entity profile including one or more scenario scores for each of the similar items. The processor may then calculate an entity score for each respective entity profile using the respective similarity distances and the scenario scores. The processor may then generate an entity list by ranking the respective entities associated with each respective entity profile using the entity score. The processor may then output the entity list to the client device.