Product Citation Identification via Entity Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for creating databases that rank products by citations, such as the CiteAb database, face challenges in efficiently identifying product citations across large numbers of documents, requiring extensive manual labor and time due to the need to individually search each document for multiple product identifiers.
Innovation Solution
A computer-implemented method and system that uses a two-stage process to identify product citations, first by searching for an entity identifier and then applying a regular expression to a targeted text portion to determine if products from a catalogue are cited, significantly reducing search time and computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional searching techniques are used to individually search each document for each product in a product catalogue, then complete citation identification is achieved, but search time becomes excessively long and becomes impractical for large product catalogues
Solution Approach 1:
The patent segments the search process into two distinct stages: first identifying entity identifiers (supplier names) in documents, then searching for product identifiers only within the context of those entities. This segmentation transforms a single exhaustive search into a targeted two-phase approach, dramatically reducing the search space while maintaining complete citation identification.
Solution Approach 2:
The patent performs preliminary action by first identifying and extracting entity identifiers (supplier names) from documents before conducting the actual product citation search. This preliminary step creates a focused search context, allowing subsequent product identifier searches to be confined to relevant portions of documents associated with specific suppliers, thereby reducing overall search time.
2Productivity
If a two-stage process is used to first identify entity identifiers and then apply regular expressions to target text, then search speed is significantly improved, but the process complexity increases
Solution Approach 1:
The patent employs regular expressions as a universal tool that serves multiple functions: identifying entity identifiers, defining target text portions, and matching product identifiers. This multi-functionality reduces the need for separate specialized tools for each search stage, simplifying the overall system while maintaining high search speed.
Solution Approach 2:
The patent creates a simplified representation of the search problem by using regular expressions to capture patterns of entity identifiers and product identifiers. Instead of implementing complex logic to recognize each specific supplier name or product code, the system copies the structural patterns of these identifiers into regex templates, enabling fast pattern matching without complex decision-making processes.
3Measurement precision
If manual review of documents is performed to find product citations, then accurate citation identification is achieved, but extensive labor and time are required
Solution Approach 1:
The patent enables the system to automatically identify and extract product citations without human intervention. By using regular expressions to recognize patterns of entity identifiers and product identifiers, the system serves itself in identifying citations, eliminating the need for manual review while maintaining high accuracy. The system automatically validates matches against product catalogues and generates citation data.
Data Source
AI summary
A computer-implemented method for identifying a product citation in a document, the method comprising searching, in the document, for an entity identifier corresponding to an entity and, if an instance of the entity identifier is detected in the document, determining a portion of the document around the instance of the entity identifier as a target text, wherein the entity is associated with a product catalogue, the product catalogue comprising a plurality of product identifiers; applying a first regular expression to the target text, wherein the first regular expression is configured to match one or more of the plurality of product identifiers; and if a product identifier from the plurality of product identifiers is determined to be cited in the target text, adding an entry to a citation database linking the document and the product identifier.