Weighted Section Search Profiles for Patent Document Retrieval

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing electronic intellectual property document search tools do not efficiently support different classes of searches, such as novelty, product clearance, and invalidity searches, as they require manual section selection by the searcher, increasing the burden with growing databases and lacking in accuracy.

Innovation Solution

A method and system that create search profiles by assigning weights to sections of intellectual property documents, allowing for selective emphasis on specific sections based on search types, with the option for secondary weights and hierarchical structures to refine search results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual section selection is used by searchers, then search scope can be limited, but the burden on searchers increases and accuracy decreases

Engineering Contradiction:
Improvesearcher burdenVSAvoidsearch accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs preliminary actions by automatically identifying and weighting relevant document sections before the search is executed. Search profiles pre-configure which sections (claims, specification, drawings) should be emphasized, eliminating the need for searchers to manually select sections and ensuring consistent, accurate section weighting across all searches.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The search system serves itself by automatically analyzing and weighting document sections based on pre-configured search profiles. The system autonomously determines which sections are most relevant to the search query without requiring manual intervention from searchers, thereby reducing searcher burden while maintaining or improving search accuracy.

Inventive Principle:
Principle #25Self-service

2Reliability

If all document sections are reviewed, then comprehensive search results are achieved, but search time and resources increase with growing databases

Engineering Contradiction:
Improvesearch comprehensivenessVSAvoidsearch time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system applies local quality by assigning different weights to different sections of patent documents based on their relevance to specific search types. Instead of uniformly reviewing all sections, the system emphasizes locally important sections (e.g., claims for novelty searches, specification for invalidity searches), achieving comprehensive results in less time by focusing computational resources on the most relevant areas.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If section weights are assigned based on search type, then search relevance is improved, but system complexity increases

Engineering Contradiction:
Improvesearch relevanceVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system implements dynamics by making section weights adjustable and search-profile-specific rather than fixed. Different search types (novelty, invalidity, clearance) have different pre-configured weightings for various document sections, allowing the system to dynamically adapt to different search requirements while maintaining manageable complexity through automation and pre-configuration.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP2427830B1Method, system, and apparatus for searching an electronic document collection
Publication Date: 2015.06.24 CPA SOFTWARE
  • EP2427830B1 patent drawingFigure 1
  • EP2427830B1 patent drawingFigure 2
  • EP2427830B1 patent drawingFigure 3

AI summary

A method, system, and article are provided for efficiently and effectively searching an electronic document collection. Each of the documents in the collection is pre-divided into sub-sections. One or more profiles are created, with each profile including a selection of one or more of the sections of the documents in the collection. In addition, a weight is assigned to each of the selected sections in the profile. Based upon the parameters of a query and selection of a profile, select sub-sections of each document are employed in a comparison of query data to the underlying document collection. A compilation of documents is created based upon all documents with data matching the query data within the sections of the document as identified in the submitted profile.