Search Query Substitution Vector Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines face challenges in accurately identifying and eliminating bad contexts for substitution rules, which can lead to unreliable or spurious substitute terms, affecting the accuracy of query revisions and increasing data processing complexity.
Innovation Solution
The method involves constructing vectors of co-occurrence frequencies for terms in search queries and comparing them to evaluate the goodness of candidate substitute terms and contexts, with a scoring system that weights significant changes in co-occurrence frequencies to determine the importance of terms and designate bad contexts, thereby improving substitution rule accuracy and reducing data collection for unhelpful contexts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If query revision engines evaluate candidate substitute terms using co-occurrence frequencies to improve substitution accuracy, then the reliability of substitute terms improves, but the data processing complexity and computational resources increase
Solution Approach 1:
The patent segments the evaluation process into distinct phases: constructing co-occurrence vectors from search query data, comparing vectors to identify substitute terms, and evaluating contexts separately. This segmentation allows the system to process and manage complex evaluations in manageable stages, reducing overall computational complexity while maintaining reliability.
Solution Approach 2:
The patent performs preliminary actions by pre-computing and storing co-occurrence frequency vectors for terms in the search index. These pre-computed vectors are then reused during query processing, avoiding redundant calculations and significantly reducing real-time data processing complexity while maintaining high substitution reliability.
2Measurement precision
If the system collects and processes data from all contexts to ensure comprehensive evaluation, then the accuracy of substitution rules improves, but the quantity of data to be processed increases
Solution Approach 1:
The patent applies local quality by evaluating and weighting different contexts differently based on their relevance and informativeness. Not all contexts are treated equally - the system identifies and focuses on high-quality contexts that provide meaningful signals for substitution, while reducing or eliminating processing of low-quality or redundant contexts.
Solution Approach 2:
The patent extracts and focuses on the most relevant features from the data - specifically, co-occurrence frequencies of terms within defined contexts. By extracting only the essential information needed for substitution evaluation rather than processing all raw context data, the system maintains accuracy while reducing data volume.
3Reliability
If the system evaluates and eliminates bad contexts to improve substitution rule accuracy, then the reliability of query revisions improves, but the complexity of context evaluation increases
Solution Approach 1:
The patent implements feedback mechanisms where the system evaluates contexts, identifies bad or unhelpful contexts, and uses this information to refine future evaluations. The feedback loop allows the system to learn from past performance and progressively improve context evaluation accuracy, reducing the complexity of identifying bad contexts over time.
Solution Approach 2:
The patent changes evaluation parameters by using co-occurrence frequency vectors as a quantitative measure of context quality. By transforming qualitative context assessment into quantitative vector comparisons with measurable parameters, the system objectively identifies bad contexts and eliminates subjectivity, simplifying the evaluation process while improving reliability.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for evaluating substitute terms. One of the methods includes selecting a first term and a second term. A first co-occurrence frequency is determined for co-occurring terms in search queries that include the first term. A first vector is generated for the first term using the first co-occurrence frequencies. A second co-occurrence frequency is determined for the co-occurring terms in the search queries that include the first term adjacent to the second term. A second vector is generated for the second term using the second co-occurrence frequencies. A score for the second term as a context for a substitution rule based on the first term is computed, wherein the score is based on a comparison between the first vector and the second vector.