Product Summary Generator Using Assertion Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current systems fail to generate naturally reading narrative product summaries and recommendations, requiring significant time and resources, and lack the ability to automatically update summaries as product attributes change or provide comparable alternative products.

Innovation Solution

A product summary generator that determines attributes of a selected product, retrieves assertion models to describe the product naturally, and generates a narrative summary, including recommendations for alternative products, while also updating summaries based on changes in product attributes and market conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual evaluation and writing of product summaries is used, then the quality and natural reading of summaries is improved, but the time and resources required increase significantly

Engineering Contradiction:

Improvequality of product summaryVSAvoidtime required for summary generation

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system uses template-based generation where pre-defined summary templates are filled with product data to create natural-sounding summaries automatically, replicating the structure and style of manual reviews without requiring actual human writing for each product

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system dynamically adjusts summary parameters such as tone, detail level, and highlighting based on product attributes and category-specific templates, allowing automated generation that adapts to different product types while maintaining quality consistency

Inventive Principle:

Principle #35Parameter changes

2Loss of information

If comprehensive product information is provided for all attributes, then the completeness of product data is improved, but the complexity of presenting and processing this information increases

Engineering Contradiction:

Improvecompleteness of product informationVSAvoidcomplexity of information processing

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system divides comprehensive product information into discrete attribute categories (price, features, specifications) and processes each segment separately through dedicated templates, making the overall complex information manageable and systematically generated

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The template system acts as an intermediary layer that translates raw product data into natural language summaries, mediating between the complexity of comprehensive product attributes and the simplicity of readable narrative output

Inventive Principle:

Principle #24Intermediary (Mediator)

3Device complexity

If static product summaries are used, then the simplicity of the system is maintained, but the ability to adapt to changing product attributes and market conditions is reduced

Engineering Contradiction:

Improvesimplicity of summary systemVSAvoidadaptability to product changes

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The template system is designed to be dynamically configurable, allowing templates and their parameters to be updated automatically as product attributes change, enabling the system to adapt to new products and market conditions without requiring system redesign

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms where product data automatically triggers appropriate template selection and parameter adjustment, allowing the summary generation to respond to changing product attributes in real-time while maintaining systematic simplicity

Inventive Principle:

Principle #23Feedback

4Adaptability or versatility

If alternative product recommendations are added to summaries, then the usefulness for consumer decision-making is improved, but the length and detail of the summary increases

Engineering Contradiction:

Improveusefulness for purchasing decisionsVSAvoidlength of product summary

Core Design Contradiction:

Adaptability or versatilityVSLength of moving object

Solution Approach 1:

The system provides alternative product recommendations selectively based on the main product's standout features or weaknesses, only adding comparison information when it adds value to the decision-making process rather than universally including all possible comparisons

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS8019656B2System and method for generating an alternative product recommendation

Publication Date: 2011.09.13 CBS INTERACTIVE INC

AI summary

A method and system for automatically generating a self-updating naturally-reading narrative product summary including assertions about a selected product. In one embodiment, the system and method includes evaluating an existing narrative product summary, comparing an existing attribute name, attribute value, attribute unit, and assertion model, respectively, to a current attribute name, attribute value, attribute unit, and assertion model to determine if one of the comparisons shows a change. The system and method further determines a new attribute associated with the selected product, selects an alternative product, retrieves a new assertion model with assertions that describe the selected product and identify an alternative product in a natural manner. The system and method then generates a naturally-reading narrative product summary by combining the new attribute with the new retrieved assertion model, and by combining the selected alternative product with another retrieved assertion model to recommend the selected alternative product in the narrative.